Search
Find a vulnerability
Search criteria
12 vulnerabilities found for MCP Toolbox for Databases (googleapis/mcp-toolbox) by Google
CVE-2026-16481 (GCVE-0-2026-16481)
Vulnerability from nvd – Published: 2026-07-27 19:13 – Updated: 2026-07-27 19:35
VLAI
EPSS
VEX
Title
Server-Side Request Forgery (SSRF) and Credential Exfiltration in googleapis/mcp-toolbox cloud-healthcare-fhir-fetch-page Tool
Summary
A Server-Side Request Forgery (SSRF) and credential exfiltration vulnerability exists in the cloud-healthcare-fhir-fetch-page tool of googleapis/mcp-toolbox.
The tool takes an unvalidated pageURL parameter from the client and issues an HTTP GET request to it using an authenticated client. The underlying transport automatically attaches an Authorization: Bearer header to every outbound request regardless of the destination host. An attacker can supply an arbitrary external URL to the pageURL parameter (either directly via the tool execution payload or implicitly via data-driven pagination tracking loops), leading Toolbox into sending its OAuth/service-account access token to an attacker-controlled listener. Depending on the configuration, this leaks either the end-user's token or the broader service-account access token (ADC), potentially exposing Protected Health Information (PHI) and secondary Google Cloud Platform services.
Severity
SSVC
Exploitation: none
Automatable: no
Technical Impact: partial
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-07-27 19:35 UTC
CWE
- CWE-918 - Server-Side Request Forgery (SSRF)
Assigner
References
1 reference
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| MCP Toolbox for Databases (googleapis/mcp-toolbox) |
Affected:
0.19.1 , ≤ 1.4.0
(semver)
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-16481",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-07-27T19:35:22.831604Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-07-27T19:35:53.065Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"defaultStatus": "unaffected",
"product": "MCP Toolbox for Databases (googleapis/mcp-toolbox)",
"vendor": "Google",
"versions": [
{
"lessThanOrEqual": "1.4.0",
"status": "affected",
"version": "0.19.1",
"versionType": "semver"
}
]
}
],
"credits": [
{
"lang": "en",
"type": "finder",
"value": "HE WEI\uff08\u30ae\u30ab\u30af\uff09(https://www.linkedin.com/in/gikaku/)"
}
],
"descriptions": [
{
"lang": "en",
"supportingMedia": [
{
"base64": false,
"type": "text/html",
"value": "A Server-Side Request Forgery (SSRF) and credential exfiltration vulnerability exists in the cloud-healthcare-fhir-fetch-page tool of googleapis/mcp-toolbox.\n\nThe tool takes an unvalidated pageURL parameter from the client and issues an HTTP GET request to it using an authenticated client. The underlying transport automatically attaches an Authorization: Bearer header to every outbound request regardless of the destination host. An attacker can supply an arbitrary external URL to the pageURL parameter (either directly via the tool execution payload or implicitly via data-driven pagination tracking loops), leading Toolbox into sending its OAuth/service-account access token to an attacker-controlled listener. Depending on the configuration, this leaks either the end-user\u0027s token or the broader service-account access token (ADC), potentially exposing Protected Health Information (PHI) and secondary Google Cloud Platform services."
}
],
"value": "A Server-Side Request Forgery (SSRF) and credential exfiltration vulnerability exists in the cloud-healthcare-fhir-fetch-page tool of googleapis/mcp-toolbox.\n\nThe tool takes an unvalidated pageURL parameter from the client and issues an HTTP GET request to it using an authenticated client. The underlying transport automatically attaches an Authorization: Bearer header to every outbound request regardless of the destination host. An attacker can supply an arbitrary external URL to the pageURL parameter (either directly via the tool execution payload or implicitly via data-driven pagination tracking loops), leading Toolbox into sending its OAuth/service-account access token to an attacker-controlled listener. Depending on the configuration, this leaks either the end-user\u0027s token or the broader service-account access token (ADC), potentially exposing Protected Health Information (PHI) and secondary Google Cloud Platform services."
}
],
"impacts": [
{
"capecId": "CAPEC-664",
"descriptions": [
{
"lang": "en",
"value": "CAPEC-664: Server-Side Request Forgery"
}
]
}
],
"metrics": [
{
"cvssV4_0": {
"Automatable": "NOT_DEFINED",
"Recovery": "NOT_DEFINED",
"Safety": "NOT_DEFINED",
"attackComplexity": "LOW",
"attackRequirements": "NONE",
"attackVector": "NETWORK",
"baseScore": 8.4,
"baseSeverity": "HIGH",
"exploitMaturity": "NOT_DEFINED",
"privilegesRequired": "LOW",
"providerUrgency": "NOT_DEFINED",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "HIGH",
"subIntegrityImpact": "HIGH",
"userInteraction": "NONE",
"valueDensity": "NOT_DEFINED",
"vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:N/VA:N/SC:H/SI:H/SA:N",
"version": "4.0",
"vulnAvailabilityImpact": "NONE",
"vulnConfidentialityImpact": "HIGH",
"vulnIntegrityImpact": "NONE",
"vulnerabilityResponseEffort": "NOT_DEFINED"
},
"format": "CVSS",
"scenarios": [
{
"lang": "en",
"value": "GENERAL"
}
]
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-918",
"description": "CWE-918: Server-Side Request Forgery (SSRF)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-07-27T19:13:29.324Z",
"orgId": "14ed7db2-1595-443d-9d34-6215bf890778",
"shortName": "Google"
},
"references": [
{
"url": "https://github.com/googleapis/mcp-toolbox/pull/3453"
}
],
"source": {
"discovery": "UNKNOWN"
},
"title": "Server-Side Request Forgery (SSRF) and Credential Exfiltration in googleapis/mcp-toolbox cloud-healthcare-fhir-fetch-page Tool",
"x_generator": {
"engine": "Vulnogram 1.0.2"
}
}
},
"cveMetadata": {
"assignerOrgId": "14ed7db2-1595-443d-9d34-6215bf890778",
"assignerShortName": "Google",
"cveId": "CVE-2026-16481",
"datePublished": "2026-07-27T19:13:29.324Z",
"dateReserved": "2026-07-21T14:56:59.820Z",
"dateUpdated": "2026-07-27T19:35:53.065Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-15829 (GCVE-0-2026-15829)
Vulnerability from nvd – Published: 2026-07-21 16:39 – Updated: 2026-07-22 18:49
VLAI
EPSS
VEX
Title
SQL Injection and Security Boundary Bypass in googleapis/mcp-toolbox
Summary
A SQL injection (CWE-89) and security boundary bypass (CWE-863) vulnerability exists in the prebuilt BigQuery forecasting tool (bigquery-forecast) of googleapis/mcp-toolbox.
The tool accepts client-controlled parameters (data_col, timestamp_col, and id_cols) as plain strings and interpolates them unescaped via fmt.Sprintf directly into a generated AI.FORECAST table-valued SELECT statement. While MCP Toolbox utilizes an allowedDatasets mechanism to restrict queries, this defense only validates the history_data parameter; the final assembled query is executed without re-validation.
An attacker can break out of the string literal fields (such as timestamp_col) to inject a valid multi-statement or cross-dataset query block. This allows an unauthorized user to bypass the operator-configured allowedDatasets boundary and read arbitrary BigQuery tables.
Severity
SSVC
Exploitation: none
Automatable: no
Technical Impact: total
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-07-22 18:33 UTC
CWE
Assigner
References
1 reference
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| MCP Toolbox for Databases (googleapis/mcp-toolbox) |
Affected:
0.13.0 , ≤ 1.3.0
(semver)
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-15829",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "no"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-07-22T18:33:38.844180Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-07-22T18:49:05.965Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"defaultStatus": "unaffected",
"product": "MCP Toolbox for Databases (googleapis/mcp-toolbox)",
"vendor": "Google",
"versions": [
{
"lessThanOrEqual": "1.3.0",
"status": "affected",
"version": "0.13.0",
"versionType": "semver"
}
]
}
],
"credits": [
{
"lang": "en",
"type": "finder",
"value": "Matteo Panzeri (Universit\u00e0 di Pavia), GitHub @matte1782"
}
],
"descriptions": [
{
"lang": "en",
"supportingMedia": [
{
"base64": false,
"type": "text/html",
"value": "A SQL injection (CWE-89) and security boundary bypass (CWE-863) vulnerability exists in the prebuilt BigQuery forecasting tool (bigquery-forecast) of googleapis/mcp-toolbox.\n\nThe tool accepts client-controlled parameters (data_col, timestamp_col, and id_cols) as plain strings and interpolates them unescaped via fmt.Sprintf directly into a generated AI.FORECAST table-valued SELECT statement. While MCP Toolbox utilizes an allowedDatasets mechanism to restrict queries, this defense only validates the history_data parameter; the final assembled query is executed without re-validation.\n\nAn attacker can break out of the string literal fields (such as timestamp_col) to inject a valid multi-statement or cross-dataset query block. This allows an unauthorized user to bypass the operator-configured allowedDatasets boundary and read arbitrary BigQuery tables."
