Search
Find a vulnerability
Search criteria
10 vulnerabilities found for mcp-toolbox by Google
CVE-2026-14541 (GCVE-0-2026-14541)
Vulnerability from nvd – Published: 2026-07-31 01:48 – Updated: 2026-07-31 16:14
VLAI
EPSS
VEX
Title
Authentication Bypass and Audience Confusion in MCP Toolbox OAuth Provider
Summary
An authentication bypass and audience confusion vulnerability exists in the Google OAuth provider component of Google mcp-toolbox version 1.4.0. When a Google authService is initialized with mcpEnabled: true but lacks an explicitly defined audience or clientId, the ValidateMCPAuth pipeline for opaque tokens skips audience validation entirely. As a result, the toolbox will accept any valid Google OAuth access token—even those minted for unrelated ecosystem applications—granting unauthorized clients access to protected tools and data backends.
Severity
SSVC
Exploitation: none
Automatable: yes
Technical Impact: total
CISA Coordinator (v2.0.3)
CWE
- CWE-287 - (Improper Authentication)
Assigner
References
1 reference
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| mcp-toolbox |
Affected:
1.4.0
(semver)
|
Credits
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-14541",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-07-31T16:14:40.882881Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-07-31T16:14:54.005Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"defaultStatus": "unaffected",
"product": "mcp-toolbox",
"vendor": "Google",
"versions": [
{
"status": "affected",
"version": "1.4.0",
"versionType": "semver"
}
]
}
],
"credits": [
{
"lang": "en",
"type": "finder",
"value": "HE WEI (\u30ae\u30ab\u30af)"
}
],
"descriptions": [
{
"lang": "en",
"supportingMedia": [
{
"base64": false,
"type": "text/html",
"value": "An authentication bypass and audience confusion vulnerability exists in the Google OAuth provider component of Google mcp-toolbox version 1.4.0. When a Google authService is initialized with mcpEnabled: true but lacks an explicitly defined audience or clientId, the ValidateMCPAuth pipeline for opaque tokens skips audience validation entirely. As a result, the toolbox will accept any valid Google OAuth access token\u2014even those minted for unrelated ecosystem applications\u2014granting unauthorized clients access to protected tools and data backends."
}
],
"value": "An authentication bypass and audience confusion vulnerability exists in the Google OAuth provider component of Google mcp-toolbox version 1.4.0. When a Google authService is initialized with mcpEnabled: true but lacks an explicitly defined audience or clientId, the ValidateMCPAuth pipeline for opaque tokens skips audience validation entirely. As a result, the toolbox will accept any valid Google OAuth access token\u2014even those minted for unrelated ecosystem applications\u2014granting unauthorized clients access to protected tools and data backends."
}
],
"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,
"baseSeverity": "HIGH",
"exploitMaturity": "UNREPORTED",
"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/E:U",
"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": "2026-07-31T01:48:39.019Z",
"orgId": "14ed7db2-1595-443d-9d34-6215bf890778",
"shortName": "Google"
},
"references": [
{
"url": "https://github.com/googleapis/mcp-toolbox/pull/3450"
}
],
"source": {
"discovery": "UNKNOWN"
},
"title": "Authentication Bypass and Audience Confusion in MCP Toolbox OAuth Provider",
"x_generator": {
"engine": "Vulnogram 1.0.2"
}
}
},
"cveMetadata": {
"assignerOrgId": "14ed7db2-1595-443d-9d34-6215bf890778",
"assignerShortName": "Google",
"cveId": "CVE-2026-14541",
"datePublished": "2026-07-31T01:48:39.019Z",
"dateReserved": "2026-07-03T03:38:02.749Z",
"dateUpdated": "2026-07-31T16:14:54.005Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-14540 (GCVE-0-2026-14540)
Vulnerability from nvd – Published: 2026-07-31 01:46 – Updated: 2026-07-31 16:12
VLAI
EPSS
VEX
Title
Server-Side Request Forgery via Unrestricted HTTP Redirection in MCP Toolbox
Summary
A Server-Side Request Forgery (SSRF) vulnerability exists in the generic HTTP source and tool components of Google mcp-toolbox versions 0.3.0 through 1.4.0. While the toolbox implements baseline input sanitization for user-controlled parameters, the underlying HTTP client (internal/sources/http/http.go) fails to safely regulate request redirection boundaries. Specifically, the client is initialized without a restrictive CheckRedirect policy hook and lacks target IP validation. An attacker or a malicious data-driven prompt can supply a crafted path parameter that triggers an open redirect or a direct destination swap on the target backend, coercing the mcp-toolbox into blindly following the redirection and making unauthorized requests to internal or arbitrary external endpoints.