}
],
"value": "A SQL injection (CWE-89) and security boundary bypass (CWE-863) vulnerability exists in the prebuilt BigQuery forecasting tool (bigquery-forecast) of googleapis/mcp-toolbox.\n\nThe tool accepts client-controlled parameters (data_col, timestamp_col, and id_cols) as plain strings and interpolates them unescaped via fmt.Sprintf directly into a generated AI.FORECAST table-valued SELECT statement. While MCP Toolbox utilizes an allowedDatasets mechanism to restrict queries, this defense only validates the history_data parameter; the final assembled query is executed without re-validation.\n\nAn attacker can break out of the string literal fields (such as timestamp_col) to inject a valid multi-statement or cross-dataset query block. This allows an unauthorized user to bypass the operator-configured allowedDatasets boundary and read arbitrary BigQuery tables."
}
],
"impacts": [
{
"capecId": "CAPEC-66",
"descriptions": [
{
"lang": "en",
"value": "CAPEC-66: SQL Injection"
}
]
}
],
"metrics": [
{
"cvssV4_0": {
"Automatable": "NOT_DEFINED",
"Recovery": "NOT_DEFINED",
"Safety": "NOT_DEFINED",
"attackComplexity": "LOW",
"attackRequirements": "NONE",
"attackVector": "NETWORK",
"baseScore": 8.6,
"baseSeverity": "HIGH",
"exploitMaturity": "NOT_DEFINED",
"privilegesRequired": "LOW",
"providerUrgency": "NOT_DEFINED",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "NONE",
"subIntegrityImpact": "NONE",
"userInteraction": "NONE",
"valueDensity": "NOT_DEFINED",
"vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:N/SC:N/SI:N/SA:N",
"version": "4.0",
"vulnAvailabilityImpact": "NONE",
"vulnConfidentialityImpact": "HIGH",
"vulnIntegrityImpact": "HIGH",
"vulnerabilityResponseEffort": "NOT_DEFINED"
},
"format": "CVSS",
"scenarios": [
{
"lang": "en",
"value": "GENERAL"
}
]
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-89",
"description": "CWE-89: Improper Neutralization of Special Elements used in an SQL Command (\u0027SQL Injection\u0027)",
"lang": "en",
"type": "CWE"
}
]
},
{
"descriptions": [
{
"cweId": "CWE-863",
"description": "CWE-863: Incorrect Authorization",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-07-21T16:39:54.968Z",
"orgId": "14ed7db2-1595-443d-9d34-6215bf890778",
"shortName": "Google"
},
"references": [
{
"url": "https://github.com/googleapis/mcp-toolbox/pull/3324"
}
],
"source": {
"discovery": "UNKNOWN"
},
"title": "SQL Injection and Security Boundary Bypass in googleapis/mcp-toolbox",
"x_generator": {
"engine": "Vulnogram 1.0.2"
}
}
},
"cveMetadata": {
"assignerOrgId": "14ed7db2-1595-443d-9d34-6215bf890778",
"assignerShortName": "Google",
"cveId": "CVE-2026-15829",
"datePublished": "2026-07-21T16:39:54.968Z",
"dateReserved": "2026-07-15T15:00:56.723Z",
"dateUpdated": "2026-07-22T18:49:05.965Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-11720 (GCVE-0-2026-11720)
Vulnerability from nvd – Published: 2026-06-29 17:51 – Updated: 2026-06-29 18:26
VLAI
EPSS
VEX
Title
Path Traversal in googleapis/mcp-toolbox HTTP Tool URL Builder
Summary
A path traversal vulnerability exists in the HTTP tool URL builder of googleapis/mcp-toolbox.
When constructing downstream API requests, the URL builder substitutes user-controlled pathParams into the configured tool path and parses the resulting string as a relative URL. While it checks that the input does not alter the scheme, host, or user info, it relies on ResolveReference for the final URL resolution. Because dot segments (../) are normalized during this resolution step, an attacker can supply path parameters containing directory traversal sequences to escape the operator-configured path scope. This allows the client to coerce the toolbox into making requests to unintended endpoints on the same target host while forwarding the toolbox's configured credentials (e.g., bypassing a restricted path like /api/v1/users/{{.id}} to reach /admin/secrets).
Severity
SSVC
Exploitation: none
Automatable: yes
Technical Impact: total
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-06-29 18:25 UTC
CWE
- CWE-22 - Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal')
Assigner
References
1 reference
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| MCP Toolbox for Databases (googleapis/mcp-toolbox) |
Affected:
0 , < 1.3.0
(semver)
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-11720",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-06-29T18:25:08.204755Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-06-29T18:26:17.242Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"defaultStatus": "unaffected",
"product": "MCP Toolbox for Databases (googleapis/mcp-toolbox)",
"vendor": "Google",
"versions": [
{
"lessThan": "1.3.0",
"status": "affected",
"version": "0",
"versionType": "semver"
}
]
}
],
"credits": [
{
"lang": "en",
"type": "finder",
"value": "Ryan Vonbrubeck / @dodge1218"
}
],
"descriptions": [
{
"lang": "en",
"supportingMedia": [
{
"base64": false,
"type": "text/html",
"value": "A path traversal vulnerability exists in the HTTP tool URL builder of googleapis/mcp-toolbox.\n\nWhen constructing downstream API requests, the URL builder substitutes user-controlled pathParams into the configured tool path and parses the resulting string as a relative URL. While it checks that the input does not alter the scheme, host, or user info, it relies on ResolveReference for the final URL resolution. Because dot segments (../) are normalized during this resolution step, an attacker can supply path parameters containing directory traversal sequences to escape the operator-configured path scope. This allows the client to coerce the toolbox into making requests to unintended endpoints on the same target host while forwarding the toolbox\u0027s configured credentials (e.g., bypassing a restricted path like /api/v1/users/{{.id}} to reach /admin/secrets)."
}
],
"value": "A path traversal vulnerability exists in the HTTP tool URL builder of googleapis/mcp-toolbox.\n\nWhen constructing downstream API requests, the URL builder substitutes user-controlled pathParams into the configured tool path and parses the resulting string as a relative URL. While it checks that the input does not alter the scheme, host, or user info, it relies on ResolveReference for the final URL resolution. Because dot segments (../) are normalized during this resolution step, an attacker can supply path parameters containing directory traversal sequences to escape the operator-configured path scope. This allows the client to coerce the toolbox into making requests to unintended endpoints on the same target host while forwarding the toolbox\u0027s configured credentials (e.g., bypassing a restricted path like /api/v1/users/{{.id}} to reach /admin/secrets)."