Severity
SSVC
Exploitation: none
Automatable: yes
Technical Impact: total
CISA Coordinator (v2.0.3)
CWE
- CWE-918 - (Server-Side Request Forgery (SSRF))
Assigner
References
1 reference
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| mcp-toolbox |
Affected:
0.3.0 , ≤ 1.4.0
(semver)
|
Credits
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-14540",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-07-31T16:12:37.398569Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-07-31T16:12:49.663Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"defaultStatus": "unaffected",
"product": "mcp-toolbox",
"vendor": "Google",
"versions": [
{
"lessThanOrEqual": "1.4.0",
"status": "affected",
"version": "0.3.0",
"versionType": "semver"
}
]
}
],
"credits": [
{
"lang": "en",
"type": "finder",
"value": "Syed Anas Mohiuddin"
}
],
"descriptions": [
{
"lang": "en",
"supportingMedia": [
{
"base64": false,
"type": "text/html",
"value": "A Server-Side Request Forgery (SSRF) vulnerability exists in the generic HTTP source and tool components of Google mcp-toolbox versions 0.3.0 through 1.4.0. While the toolbox implements baseline input sanitization for user-controlled parameters, the underlying HTTP client (internal/sources/http/http.go) fails to safely regulate request redirection boundaries. Specifically, the client is initialized without a restrictive CheckRedirect policy hook and lacks target IP validation. An attacker or a malicious data-driven prompt can supply a crafted path parameter that triggers an open redirect or a direct destination swap on the target backend, coercing the mcp-toolbox into blindly following the redirection and making unauthorized requests to internal or arbitrary external endpoints."
}
],
"value": "A Server-Side Request Forgery (SSRF) vulnerability exists in the generic HTTP source and tool components of Google mcp-toolbox versions 0.3.0 through 1.4.0. While the toolbox implements baseline input sanitization for user-controlled parameters, the underlying HTTP client (internal/sources/http/http.go) fails to safely regulate request redirection boundaries. Specifically, the client is initialized without a restrictive CheckRedirect policy hook and lacks target IP validation. An attacker or a malicious data-driven prompt can supply a crafted path parameter that triggers an open redirect or a direct destination swap on the target backend, coercing the mcp-toolbox into blindly following the redirection and making unauthorized requests to internal or arbitrary external endpoints."