}
],
"impacts": [
{
"capecId": "CAPEC-139",
"descriptions": [
{
"lang": "en",
"value": "CAPEC-139: Relative Path Traversal"
}
]
}
],
"metrics": [
{
"cvssV4_0": {
"Automatable": "NOT_DEFINED",
"Recovery": "NOT_DEFINED",
"Safety": "NOT_DEFINED",
"attackComplexity": "LOW",
"attackRequirements": "NONE",
"attackVector": "NETWORK",
"baseScore": 9.3,
"baseSeverity": "CRITICAL",
"exploitMaturity": "NOT_DEFINED",
"privilegesRequired": "NONE",
"providerUrgency": "NOT_DEFINED",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "NONE",
"subIntegrityImpact": "NONE",
"userInteraction": "NONE",
"valueDensity": "NOT_DEFINED",
"vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:N/SC:N/SI:N/SA:N",
"version": "4.0",
"vulnAvailabilityImpact": "NONE",
"vulnConfidentialityImpact": "HIGH",
"vulnIntegrityImpact": "HIGH",
"vulnerabilityResponseEffort": "NOT_DEFINED"
},
"format": "CVSS",
"scenarios": [
{
"lang": "en",
"value": "GENERAL"
}
]
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-22",
"description": "CWE-22: Improper Limitation of a Pathname to a Restricted Directory (\u0027Path Traversal\u0027)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-06-29T17:51:30.077Z",
"orgId": "14ed7db2-1595-443d-9d34-6215bf890778",
"shortName": "Google"
},
"references": [
{
"url": "https://github.com/googleapis/mcp-toolbox/pull/3218"
}
],
"source": {
"discovery": "UNKNOWN"
},
"title": "Path Traversal in googleapis/mcp-toolbox HTTP Tool URL Builder",
"x_generator": {
"engine": "Vulnogram 1.0.2"
}
}
},
"cveMetadata": {
"assignerOrgId": "14ed7db2-1595-443d-9d34-6215bf890778",
"assignerShortName": "Google",
"cveId": "CVE-2026-11720",
"datePublished": "2026-06-29T17:51:30.077Z",
"dateReserved": "2026-06-09T00:57:55.333Z",
"dateUpdated": "2026-06-29T18:26:17.242Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-11719 (GCVE-0-2026-11719)
Vulnerability from nvd – Published: 2026-06-18 11:55 – Updated: 2026-06-18 13:53
VLAI
EPSS
VEX
Summary
An authenticated authorization bypass vulnerability exists in MCP Toolbox for Databases due to missing scope enforcement across older protocol handlers.
While the 2025-11-25 protocol version handler correctly enforces per-tool restrictions defined by scopesRequired, older supported protocol versions (2025-06-18, 2025-03-26, and 2024-11-05) omit this check. An authenticated client with low-privilege tokens (e.g., read) can bypass the intended per-tool scope restrictions and execute high-privilege tools (e.g., admin) simply by specifying an older protocol version in the MCP-Protocol-Version header, or by omitting the header entirely (which causes the server to default to the vulnerable 2024-11-05 handler).
Severity
SSVC
Exploitation: none
Automatable: no
Technical Impact: total
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-06-18 12:55 UTC
CWE
- CWE-862 - Missing Authorization
Assigner
References
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| MCP Toolbox for Databases (googleapis/mcp-toolbox) |
Affected:
1.3.0
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-11719",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "no"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-06-18T12:55:43.505312Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-06-18T13:53:08.793Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"defaultStatus": "unaffected",
"product": "MCP Toolbox for Databases (googleapis/mcp-toolbox)",
"vendor": "Google",
"versions": [
{
"status": "affected",
"version": "1.3.0"
}
]
}
],
"credits": [
{
"lang": "en",
"type": "finder",
"value": "HE WEI\uff08\u30ae\u30ab\u30af\uff09(https://www.linkedin.com/in/gikaku/)"
}
],
"descriptions": [
{
"lang": "en",
"supportingMedia": [
{
"base64": false,
"type": "text/html",
"value": "An authenticated authorization bypass vulnerability exists in MCP Toolbox for Databases due to missing scope enforcement across older protocol handlers.\n\nWhile the 2025-11-25 protocol version handler correctly enforces per-tool restrictions defined by scopesRequired, older supported protocol versions (2025-06-18, 2025-03-26, and 2024-11-05) omit this check. An authenticated client with low-privilege tokens (e.g., read) can bypass the intended per-tool scope restrictions and execute high-privilege tools (e.g., admin) simply by specifying an older protocol version in the MCP-Protocol-Version header, or by omitting the header entirely (which causes the server to default to the vulnerable 2024-11-05 handler)."
}
],
"value": "An authenticated authorization bypass vulnerability exists in MCP Toolbox for Databases due to missing scope enforcement across older protocol handlers.\n\nWhile the 2025-11-25 protocol version handler correctly enforces per-tool restrictions defined by scopesRequired, older supported protocol versions (2025-06-18, 2025-03-26, and 2024-11-05) omit this check. An authenticated client with low-privilege tokens (e.g., read) can bypass the intended per-tool scope restrictions and execute high-privilege tools (e.g., admin) simply by specifying an older protocol version in the MCP-Protocol-Version header, or by omitting the header entirely (which causes the server to default to the vulnerable 2024-11-05 handler)."
}
],
"impacts": [
{
"capecId": "CAPEC-115",
"descriptions": [
{
"lang": "en",
"value": "CAPEC-115: Authentication Bypass"
}
]
}
],
"metrics": [
{
"cvssV4_0": {
"Automatable": "NOT_DEFINED",
"Recovery": "NOT_DEFINED",
"Safety": "NOT_DEFINED",
"attackComplexity": "LOW",
"attackRequirements": "NONE",
"attackVector": "NETWORK",
"baseScore": 8.6,
"baseSeverity": "HIGH",
"exploitMaturity": "NOT_DEFINED",
"privilegesRequired": "LOW",
"providerUrgency": "NOT_DEFINED",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "NONE",
"subIntegrityImpact": "NONE",
"userInteraction": "NONE",
"valueDensity": "NOT_DEFINED",
"vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:N/SC:N/SI:N/SA:N",
"version": "4.0",
"vulnAvailabilityImpact": "NONE",
"vulnConfidentialityImpact": "HIGH",
"vulnIntegrityImpact": "HIGH",
"vulnerabilityResponseEffort": "NOT_DEFINED"
},
"format": "CVSS",
"scenarios": [
{
"lang": "en",
"value": "GENERAL"
}
]
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-862",
"description": "CWE-862: Missing Authorization",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-06-18T11:55:03.666Z",
"orgId": "14ed7db2-1595-443d-9d34-6215bf890778",
"shortName": "Google"
},
"references": [
{
"url": "https://github.com/googleapis/mcp-toolbox/pull/3335"
},
{
"url": "https://github.com/googleapis/mcp-toolbox/pull/3049"
}
],
"source": {
"discovery": "UNKNOWN"
},
"x_generator": {
"engine": "Vulnogram 1.0.2"
}
}
},
"cveMetadata": {
"assignerOrgId": "14ed7db2-1595-443d-9d34-6215bf890778",
"assignerShortName": "Google",
"cveId": "CVE-2026-11719",
"datePublished": "2026-06-18T11:55:03.666Z",
"dateReserved": "2026-06-09T00:53:57.846Z",
"dateUpdated": "2026-06-18T13:53:08.793Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-11718 (GCVE-0-2026-11718)
Vulnerability from nvd – Published: 2026-06-18 11:52 – Updated: 2026-06-18 13:53
VLAI
EPSS
VEX
Summary
An authentication bypass vulnerability exists in the generic opaque token validation path (validateOpaqueToken) of googleapis/mcp-toolbox.
When the toolbox validates an opaque token via an OAuth 2.0 introspection endpoint (RFC 7662), it decodes the response into an introspectResp struct. However, the subsequent claim-checking logic (validateClaims) evaluates the issuer condition as if a.issuer != "" && iss != "". If the external OAuth provider's introspection response omits the optional iss (issuer) field completely, the variable iss defaults to an empty string. This causes the conditional block to evaluate to false and be skipped silently. Consequently, the application accepts tokens issued by unauthorized or unintended third-party identity providers.
Severity
SSVC
Exploitation: none
Automatable: yes
Technical Impact: total
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-06-18 13:01 UTC
CWE
- CWE-287 - Improper Authentication
Assigner
References
1 reference
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| MCP Toolbox for Databases (googleapis/mcp-toolbox) |
Affected:
1.0.0 , ≤ 1.3.0
(semver)
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-11718",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-06-18T13:01:08.666194Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-06-18T13:53:14.985Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"defaultStatus": "unaffected",
"product": "MCP Toolbox for Databases (googleapis/mcp-toolbox)",
"vendor": "Google",
"versions": [
{
"lessThanOrEqual": "1.3.0",
"status": "affected",
"version": "1.0.0",
"versionType": "semver"
}
]
}
],
"credits": [
{
"lang": "en",
"type": "finder",
"value": "HaoNH Leader Redteam From VINCSS ( Member Of Vingroup )."
}
],
"descriptions": [
{
"lang": "en",
"supportingMedia": [
{
"base64": false,
"type": "text/html",
"value": "An authentication bypass vulnerability exists in the generic opaque token validation path (validateOpaqueToken) of googleapis/mcp-toolbox.\n\nWhen the toolbox validates an opaque token via an OAuth 2.0 introspection endpoint (RFC 7662), it decodes the response into an introspectResp struct. However, the subsequent claim-checking logic (validateClaims) evaluates the issuer condition as if a.issuer != \"\" \u0026amp;\u0026amp; iss != \"\". If the external OAuth provider\u0027s introspection response omits the optional iss (issuer) field completely, the variable iss defaults to an empty string. This causes the conditional block to evaluate to false and be skipped silently. Consequently, the application accepts tokens issued by unauthorized or unintended third-party identity providers."
}
],
"value": "An authentication bypass vulnerability exists in the generic opaque token validation path (validateOpaqueToken) of googleapis/mcp-toolbox.\n\nWhen the toolbox validates an opaque token via an OAuth 2.0 introspection endpoint (RFC 7662), it decodes the response into an introspectResp struct. However, the subsequent claim-checking logic (validateClaims) evaluates the issuer condition as if a.issuer != \"\" \u0026\u0026 iss != \"\". If the external OAuth provider\u0027s introspection response omits the optional iss (issuer) field completely, the variable iss defaults to an empty string. This causes the conditional block to evaluate to false and be skipped silently. Consequently, the application accepts tokens issued by unauthorized or unintended third-party identity providers."
}
],
"impacts": [
{
"capecId": "CAPEC-115",
"descriptions": [
{
"lang": "en",
"value": "CAPEC-115: Authentication Bypass"
}
]
}
],
"metrics": [
{
"cvssV4_0": {
"Automatable": "NOT_DEFINED",
"Recovery": "NOT_DEFINED",
"Safety": "NOT_DEFINED",
"attackComplexity": "LOW",
"attackRequirements": "NONE",
"attackVector": "NETWORK",
"baseScore": 9.3,
"baseSeverity": "CRITICAL",
"exploitMaturity": "NOT_DEFINED",
"privilegesRequired": "NONE",
"providerUrgency": "NOT_DEFINED",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "NONE",
"subIntegrityImpact": "NONE",
"userInteraction": "NONE",
"valueDensity": "NOT_DEFINED",
"vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:N/SC:N/SI:N/SA:N",
"version": "4.0",
"vulnAvailabilityImpact": "NONE",
"vulnConfidentialityImpact": "HIGH",
"vulnIntegrityImpact": "HIGH",
"vulnerabilityResponseEffort": "NOT_DEFINED"
},
"format": "CVSS",
"scenarios": [
{
"lang": "en",
"value": "GENERAL"
}
]
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-287",
"description": "CWE-287: Improper Authentication",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-06-18T11:52:42.327Z",
"orgId": "14ed7db2-1595-443d-9d34-6215bf890778",
"shortName": "Google"
},
"references": [
{
"url": "https://github.com/googleapis/mcp-toolbox/pull/3360"
}
],
"source": {
"discovery": "UNKNOWN"
},
"x_generator": {
"engine": "Vulnogram 1.0.2"
}
}
},
"cveMetadata": {
"assignerOrgId": "14ed7db2-1595-443d-9d34-6215bf890778",
"assignerShortName": "Google",
"cveId": "CVE-2026-11718",
"datePublished": "2026-06-18T11:52:42.327Z",
"dateReserved": "2026-06-09T00:49:55.908Z",
"dateUpdated": "2026-06-18T13:53:14.985Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-11717 (GCVE-0-2026-11717)
Vulnerability from nvd – Published: 2026-06-18 11:50 – Updated: 2026-06-18 12:23
VLAI
EPSS
VEX
Summary
An authentication bypass vulnerability exists in the generic opaque token validation path (validateOpaqueToken) of googleapis/mcp-toolbox.
When verifying an unparsed opaque token via an OAuth 2.0 introspection endpoint (RFC 7662), the toolbox decodes the response into an introspectResp struct where the Active field is declared as a pointer to a boolean (*bool). The code only explicitly rejects a token if the response contains a populated active field set to false (if introspectResp.Active != nil && !*introspectResp.Active). If an introspection endpoint responds with a payload that completely omits the mandatory active key, the internal variable remains nil, causing the conditional check to short-circuit. As a result, Toolbox accepts authorization tokens missing the "active" field, granting access to protected tools and underlying data sources.
Severity
SSVC
Exploitation: none
Automatable: yes
Technical Impact: total
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-06-18 12:23 UTC
CWE
- CWE-287 - Improper Authentication
Assigner
References
1 reference
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| MCP Toolbox for Databases (googleapis/mcp-toolbox) |
Affected:
1.0.0 , ≤ 1.3.0
(semver)
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-11717",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-06-18T12:23:05.330652Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-06-18T12:23:15.209Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"defaultStatus": "unaffected",
"product": "MCP Toolbox for Databases (googleapis/mcp-toolbox)",
"vendor": "Google",
"versions": [
{
"lessThanOrEqual": "1.3.0",
"status": "affected",
"version": "1.0.0",
"versionType": "semver"
}
]
}
],
"credits": [
{
"lang": "en",
"type": "finder",
"value": "HaoNH Leader Redteam From VINCSS ( Member Of Vingroup )"
}
],
"descriptions": [
{
"lang": "en",
"supportingMedia": [
{
"base64": false,
"type": "text/html",
"value": "An authentication bypass vulnerability exists in the generic opaque token validation path (validateOpaqueToken) of googleapis/mcp-toolbox.\n\nWhen verifying an unparsed opaque token via an OAuth 2.0 introspection endpoint (RFC 7662), the toolbox decodes the response into an introspectResp struct where the Active field is declared as a pointer to a boolean (*bool). The code only explicitly rejects a token if the response contains a populated active field set to false (if introspectResp.Active != nil \u0026amp;\u0026amp; !*introspectResp.Active). If an introspection endpoint responds with a payload that completely omits the mandatory active key, the internal variable remains nil, causing the conditional check to short-circuit. As a result, Toolbox accepts authorization tokens missing the \"active\" field, granting access to protected tools and underlying data sources."
}
],
"value": "An authentication bypass vulnerability exists in the generic opaque token validation path (validateOpaqueToken) of googleapis/mcp-toolbox.\n\nWhen verifying an unparsed opaque token via an OAuth 2.0 introspection endpoint (RFC 7662), the toolbox decodes the response into an introspectResp struct where the Active field is declared as a pointer to a boolean (*bool). The code only explicitly rejects a token if the response contains a populated active field set to false (if introspectResp.Active != nil \u0026\u0026 !*introspectResp.Active). If an introspection endpoint responds with a payload that completely omits the mandatory active key, the internal variable remains nil, causing the conditional check to short-circuit. As a result, Toolbox accepts authorization tokens missing the \"active\" field, granting access to protected tools and underlying data sources."
}
],
"impacts": [
{
"capecId": "CAPEC-114",
"descriptions": [
{
"lang": "en",
"value": "CAPEC-114: Authentication Abuse"
}
]
}
],
"metrics": [
{
"cvssV4_0": {
"Automatable": "NOT_DEFINED",
"Recovery": "NOT_DEFINED",
"Safety": "NOT_DEFINED",
"attackComplexity": "LOW",
"attackRequirements": "NONE",
"attackVector": "NETWORK",
"baseScore": 9.3,
"baseSeverity": "CRITICAL",
"exploitMaturity": "NOT_DEFINED",
"privilegesRequired": "NONE",
"providerUrgency": "NOT_DEFINED",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "NONE",
"subIntegrityImpact": "NONE",
"userInteraction": "NONE",
"valueDensity": "NOT_DEFINED",
"vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:N/SC:N/SI:N/SA:N",
"version": "4.0",
"vulnAvailabilityImpact": "NONE",
"vulnConfidentialityImpact": "HIGH",
"vulnIntegrityImpact": "HIGH",
"vulnerabilityResponseEffort": "NOT_DEFINED"
},
"format": "CVSS",
"scenarios": [
{
"lang": "en",
"value": "GENERAL"
}
]
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-287",
"description": "CWE-287: Improper Authentication",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-06-18T11:50:23.665Z",
"orgId": "14ed7db2-1595-443d-9d34-6215bf890778",
"shortName": "Google"
},
"references": [
{
"url": "https://github.com/googleapis/mcp-toolbox/pull/3341"
}
],
"source": {
"discovery": "UNKNOWN"
},
"x_generator": {
"engine": "Vulnogram 1.0.2"
}
}
},
"cveMetadata": {
"assignerOrgId": "14ed7db2-1595-443d-9d34-6215bf890778",
"assignerShortName": "Google",
"cveId": "CVE-2026-11717",
"datePublished": "2026-06-18T11:50:23.665Z",
"dateReserved": "2026-06-09T00:41:54.835Z",
"dateUpdated": "2026-06-18T12:23:15.209Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-16481 (GCVE-0-2026-16481)
Vulnerability from cvelistv5 – Published: 2026-07-27 19:13 – Updated: 2026-07-27 19:35
VLAI
EPSS
VEX
Title
Server-Side Request Forgery (SSRF) and Credential Exfiltration in googleapis/mcp-toolbox cloud-healthcare-fhir-fetch-page Tool
Summary
A Server-Side Request Forgery (SSRF) and credential exfiltration vulnerability exists in the cloud-healthcare-fhir-fetch-page tool of googleapis/mcp-toolbox.