}
],
"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,
"baseSeverity": "HIGH",
"exploitMaturity": "UNREPORTED",
"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/E:U",
"version": "4.0",
"vulnAvailabilityImpact": "NONE",
"vulnConfidentialityImpact": "HIGH",
"vulnIntegrityImpact": "HIGH",
"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": "2026-07-31T01:46:54.942Z",
"orgId": "14ed7db2-1595-443d-9d34-6215bf890778",
"shortName": "Google"
},
"references": [
{
"url": "https://github.com/googleapis/mcp-toolbox/pull/3448"
}
],
"source": {
"discovery": "UNKNOWN"
},
"title": "Server-Side Request Forgery via Unrestricted HTTP Redirection in MCP Toolbox",
"x_generator": {
"engine": "Vulnogram 1.0.2"
}
}
},
"cveMetadata": {
"assignerOrgId": "14ed7db2-1595-443d-9d34-6215bf890778",
"assignerShortName": "Google",
"cveId": "CVE-2026-14540",
"datePublished": "2026-07-31T01:46:54.942Z",
"dateReserved": "2026-07-03T03:28:09.464Z",
"dateUpdated": "2026-07-31T16:12:49.663Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-14539 (GCVE-0-2026-14539)
Vulnerability from nvd – Published: 2026-07-31 01:45 – Updated: 2026-07-31 16:11
VLAI
EPSS
VEX
Title
Denial of Service via Unrestricted Payload Buffering in MCP Toolbox
Summary
An allocation of resources without limits vulnerability in the HTTP handler component of Google mcp-toolbox versions up to and including 1.4.0 allows an unauthenticated attacker to cause a denial of service (DoS). The /mcp endpoint handler reads incoming payloads directly into system memory using an unrestricted buffer loop (io.ReadAll) without applying defensive constraints such as http.MaxBytesReader or pre-read Content-Length enforcement. By submitting a single, massive HTTP request body, an attacker can linearly consume available host memory until the runtime process is terminated by an Out-Of-Memory (OOM) error.
Severity
SSVC
Exploitation: none
Automatable: yes
Technical Impact: partial
CISA Coordinator (v2.0.3)
CWE
- CWE-770 - (Allocation of Resources Without Limits or Throttling)
Assigner
References
1 reference
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| mcp-toolbox |
Affected:
0.0.0 , ≤ 1.4.0
(semver)
|
Credits
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-14539",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-07-31T16:10:46.118537Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-07-31T16:11:48.201Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"defaultStatus": "unaffected",
"product": "mcp-toolbox",
"vendor": "Google",
"versions": [
{
"lessThanOrEqual": "1.4.0",
"status": "affected",
"version": "0.0.0",
"versionType": "semver"
}
]
}
],
"credits": [
{
"lang": "en",
"type": "finder",
"value": "HE WEI (\u30ae\u30ab\u30af)"
}
],
"descriptions": [
{
"lang": "en",
"supportingMedia": [
{
"base64": false,
"type": "text/html",
"value": "An allocation of resources without limits vulnerability in the HTTP handler component of Google mcp-toolbox versions up to and including 1.4.0 allows an unauthenticated attacker to cause a denial of service (DoS). The /mcp endpoint handler reads incoming payloads directly into system memory using an unrestricted buffer loop (io.ReadAll) without applying defensive constraints such as http.MaxBytesReader or pre-read Content-Length enforcement. By submitting a single, massive HTTP request body, an attacker can linearly consume available host memory until the runtime process is terminated by an Out-Of-Memory (OOM) error."
}
],
"value": "An allocation of resources without limits vulnerability in the HTTP handler component of Google mcp-toolbox versions up to and including 1.4.0 allows an unauthenticated attacker to cause a denial of service (DoS). The /mcp endpoint handler reads incoming payloads directly into system memory using an unrestricted buffer loop (io.ReadAll) without applying defensive constraints such as http.MaxBytesReader or pre-read Content-Length enforcement. By submitting a single, massive HTTP request body, an attacker can linearly consume available host memory until the runtime process is terminated by an Out-Of-Memory (OOM) error."
}
],
"impacts": [
{
"capecId": "CAPEC-130",
"descriptions": [
{
"lang": "en",
"value": "CAPEC-130 Excessive Allocation"
}
]
}
],
"metrics": [
{
"cvssV4_0": {
"Automatable": "NOT_DEFINED",
"Recovery": "NOT_DEFINED",
"Safety": "NOT_DEFINED",
"attackComplexity": "LOW",
"attackRequirements": "NONE",
"attackVector": "NETWORK",
"baseScore": 6.6,
"baseSeverity": "MEDIUM",
"exploitMaturity": "UNREPORTED",
"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:N/VI:N/VA:H/SC:N/SI:N/SA:N/E:U",
"version": "4.0",
"vulnAvailabilityImpact": "HIGH",
"vulnConfidentialityImpact": "NONE",
"vulnIntegrityImpact": "NONE",
"vulnerabilityResponseEffort": "NOT_DEFINED"
},
"format": "CVSS",
"scenarios": [
{
"lang": "en",
"value": "GENERAL"
}
]
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-770",
"description": "CWE-770 (Allocation of Resources Without Limits or Throttling)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-07-31T01:45:35.468Z",
"orgId": "14ed7db2-1595-443d-9d34-6215bf890778",
"shortName": "Google"
},
"references": [
{
"url": "https://github.com/googleapis/mcp-toolbox/pull/3216"
}
],
"source": {
"discovery": "UNKNOWN"
},
"title": "Denial of Service via Unrestricted Payload Buffering in MCP Toolbox",
"x_generator": {
"engine": "Vulnogram 1.0.2"
}
}
},
"cveMetadata": {
"assignerOrgId": "14ed7db2-1595-443d-9d34-6215bf890778",
"assignerShortName": "Google",
"cveId": "CVE-2026-14539",
"datePublished": "2026-07-31T01:45:35.468Z",
"dateReserved": "2026-07-03T02:17:44.796Z",
"dateUpdated": "2026-07-31T16:11:48.201Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-14538 (GCVE-0-2026-14538)
Vulnerability from nvd – Published: 2026-07-31 01:42 – Updated: 2026-07-31 16:09
VLAI
EPSS
VEX
Title
BigQuery Dataset Allowlist Bypass via Metadata Dry-Run in MCP Toolbox
Summary
An improper authorization and security-boundary bypass vulnerability in the bigquery-execute-sql tool component of Google mcp-toolbox versions 0.16.1 through 1.4.0 allows an authenticated attacker to bypass allowedDatasets validation checks. The toolbox relies on the BigQuery dry-run API to enforce dataset restrictions, but due to a fail-open logic flaw, it bypasses validation when the API returns an empty array for specialized constructs. This allows the attacker to extract structural DDL schemas for explicitly excluded datasets via INFORMATION_SCHEMA, and access downstream federated row data via EXTERNAL_QUERY connections.
Severity
SSVC
Exploitation: none
Automatable: no
Technical Impact: partial
CISA Coordinator (v2.0.3)
Assigner
References
1 reference
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| mcp-toolbox |
Affected:
0.16.1 , ≤ 1.4.0
(semver)
|
Credits
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-14538",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-07-31T16:09:10.915078Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-07-31T16:09:31.250Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"defaultStatus": "unaffected",
"product": "mcp-toolbox",
"vendor": "Google",
"versions": [
{
"lessThanOrEqual": "1.4.0",
"status": "affected",
"version": "0.16.1",
"versionType": "semver"
}
]
}
],
"credits": [
{
"lang": "en",
"type": "finder",
"value": "HE WEI (\u30ae\u30ab\u30af)"
}
],
"descriptions": [
{
"lang": "en",
"supportingMedia": [
{
"base64": false,
"type": "text/html",
"value": "An improper authorization and security-boundary bypass vulnerability in the bigquery-execute-sql tool component of Google mcp-toolbox versions 0.16.1 through 1.4.0 allows an authenticated attacker to bypass allowedDatasets validation checks. The toolbox relies on the BigQuery dry-run API to enforce dataset restrictions, but due to a fail-open logic flaw, it bypasses validation when the API returns an empty array for specialized constructs. This allows the attacker to extract structural DDL schemas for explicitly excluded datasets via INFORMATION_SCHEMA, and access downstream federated row data via EXTERNAL_QUERY connections."
}
],
"value": "An improper authorization and security-boundary bypass vulnerability in the bigquery-execute-sql tool component of Google mcp-toolbox versions 0.16.1 through 1.4.0 allows an authenticated attacker to bypass allowedDatasets validation checks. The toolbox relies on the BigQuery dry-run API to enforce dataset restrictions, but due to a fail-open logic flaw, it bypasses validation when the API returns an empty array for specialized constructs. This allows the attacker to extract structural DDL schemas for explicitly excluded datasets via INFORMATION_SCHEMA, and access downstream federated row data via EXTERNAL_QUERY connections."