The tool takes an unvalidated pageURL parameter from the client and issues an HTTP GET request to it using an authenticated client. The underlying transport automatically attaches an Authorization: Bearer header to every outbound request regardless of the destination host. An attacker can supply an arbitrary external URL to the pageURL parameter (either directly via the tool execution payload or implicitly via data-driven pagination tracking loops), leading Toolbox into sending its OAuth/service-account access token to an attacker-controlled listener. Depending on the configuration, this leaks either the end-user's token or the broader service-account access token (ADC), potentially exposing Protected Health Information (PHI) and secondary Google Cloud Platform services.
Severity
SSVC
Exploitation: none
Automatable: no
Technical Impact: partial
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-07-27 19:35 UTC
CWE
- CWE-918 - Server-Side Request Forgery (SSRF)
Assigner
References
1 reference
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| MCP Toolbox for Databases (googleapis/mcp-toolbox) |
Affected:
0.19.1 , ≤ 1.4.0
(semver)
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-16481",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-07-27T19:35:22.831604Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-07-27T19:35:53.065Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"defaultStatus": "unaffected",
"product": "MCP Toolbox for Databases (googleapis/mcp-toolbox)",
"vendor": "Google",
"versions": [
{
"lessThanOrEqual": "1.4.0",
"status": "affected",
"version": "0.19.1",
"versionType": "semver"
}
]
}
],
"credits": [
{
"lang": "en",
"type": "finder",
"value": "HE WEI\uff08\u30ae\u30ab\u30af\uff09(https://www.linkedin.com/in/gikaku/)"
}
],
"descriptions": [
{
"lang": "en",
"supportingMedia": [
{
"base64": false,
"type": "text/html",
"value": "A Server-Side Request Forgery (SSRF) and credential exfiltration vulnerability exists in the cloud-healthcare-fhir-fetch-page tool of googleapis/mcp-toolbox.\n\nThe tool takes an unvalidated pageURL parameter from the client and issues an HTTP GET request to it using an authenticated client. The underlying transport automatically attaches an Authorization: Bearer header to every outbound request regardless of the destination host. An attacker can supply an arbitrary external URL to the pageURL parameter (either directly via the tool execution payload or implicitly via data-driven pagination tracking loops), leading Toolbox into sending its OAuth/service-account access token to an attacker-controlled listener. Depending on the configuration, this leaks either the end-user\u0027s token or the broader service-account access token (ADC), potentially exposing Protected Health Information (PHI) and secondary Google Cloud Platform services."
}
],
"value": "A Server-Side Request Forgery (SSRF) and credential exfiltration vulnerability exists in the cloud-healthcare-fhir-fetch-page tool of googleapis/mcp-toolbox.\n\nThe tool takes an unvalidated pageURL parameter from the client and issues an HTTP GET request to it using an authenticated client. The underlying transport automatically attaches an Authorization: Bearer header to every outbound request regardless of the destination host. An attacker can supply an arbitrary external URL to the pageURL parameter (either directly via the tool execution payload or implicitly via data-driven pagination tracking loops), leading Toolbox into sending its OAuth/service-account access token to an attacker-controlled listener. Depending on the configuration, this leaks either the end-user\u0027s token or the broader service-account access token (ADC), potentially exposing Protected Health Information (PHI) and secondary Google Cloud Platform services."
}
],
"impacts": [
{
"capecId": "CAPEC-664",
"descriptions": [
{
"lang": "en",
"value": "CAPEC-664: Server-Side Request Forgery"
}
]
}
],
"metrics": [
{
"cvssV4_0": {
"Automatable": "NOT_DEFINED",
"Recovery": "NOT_DEFINED",
"Safety": "NOT_DEFINED",
"attackComplexity": "LOW",
"attackRequirements": "NONE",
"attackVector": "NETWORK",
"baseScore": 8.4,
"baseSeverity": "HIGH",
"exploitMaturity": "NOT_DEFINED",
"privilegesRequired": "LOW",
"providerUrgency": "NOT_DEFINED",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "HIGH",
"subIntegrityImpact": "HIGH",
"userInteraction": "NONE",
"valueDensity": "NOT_DEFINED",
"vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:N/VA:N/SC:H/SI:H/SA:N",
"version": "4.0",
"vulnAvailabilityImpact": "NONE",
"vulnConfidentialityImpact": "HIGH",
"vulnIntegrityImpact": "NONE",
"vulnerabilityResponseEffort": "NOT_DEFINED"
},
"format": "CVSS",
"scenarios": [
{
"lang": "en",
"value": "GENERAL"
}
]
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-918",
"description": "CWE-918: Server-Side Request Forgery (SSRF)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-07-27T19:13:29.324Z",
"orgId": "14ed7db2-1595-443d-9d34-6215bf890778",
"shortName": "Google"
},
"references": [
{
"url": "https://github.com/googleapis/mcp-toolbox/pull/3453"
}
],
"source": {
"discovery": "UNKNOWN"
},
"title": "Server-Side Request Forgery (SSRF) and Credential Exfiltration in googleapis/mcp-toolbox cloud-healthcare-fhir-fetch-page Tool",
"x_generator": {
"engine": "Vulnogram 1.0.2"
}
}
},
"cveMetadata": {
"assignerOrgId": "14ed7db2-1595-443d-9d34-6215bf890778",
"assignerShortName": "Google",
"cveId": "CVE-2026-16481",
"datePublished": "2026-07-27T19:13:29.324Z",
"dateReserved": "2026-07-21T14:56:59.820Z",
"dateUpdated": "2026-07-27T19:35:53.065Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-15829 (GCVE-0-2026-15829)
Vulnerability from cvelistv5 – Published: 2026-07-21 16:39 – Updated: 2026-07-22 18:49
VLAI
EPSS
VEX
Title
SQL Injection and Security Boundary Bypass in googleapis/mcp-toolbox
Summary
A SQL injection (CWE-89) and security boundary bypass (CWE-863) vulnerability exists in the prebuilt BigQuery forecasting tool (bigquery-forecast) of googleapis/mcp-toolbox.
The tool accepts client-controlled parameters (data_col, timestamp_col, and id_cols) as plain strings and interpolates them unescaped via fmt.Sprintf directly into a generated AI.FORECAST table-valued SELECT statement. While MCP Toolbox utilizes an allowedDatasets mechanism to restrict queries, this defense only validates the history_data parameter; the final assembled query is executed without re-validation.
An attacker can break out of the string literal fields (such as timestamp_col) to inject a valid multi-statement or cross-dataset query block. This allows an unauthorized user to bypass the operator-configured allowedDatasets boundary and read arbitrary BigQuery tables.
Severity
SSVC
Exploitation: none
Automatable: no
Technical Impact: total
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-07-22 18:33 UTC
CWE
Assigner
References
1 reference
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| MCP Toolbox for Databases (googleapis/mcp-toolbox) |
Affected:
0.13.0 , ≤ 1.3.0
(semver)
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-15829",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "no"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-07-22T18:33:38.844180Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-07-22T18:49:05.965Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"defaultStatus": "unaffected",
"product": "MCP Toolbox for Databases (googleapis/mcp-toolbox)",
"vendor": "Google",
"versions": [
{
"lessThanOrEqual": "1.3.0",
"status": "affected",
"version": "0.13.0",
"versionType": "semver"
}
]
}
],
"credits": [
{
"lang": "en",
"type": "finder",
"value": "Matteo Panzeri (Universit\u00e0 di Pavia), GitHub @matte1782"
}
],
"descriptions": [
{
"lang": "en",
"supportingMedia": [
{
"base64": false,
"type": "text/html",
"value": "A SQL injection (CWE-89) and security boundary bypass (CWE-863) vulnerability exists in the prebuilt BigQuery forecasting tool (bigquery-forecast) of googleapis/mcp-toolbox.\n\nThe tool accepts client-controlled parameters (data_col, timestamp_col, and id_cols) as plain strings and interpolates them unescaped via fmt.Sprintf directly into a generated AI.FORECAST table-valued SELECT statement. While MCP Toolbox utilizes an allowedDatasets mechanism to restrict queries, this defense only validates the history_data parameter; the final assembled query is executed without re-validation.\n\nAn attacker can break out of the string literal fields (such as timestamp_col) to inject a valid multi-statement or cross-dataset query block. This allows an unauthorized user to bypass the operator-configured allowedDatasets boundary and read arbitrary BigQuery tables."