}
],
"impacts": [
{
"capecId": "CAPEC-180",
"descriptions": [
{
"lang": "en",
"value": "CAPEC-180 Exploiting Incorrectly Configured Access Control Security Levels"
}
]
}
],
"metrics": [
{
"cvssV4_0": {
"Automatable": "NOT_DEFINED",
"Recovery": "NOT_DEFINED",
"Safety": "NOT_DEFINED",
"attackComplexity": "LOW",
"attackRequirements": "NONE",
"attackVector": "NETWORK",
"baseScore": 5.7,
"baseSeverity": "MEDIUM",
"exploitMaturity": "UNREPORTED",
"privilegesRequired": "LOW",
"providerUrgency": "NOT_DEFINED",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "HIGH",
"subIntegrityImpact": "NONE",
"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:N/SA:N/E:U",
"version": "4.0",
"vulnAvailabilityImpact": "NONE",
"vulnConfidentialityImpact": "HIGH",
"vulnIntegrityImpact": "NONE",
"vulnerabilityResponseEffort": "NOT_DEFINED"
},
"format": "CVSS",
"scenarios": [
{
"lang": "en",
"value": "GENERAL"
}
]
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-285",
"description": "CWE-285 (Improper Authorization)",
"lang": "en",
"type": "CWE"
},
{
"cweId": "CWE-863",
"description": "CWE-863 (Incorrect Authorization)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-07-31T01:42:29.707Z",
"orgId": "14ed7db2-1595-443d-9d34-6215bf890778",
"shortName": "Google"
},
"references": [
{
"url": "https://github.com/googleapis/mcp-toolbox/pull/3452"
}
],
"source": {
"discovery": "UNKNOWN"
},
"title": "BigQuery Dataset Allowlist Bypass via Metadata Dry-Run in MCP Toolbox",
"x_generator": {
"engine": "Vulnogram 1.0.2"
}
}
},
"cveMetadata": {
"assignerOrgId": "14ed7db2-1595-443d-9d34-6215bf890778",
"assignerShortName": "Google",
"cveId": "CVE-2026-14538",
"datePublished": "2026-07-31T01:42:29.707Z",
"dateReserved": "2026-07-03T02:06:17.583Z",
"dateUpdated": "2026-07-31T16:09:31.250Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-14537 (GCVE-0-2026-14537)
Vulnerability from nvd – Published: 2026-07-31 01:38 – Updated: 2026-07-31 16:08
VLAI
EPSS
VEX
Title
Authorization Bypass in MCP Toolbox Legacy HTTP Endpoints
Summary
Incorrect Authorization in the direct HTTP API tool invocation endpoint in Google mcp-toolbox versions v1.3.0 and v1.4.0 allows an unauthenticated attacker to invoke tools protected by the scopeRequired feature via sending tool invocation requests through legacy HTTP endpoints when the --enable-api flag is active.
Severity
SSVC
Exploitation: none
Automatable: yes
Technical Impact: total
CISA Coordinator (v2.0.3)
CWE
- CWE-863 - (Incorrect Authorization)
Assigner
References
1 reference
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| mcp-toolbox |
Affected:
1.3.0
Affected: v1.4.0 |
Credits
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-14537",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-07-31T16:04:28.390948Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-07-31T16:08:17.628Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"defaultStatus": "unaffected",
"product": "mcp-toolbox",
"vendor": "Google",
"versions": [
{
"status": "affected",
"version": "1.3.0"
},
{
"status": "affected",
"version": "v1.4.0"
}
]
}
],
"credits": [
{
"lang": "en",
"type": "finder",
"value": "HE WEI (\u30ae\u30ab\u30af)"
},
{
"lang": "en",
"type": "reporter",
"value": "David Carliez"
}
],
"descriptions": [
{
"lang": "en",
"supportingMedia": [
{
"base64": false,
"type": "text/html",
"value": "Incorrect Authorization in the direct HTTP API tool invocation endpoint in Google mcp-toolbox versions v1.3.0 and v1.4.0 allows an unauthenticated attacker to invoke tools protected by the scopeRequired feature via sending tool invocation requests through legacy HTTP endpoints when the --enable-api flag is active."
}
],
"value": "Incorrect Authorization in the direct HTTP API tool invocation endpoint in Google mcp-toolbox versions v1.3.0 and v1.4.0 allows an unauthenticated attacker to invoke tools protected by the scopeRequired feature via sending tool invocation requests through legacy HTTP endpoints when the --enable-api flag is active."
}
],
"impacts": [
{
"capecId": "CAPEC-180",
"descriptions": [
{
"lang": "en",
"value": "CAPEC-180 Exploiting Incorrectly Configured Access Control Security Levels"
}
]
}
],
"metrics": [
{
"cvssV4_0": {
"Automatable": "NOT_DEFINED",
"Recovery": "NOT_DEFINED",
"Safety": "NOT_DEFINED",
"attackComplexity": "LOW",
"attackRequirements": "NONE",
"attackVector": "NETWORK",
"baseScore": 8.1,
"baseSeverity": "HIGH",
"exploitMaturity": "UNREPORTED",
"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:H/SC:N/SI:N/SA:N/E:U",
"version": "4.0",
"vulnAvailabilityImpact": "HIGH",
"vulnConfidentialityImpact": "HIGH",
"vulnIntegrityImpact": "HIGH",
"vulnerabilityResponseEffort": "NOT_DEFINED"
},
"format": "CVSS",
"scenarios": [
{
"lang": "en",
"value": "GENERAL"
}
]
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-863",
"description": "CWE-863 (Incorrect Authorization)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-07-31T01:38:18.978Z",
"orgId": "14ed7db2-1595-443d-9d34-6215bf890778",
"shortName": "Google"
},
"references": [
{
"url": "https://github.com/googleapis/mcp-toolbox/pull/3435"
}
],
"source": {
"discovery": "UNKNOWN"
},
"title": "Authorization Bypass in MCP Toolbox Legacy HTTP Endpoints",
"x_generator": {
"engine": "Vulnogram 1.0.2"
}
}
},
"cveMetadata": {
"assignerOrgId": "14ed7db2-1595-443d-9d34-6215bf890778",
"assignerShortName": "Google",
"cveId": "CVE-2026-14537",
"datePublished": "2026-07-31T01:38:18.978Z",
"dateReserved": "2026-07-03T01:40:43.351Z",
"dateUpdated": "2026-07-31T16:08:17.628Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-14541 (GCVE-0-2026-14541)
Vulnerability from cvelistv5 – Published: 2026-07-31 01:48 – Updated: 2026-07-31 16:14
VLAI
EPSS
VEX
Title
Authentication Bypass and Audience Confusion in MCP Toolbox OAuth Provider
Summary
An authentication bypass and audience confusion vulnerability exists in the Google OAuth provider component of Google mcp-toolbox version 1.4.0. When a Google authService is initialized with mcpEnabled: true but lacks an explicitly defined audience or clientId, the ValidateMCPAuth pipeline for opaque tokens skips audience validation entirely. As a result, the toolbox will accept any valid Google OAuth access token—even those minted for unrelated ecosystem applications—granting unauthorized clients access to protected tools and data backends.