}
],
"value": "A SQL injection (CWE-89) and security boundary bypass (CWE-863) vulnerability exists in the prebuilt BigQuery forecasting tool (bigquery-forecast) of googleapis/mcp-toolbox.\n\nThe tool accepts client-controlled parameters (data_col, timestamp_col, and id_cols) as plain strings and interpolates them unescaped via fmt.Sprintf directly into a generated AI.FORECAST table-valued SELECT statement. While MCP Toolbox utilizes an allowedDatasets mechanism to restrict queries, this defense only validates the history_data parameter; the final assembled query is executed without re-validation.\n\nAn attacker can break out of the string literal fields (such as timestamp_col) to inject a valid multi-statement or cross-dataset query block. This allows an unauthorized user to bypass the operator-configured allowedDatasets boundary and read arbitrary BigQuery tables."
}
],
"impacts": [
{
"capecId": "CAPEC-66",
"descriptions": [
{
"lang": "en",
"value": "CAPEC-66: SQL Injection"
}
]
}
],
"metrics": [
{
"cvssV4_0": {
"Automatable": "NOT_DEFINED",
"Recovery": "NOT_DEFINED",
"Safety": "NOT_DEFINED",
"attackComplexity": "LOW",
"attackRequirements": "NONE",
"attackVector": "NETWORK",
"baseScore": 8.6,
"baseSeverity": "HIGH",
"exploitMaturity": "NOT_DEFINED",
"privilegesRequired": "LOW",
"providerUrgency": "NOT_DEFINED",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "NONE",
"subIntegrityImpact": "NONE",
"userInteraction": "NONE",
"valueDensity": "NOT_DEFINED",
"vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:N/SC:N/SI:N/SA:N",
"version": "4.0",
"vulnAvailabilityImpact": "NONE",
"vulnConfidentialityImpact": "HIGH",
"vulnIntegrityImpact": "HIGH",
"vulnerabilityResponseEffort": "NOT_DEFINED"
},
"format": "CVSS",
"scenarios": [
{
"lang": "en",
"value": "GENERAL"
}
]
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-89",
"description": "CWE-89: Improper Neutralization of Special Elements used in an SQL Command (\u0027SQL Injection\u0027)",
"lang": "en",
"type": "CWE"
}
]
},
{
"descriptions": [
{
"cweId": "CWE-863",
"description": "CWE-863: Incorrect Authorization",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-07-21T16:39:54.968Z",
"orgId": "14ed7db2-1595-443d-9d34-6215bf890778",
"shortName": "Google"
},
"references": [
{
"url": "https://github.com/googleapis/mcp-toolbox/pull/3324"
}
],
"source": {
"discovery": "UNKNOWN"
},
"title": "SQL Injection and Security Boundary Bypass in googleapis/mcp-toolbox",
"x_generator": {
"engine": "Vulnogram 1.0.2"
}
}
},
"cveMetadata": {
"assignerOrgId": "14ed7db2-1595-443d-9d34-6215bf890778",
"assignerShortName": "Google",
"cveId": "CVE-2026-15829",
"datePublished": "2026-07-21T16:39:54.968Z",
"dateReserved": "2026-07-15T15:00:56.723Z",
"dateUpdated": "2026-07-22T18:49:05.965Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-11720 (GCVE-0-2026-11720)
Vulnerability from cvelistv5 – Published: 2026-06-29 17:51 – Updated: 2026-06-29 18:26
VLAI
EPSS
VEX
Title
Path Traversal in googleapis/mcp-toolbox HTTP Tool URL Builder
Summary
A path traversal vulnerability exists in the HTTP tool URL builder of googleapis/mcp-toolbox.
When constructing downstream API requests, the URL builder substitutes user-controlled pathParams into the configured tool path and parses the resulting string as a relative URL. While it checks that the input does not alter the scheme, host, or user info, it relies on ResolveReference for the final URL resolution. Because dot segments (../) are normalized during this resolution step, an attacker can supply path parameters containing directory traversal sequences to escape the operator-configured path scope. This allows the client to coerce the toolbox into making requests to unintended endpoints on the same target host while forwarding the toolbox's configured credentials (e.g., bypassing a restricted path like /api/v1/users/{{.id}} to reach /admin/secrets).
Severity
SSVC
Exploitation: none
Automatable: yes
Technical Impact: total
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-06-29 18:25 UTC
CWE
- CWE-22 - Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal')
Assigner
References
1 reference
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| MCP Toolbox for Databases (googleapis/mcp-toolbox) |
Affected:
0 , < 1.3.0
(semver)
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-11720",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-06-29T18:25:08.204755Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-06-29T18:26:17.242Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"defaultStatus": "unaffected",
"product": "MCP Toolbox for Databases (googleapis/mcp-toolbox)",
"vendor": "Google",
"versions": [
{
"lessThan": "1.3.0",
"status": "affected",
"version": "0",
"versionType": "semver"
}
]
}
],
"credits": [
{
"lang": "en",
"type": "finder",
"value": "Ryan Vonbrubeck / @dodge1218"
}
],
"descriptions": [
{
"lang": "en",
"supportingMedia": [
{
"base64": false,
"type": "text/html",
"value": "A path traversal vulnerability exists in the HTTP tool URL builder of googleapis/mcp-toolbox.\n\nWhen constructing downstream API requests, the URL builder substitutes user-controlled pathParams into the configured tool path and parses the resulting string as a relative URL. While it checks that the input does not alter the scheme, host, or user info, it relies on ResolveReference for the final URL resolution. Because dot segments (../) are normalized during this resolution step, an attacker can supply path parameters containing directory traversal sequences to escape the operator-configured path scope. This allows the client to coerce the toolbox into making requests to unintended endpoints on the same target host while forwarding the toolbox\u0027s configured credentials (e.g., bypassing a restricted path like /api/v1/users/{{.id}} to reach /admin/secrets)."
}
],
"value": "A path traversal vulnerability exists in the HTTP tool URL builder of googleapis/mcp-toolbox.\n\nWhen constructing downstream API requests, the URL builder substitutes user-controlled pathParams into the configured tool path and parses the resulting string as a relative URL. While it checks that the input does not alter the scheme, host, or user info, it relies on ResolveReference for the final URL resolution. Because dot segments (../) are normalized during this resolution step, an attacker can supply path parameters containing directory traversal sequences to escape the operator-configured path scope. This allows the client to coerce the toolbox into making requests to unintended endpoints on the same target host while forwarding the toolbox\u0027s configured credentials (e.g., bypassing a restricted path like /api/v1/users/{{.id}} to reach /admin/secrets)."
}
],
"impacts": [
{
"capecId": "CAPEC-139",
"descriptions": [
{
"lang": "en",
"value": "CAPEC-139: Relative Path Traversal"
}
]
}
],
"metrics": [
{
"cvssV4_0": {
"Automatable": "NOT_DEFINED",
"Recovery": "NOT_DEFINED",
"Safety": "NOT_DEFINED",
"attackComplexity": "LOW",
"attackRequirements": "NONE",
"attackVector": "NETWORK",
"baseScore": 9.3,
"baseSeverity": "CRITICAL",
"exploitMaturity": "NOT_DEFINED",
"privilegesRequired": "NONE",
"providerUrgency": "NOT_DEFINED",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "NONE",
"subIntegrityImpact": "NONE",
"userInteraction": "NONE",
"valueDensity": "NOT_DEFINED",
"vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:N/SC:N/SI:N/SA:N",
"version": "4.0",
"vulnAvailabilityImpact": "NONE",
"vulnConfidentialityImpact": "HIGH",
"vulnIntegrityImpact": "HIGH",
"vulnerabilityResponseEffort": "NOT_DEFINED"
},
"format": "CVSS",
"scenarios": [
{
"lang": "en",
"value": "GENERAL"
}
]
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-22",
"description": "CWE-22: Improper Limitation of a Pathname to a Restricted Directory (\u0027Path Traversal\u0027)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-06-29T17:51:30.077Z",
"orgId": "14ed7db2-1595-443d-9d34-6215bf890778",
"shortName": "Google"
},
"references": [
{
"url": "https://github.com/googleapis/mcp-toolbox/pull/3218"
}
],
"source": {
"discovery": "UNKNOWN"
},
"title": "Path Traversal in googleapis/mcp-toolbox HTTP Tool URL Builder",
"x_generator": {
"engine": "Vulnogram 1.0.2"
}
}
},
"cveMetadata": {
"assignerOrgId": "14ed7db2-1595-443d-9d34-6215bf890778",
"assignerShortName": "Google",
"cveId": "CVE-2026-11720",
"datePublished": "2026-06-29T17:51:30.077Z",
"dateReserved": "2026-06-09T00:57:55.333Z",
"dateUpdated": "2026-06-29T18:26:17.242Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-11719 (GCVE-0-2026-11719)
Vulnerability from cvelistv5 – Published: 2026-06-18 11:55 – Updated: 2026-06-18 13:53
VLAI
EPSS
VEX
Summary
An authenticated authorization bypass vulnerability exists in MCP Toolbox for Databases due to missing scope enforcement across older protocol handlers.