Severity
SSVC
Exploitation: none
Automatable: yes
Technical Impact: total
CISA Coordinator (v2.0.3)
CWE
- CWE-287 - (Improper Authentication)
Assigner
References
1 reference
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| mcp-toolbox |
Affected:
1.4.0
(semver)
|
Credits
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-14541",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-07-31T16:14:40.882881Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-07-31T16:14:54.005Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"defaultStatus": "unaffected",
"product": "mcp-toolbox",
"vendor": "Google",
"versions": [
{
"status": "affected",
"version": "1.4.0",
"versionType": "semver"
}
]
}
],
"credits": [
{
"lang": "en",
"type": "finder",
"value": "HE WEI (\u30ae\u30ab\u30af)"
}
],
"descriptions": [
{
"lang": "en",
"supportingMedia": [
{
"base64": false,
"type": "text/html",
"value": "An authentication bypass and audience confusion vulnerability exists in the Google OAuth provider component of Google mcp-toolbox version 1.4.0. When a Google authService is initialized with mcpEnabled: true but lacks an explicitly defined audience or clientId, the ValidateMCPAuth pipeline for opaque tokens skips audience validation entirely. As a result, the toolbox will accept any valid Google OAuth access token\u2014even those minted for unrelated ecosystem applications\u2014granting unauthorized clients access to protected tools and data backends."
}
],
"value": "An authentication bypass and audience confusion vulnerability exists in the Google OAuth provider component of Google mcp-toolbox version 1.4.0. When a Google authService is initialized with mcpEnabled: true but lacks an explicitly defined audience or clientId, the ValidateMCPAuth pipeline for opaque tokens skips audience validation entirely. As a result, the toolbox will accept any valid Google OAuth access token\u2014even those minted for unrelated ecosystem applications\u2014granting unauthorized clients access to protected tools and data backends."
}
],
"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,
"baseSeverity": "HIGH",
"exploitMaturity": "UNREPORTED",
"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/E:U",
"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": "2026-07-31T01:48:39.019Z",
"orgId": "14ed7db2-1595-443d-9d34-6215bf890778",
"shortName": "Google"
},
"references": [
{
"url": "https://github.com/googleapis/mcp-toolbox/pull/3450"
}
],
"source": {
"discovery": "UNKNOWN"
},
"title": "Authentication Bypass and Audience Confusion in MCP Toolbox OAuth Provider",
"x_generator": {
"engine": "Vulnogram 1.0.2"
}
}
},
"cveMetadata": {
"assignerOrgId": "14ed7db2-1595-443d-9d34-6215bf890778",
"assignerShortName": "Google",
"cveId": "CVE-2026-14541",
"datePublished": "2026-07-31T01:48:39.019Z",
"dateReserved": "2026-07-03T03:38:02.749Z",
"dateUpdated": "2026-07-31T16:14:54.005Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-14540 (GCVE-0-2026-14540)
Vulnerability from cvelistv5 – Published: 2026-07-31 01:46 – Updated: 2026-07-31 16:12
VLAI
EPSS
VEX
Title
Server-Side Request Forgery via Unrestricted HTTP Redirection in MCP Toolbox
Summary
A Server-Side Request Forgery (SSRF) vulnerability exists in the generic HTTP source and tool components of Google mcp-toolbox versions 0.3.0 through 1.4.0. While the toolbox implements baseline input sanitization for user-controlled parameters, the underlying HTTP client (internal/sources/http/http.go) fails to safely regulate request redirection boundaries. Specifically, the client is initialized without a restrictive CheckRedirect policy hook and lacks target IP validation. An attacker or a malicious data-driven prompt can supply a crafted path parameter that triggers an open redirect or a direct destination swap on the target backend, coercing the mcp-toolbox into blindly following the redirection and making unauthorized requests to internal or arbitrary external endpoints.