While the 2025-11-25 protocol version handler correctly enforces per-tool restrictions defined by scopesRequired, older supported protocol versions (2025-06-18, 2025-03-26, and 2024-11-05) omit this check. An authenticated client with low-privilege tokens (e.g., read) can bypass the intended per-tool scope restrictions and execute high-privilege tools (e.g., admin) simply by specifying an older protocol version in the MCP-Protocol-Version header, or by omitting the header entirely (which causes the server to default to the vulnerable 2024-11-05 handler).
Severity
SSVC
Exploitation: none
Automatable: no
Technical Impact: total
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-06-18 12:55 UTC
CWE
- CWE-862 - Missing Authorization
Assigner
References
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| MCP Toolbox for Databases (googleapis/mcp-toolbox) |
Affected:
1.3.0
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-11719",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "no"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-06-18T12:55:43.505312Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-06-18T13:53:08.793Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"defaultStatus": "unaffected",
"product": "MCP Toolbox for Databases (googleapis/mcp-toolbox)",
"vendor": "Google",
"versions": [
{
"status": "affected",
"version": "1.3.0"
}
]
}
],
"credits": [
{
"lang": "en",
"type": "finder",
"value": "HE WEI\uff08\u30ae\u30ab\u30af\uff09(https://www.linkedin.com/in/gikaku/)"
}
],
"descriptions": [
{
"lang": "en",
"supportingMedia": [
{
"base64": false,
"type": "text/html",
"value": "An authenticated authorization bypass vulnerability exists in MCP Toolbox for Databases due to missing scope enforcement across older protocol handlers.\n\nWhile the 2025-11-25 protocol version handler correctly enforces per-tool restrictions defined by scopesRequired, older supported protocol versions (2025-06-18, 2025-03-26, and 2024-11-05) omit this check. An authenticated client with low-privilege tokens (e.g., read) can bypass the intended per-tool scope restrictions and execute high-privilege tools (e.g., admin) simply by specifying an older protocol version in the MCP-Protocol-Version header, or by omitting the header entirely (which causes the server to default to the vulnerable 2024-11-05 handler)."
}
],
"value": "An authenticated authorization bypass vulnerability exists in MCP Toolbox for Databases due to missing scope enforcement across older protocol handlers.\n\nWhile the 2025-11-25 protocol version handler correctly enforces per-tool restrictions defined by scopesRequired, older supported protocol versions (2025-06-18, 2025-03-26, and 2024-11-05) omit this check. An authenticated client with low-privilege tokens (e.g., read) can bypass the intended per-tool scope restrictions and execute high-privilege tools (e.g., admin) simply by specifying an older protocol version in the MCP-Protocol-Version header, or by omitting the header entirely (which causes the server to default to the vulnerable 2024-11-05 handler)."
}
],
"impacts": [
{
"capecId": "CAPEC-115",
"descriptions": [
{
"lang": "en",
"value": "CAPEC-115: Authentication Bypass"
}
]
}
],
"metrics": [
{
"cvssV4_0": {
"Automatable": "NOT_DEFINED",
"Recovery": "NOT_DEFINED",
"Safety": "NOT_DEFINED",
"attackComplexity": "LOW",
"attackRequirements": "NONE",
"attackVector": "NETWORK",
"baseScore": 8.6,
"baseSeverity": "HIGH",
"exploitMaturity": "NOT_DEFINED",
"privilegesRequired": "LOW",
"providerUrgency": "NOT_DEFINED",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "NONE",
"subIntegrityImpact": "NONE",
"userInteraction": "NONE",
"valueDensity": "NOT_DEFINED",
"vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:N/SC:N/SI:N/SA:N",
"version": "4.0",
"vulnAvailabilityImpact": "NONE",
"vulnConfidentialityImpact": "HIGH",
"vulnIntegrityImpact": "HIGH",
"vulnerabilityResponseEffort": "NOT_DEFINED"
},
"format": "CVSS",
"scenarios": [
{
"lang": "en",
"value": "GENERAL"
}
]
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-862",
"description": "CWE-862: Missing Authorization",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-06-18T11:55:03.666Z",
"orgId": "14ed7db2-1595-443d-9d34-6215bf890778",
"shortName": "Google"
},
"references": [
{
"url": "https://github.com/googleapis/mcp-toolbox/pull/3335"
},
{
"url": "https://github.com/googleapis/mcp-toolbox/pull/3049"
}
],
"source": {
"discovery": "UNKNOWN"
},
"x_generator": {
"engine": "Vulnogram 1.0.2"
}
}
},
"cveMetadata": {
"assignerOrgId": "14ed7db2-1595-443d-9d34-6215bf890778",
"assignerShortName": "Google",
"cveId": "CVE-2026-11719",
"datePublished": "2026-06-18T11:55:03.666Z",
"dateReserved": "2026-06-09T00:53:57.846Z",
"dateUpdated": "2026-06-18T13:53:08.793Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-11718 (GCVE-0-2026-11718)
Vulnerability from cvelistv5 – Published: 2026-06-18 11:52 – Updated: 2026-06-18 13:53
VLAI
EPSS
VEX
Summary
An authentication bypass vulnerability exists in the generic opaque token validation path (validateOpaqueToken) of googleapis/mcp-toolbox.
When the toolbox validates an opaque token via an OAuth 2.0 introspection endpoint (RFC 7662), it decodes the response into an introspectResp struct. However, the subsequent claim-checking logic (validateClaims) evaluates the issuer condition as if a.issuer != "" && iss != "". If the external OAuth provider's introspection response omits the optional iss (issuer) field completely, the variable iss defaults to an empty string. This causes the conditional block to evaluate to false and be skipped silently. Consequently, the application accepts tokens issued by unauthorized or unintended third-party identity providers.
Severity
SSVC
Exploitation: none
Automatable: yes
Technical Impact: total
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-06-18 13:01 UTC
CWE
- CWE-287 - Improper Authentication
Assigner
References
1 reference
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| MCP Toolbox for Databases (googleapis/mcp-toolbox) |
Affected:
1.0.0 , ≤ 1.3.0
(semver)
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-11718",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-06-18T13:01:08.666194Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-06-18T13:53:14.985Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"defaultStatus": "unaffected",
"product": "MCP Toolbox for Databases (googleapis/mcp-toolbox)",
"vendor": "Google",
"versions": [
{
"lessThanOrEqual": "1.3.0",
"status": "affected",
"version": "1.0.0",
"versionType": "semver"
}
]
}
],
"credits": [
{
"lang": "en",
"type": "finder",
"value": "HaoNH Leader Redteam From VINCSS ( Member Of Vingroup )."
}
],
"descriptions": [
{
"lang": "en",
"supportingMedia": [
{
"base64": false,
"type": "text/html",
"value": "An authentication bypass vulnerability exists in the generic opaque token validation path (validateOpaqueToken) of googleapis/mcp-toolbox.\n\nWhen the toolbox validates an opaque token via an OAuth 2.0 introspection endpoint (RFC 7662), it decodes the response into an introspectResp struct. However, the subsequent claim-checking logic (validateClaims) evaluates the issuer condition as if a.issuer != \"\" \u0026amp;\u0026amp; iss != \"\". If the external OAuth provider\u0027s introspection response omits the optional iss (issuer) field completely, the variable iss defaults to an empty string. This causes the conditional block to evaluate to false and be skipped silently. Consequently, the application accepts tokens issued by unauthorized or unintended third-party identity providers."
}
],
"value": "An authentication bypass vulnerability exists in the generic opaque token validation path (validateOpaqueToken) of googleapis/mcp-toolbox.\n\nWhen the toolbox validates an opaque token via an OAuth 2.0 introspection endpoint (RFC 7662), it decodes the response into an introspectResp struct. However, the subsequent claim-checking logic (validateClaims) evaluates the issuer condition as if a.issuer != \"\" \u0026\u0026 iss != \"\". If the external OAuth provider\u0027s introspection response omits the optional iss (issuer) field completely, the variable iss defaults to an empty string. This causes the conditional block to evaluate to false and be skipped silently. Consequently, the application accepts tokens issued by unauthorized or unintended third-party identity providers."
}
],
"impacts": [
{
"capecId": "CAPEC-115",
"descriptions": [
{
"lang": "en",
"value": "CAPEC-115: Authentication Bypass"
}
]
}
],
"metrics": [
{
"cvssV4_0": {
"Automatable": "NOT_DEFINED",
"Recovery": "NOT_DEFINED",
"Safety": "NOT_DEFINED",
"attackComplexity": "LOW",
"attackRequirements": "NONE",
"attackVector": "NETWORK",
"baseScore": 9.3,
"baseSeverity": "CRITICAL",
"exploitMaturity": "NOT_DEFINED",
"privilegesRequired": "NONE",
"providerUrgency": "NOT_DEFINED",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "NONE",
"subIntegrityImpact": "NONE",
"userInteraction": "NONE",
"valueDensity": "NOT_DEFINED",
"vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:N/SC:N/SI:N/SA:N",
"version": "4.0",
"vulnAvailabilityImpact": "NONE",
"vulnConfidentialityImpact": "HIGH",
"vulnIntegrityImpact": "HIGH",
"vulnerabilityResponseEffort": "NOT_DEFINED"
},
"format": "CVSS",
"scenarios": [
{
"lang": "en",
"value": "GENERAL"
}
]
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-287",
"description": "CWE-287: Improper Authentication",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-06-18T11:52:42.327Z",
"orgId": "14ed7db2-1595-443d-9d34-6215bf890778",
"shortName": "Google"
},
"references": [
{
"url": "https://github.com/googleapis/mcp-toolbox/pull/3360"
}
],
"source": {
"discovery": "UNKNOWN"
},
"x_generator": {
"engine": "Vulnogram 1.0.2"
}
}
},
"cveMetadata": {
"assignerOrgId": "14ed7db2-1595-443d-9d34-6215bf890778",
"assignerShortName": "Google",
"cveId": "CVE-2026-11718",
"datePublished": "2026-06-18T11:52:42.327Z",
"dateReserved": "2026-06-09T00:49:55.908Z",
"dateUpdated": "2026-06-18T13:53:14.985Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-11717 (GCVE-0-2026-11717)
Vulnerability from cvelistv5 – Published: 2026-06-18 11:50 – Updated: 2026-06-18 12:23
VLAI
EPSS
VEX
Summary
An authentication bypass vulnerability exists in the generic opaque token validation path (validateOpaqueToken) of googleapis/mcp-toolbox.
When verifying an unparsed opaque token via an OAuth 2.0 introspection endpoint (RFC 7662), the toolbox decodes the response into an introspectResp struct where the Active field is declared as a pointer to a boolean (*bool). The code only explicitly rejects a token if the response contains a populated active field set to false (if introspectResp.Active != nil && !*introspectResp.Active). If an introspection endpoint responds with a payload that completely omits the mandatory active key, the internal variable remains nil, causing the conditional check to short-circuit. As a result, Toolbox accepts authorization tokens missing the "active" field, granting access to protected tools and underlying data sources.
Severity
SSVC
Exploitation: none
Automatable: yes
Technical Impact: total
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-06-18 12:23 UTC
CWE
- CWE-287 - Improper Authentication
Assigner
References
1 reference
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| MCP Toolbox for Databases (googleapis/mcp-toolbox) |
Affected:
1.0.0 , ≤ 1.3.0
(semver)
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-11717",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-06-18T12:23:05.330652Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-06-18T12:23:15.209Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"defaultStatus": "unaffected",
"product": "MCP Toolbox for Databases (googleapis/mcp-toolbox)",
"vendor": "Google",
"versions": [
{
"lessThanOrEqual": "1.3.0",
"status": "affected",
"version": "1.0.0",
"versionType": "semver"
}
]
}
],
"credits": [
{
"lang": "en",
"type": "finder",
"value": "HaoNH Leader Redteam From VINCSS ( Member Of Vingroup )"
}
],
"descriptions": [
{
"lang": "en",
"supportingMedia": [
{
"base64": false,
"type": "text/html",
"value": "An authentication bypass vulnerability exists in the generic opaque token validation path (validateOpaqueToken) of googleapis/mcp-toolbox.\n\nWhen verifying an unparsed opaque token via an OAuth 2.0 introspection endpoint (RFC 7662), the toolbox decodes the response into an introspectResp struct where the Active field is declared as a pointer to a boolean (*bool). The code only explicitly rejects a token if the response contains a populated active field set to false (if introspectResp.Active != nil \u0026amp;\u0026amp; !*introspectResp.Active). If an introspection endpoint responds with a payload that completely omits the mandatory active key, the internal variable remains nil, causing the conditional check to short-circuit. As a result, Toolbox accepts authorization tokens missing the \"active\" field, granting access to protected tools and underlying data sources."
}
],
"value": "An authentication bypass vulnerability exists in the generic opaque token validation path (validateOpaqueToken) of googleapis/mcp-toolbox.\n\nWhen verifying an unparsed opaque token via an OAuth 2.0 introspection endpoint (RFC 7662), the toolbox decodes the response into an introspectResp struct where the Active field is declared as a pointer to a boolean (*bool). The code only explicitly rejects a token if the response contains a populated active field set to false (if introspectResp.Active != nil \u0026\u0026 !*introspectResp.Active). If an introspection endpoint responds with a payload that completely omits the mandatory active key, the internal variable remains nil, causing the conditional check to short-circuit. As a result, Toolbox accepts authorization tokens missing the \"active\" field, granting access to protected tools and underlying data sources."
}
],
"impacts": [
{
"capecId": "CAPEC-114",
"descriptions": [
{
"lang": "en",
"value": "CAPEC-114: Authentication Abuse"
}
]
}
],
"metrics": [
{
"cvssV4_0": {
"Automatable": "NOT_DEFINED",
"Recovery": "NOT_DEFINED",
"Safety": "NOT_DEFINED",
"attackComplexity": "LOW",
"attackRequirements": "NONE",
"attackVector": "NETWORK",
"baseScore": 9.3,
"baseSeverity": "CRITICAL",
"exploitMaturity": "NOT_DEFINED",
"privilegesRequired": "NONE",
"providerUrgency": "NOT_DEFINED",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "NONE",
"subIntegrityImpact": "NONE",
"userInteraction": "NONE",
"valueDensity": "NOT_DEFINED",
"vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:N/SC:N/SI:N/SA:N",
"version": "4.0",
"vulnAvailabilityImpact": "NONE",
"vulnConfidentialityImpact": "HIGH",
"vulnIntegrityImpact": "HIGH",
"vulnerabilityResponseEffort": "NOT_DEFINED"
},
"format": "CVSS",
"scenarios": [
{
"lang": "en",
"value": "GENERAL"
}
]
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-287",
"description": "CWE-287: Improper Authentication",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-06-18T11:50:23.665Z",
"orgId": "14ed7db2-1595-443d-9d34-6215bf890778",
"shortName": "Google"
},
"references": [
{
"url": "https://github.com/googleapis/mcp-toolbox/pull/3341"
}
],
"source": {
"discovery": "UNKNOWN"
},
"x_generator": {
"engine": "Vulnogram 1.0.2"
}
}
},
"cveMetadata": {
"assignerOrgId": "14ed7db2-1595-443d-9d34-6215bf890778",
"assignerShortName": "Google",
"cveId": "CVE-2026-11717",
"datePublished": "2026-06-18T11:50:23.665Z",
"dateReserved": "2026-06-09T00:41:54.835Z",
"dateUpdated": "2026-06-18T12:23:15.209Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}