Severity
SSVC
Exploitation: none
Automatable: yes
Technical Impact: total
CISA Coordinator (v2.0.3)
CWE
- CWE-918 - (Server-Side Request Forgery (SSRF))
Assigner
References
1 reference
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| mcp-toolbox |
Affected:
0.3.0 , ≤ 1.4.0
(semver)
|
Credits
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-14540",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-07-31T16:12:37.398569Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-07-31T16:12:49.663Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"defaultStatus": "unaffected",
"product": "mcp-toolbox",
"vendor": "Google",
"versions": [
{
"lessThanOrEqual": "1.4.0",
"status": "affected",
"version": "0.3.0",
"versionType": "semver"
}
]
}
],
"credits": [
{
"lang": "en",
"type": "finder",
"value": "Syed Anas Mohiuddin"
}
],
"descriptions": [
{
"lang": "en",
"supportingMedia": [
{
"base64": false,
"type": "text/html",
"value": "A Server-Side Request Forgery (SSRF) vulnerability exists in the generic HTTP source and tool components of Google mcp-toolbox versions 0.3.0 through 1.4.0. While the toolbox implements baseline input sanitization for user-controlled parameters, the underlying HTTP client (internal/sources/http/http.go) fails to safely regulate request redirection boundaries. Specifically, the client is initialized without a restrictive CheckRedirect policy hook and lacks target IP validation. An attacker or a malicious data-driven prompt can supply a crafted path parameter that triggers an open redirect or a direct destination swap on the target backend, coercing the mcp-toolbox into blindly following the redirection and making unauthorized requests to internal or arbitrary external endpoints."
}
],
"value": "A Server-Side Request Forgery (SSRF) vulnerability exists in the generic HTTP source and tool components of Google mcp-toolbox versions 0.3.0 through 1.4.0. While the toolbox implements baseline input sanitization for user-controlled parameters, the underlying HTTP client (internal/sources/http/http.go) fails to safely regulate request redirection boundaries. Specifically, the client is initialized without a restrictive CheckRedirect policy hook and lacks target IP validation. An attacker or a malicious data-driven prompt can supply a crafted path parameter that triggers an open redirect or a direct destination swap on the target backend, coercing the mcp-toolbox into blindly following the redirection and making unauthorized requests to internal or arbitrary external endpoints."
}
],
"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,
"baseSeverity": "HIGH",
"exploitMaturity": "UNREPORTED",
"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/E:U",
"version": "4.0",
"vulnAvailabilityImpact": "NONE",
"vulnConfidentialityImpact": "HIGH",
"vulnIntegrityImpact": "HIGH",
"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": "2026-07-31T01:46:54.942Z",
"orgId": "14ed7db2-1595-443d-9d34-6215bf890778",
"shortName": "Google"
},
"references": [
{
"url": "https://github.com/googleapis/mcp-toolbox/pull/3448"
}
],
"source": {
"discovery": "UNKNOWN"
},
"title": "Server-Side Request Forgery via Unrestricted HTTP Redirection in MCP Toolbox",
"x_generator": {
"engine": "Vulnogram 1.0.2"
}
}
},
"cveMetadata": {
"assignerOrgId": "14ed7db2-1595-443d-9d34-6215bf890778",
"assignerShortName": "Google",
"cveId": "CVE-2026-14540",
"datePublished": "2026-07-31T01:46:54.942Z",
"dateReserved": "2026-07-03T03:28:09.464Z",
"dateUpdated": "2026-07-31T16:12:49.663Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-14539 (GCVE-0-2026-14539)
Vulnerability from cvelistv5 – Published: 2026-07-31 01:45 – Updated: 2026-07-31 16:11
VLAI
EPSS
VEX
Title
Denial of Service via Unrestricted Payload Buffering in MCP Toolbox
Summary
An allocation of resources without limits vulnerability in the HTTP handler component of Google mcp-toolbox versions up to and including 1.4.0 allows an unauthenticated attacker to cause a denial of service (DoS). The /mcp endpoint handler reads incoming payloads directly into system memory using an unrestricted buffer loop (io.ReadAll) without applying defensive constraints such as http.MaxBytesReader or pre-read Content-Length enforcement. By submitting a single, massive HTTP request body, an attacker can linearly consume available host memory until the runtime process is terminated by an Out-Of-Memory (OOM) error.
Severity
SSVC
Exploitation: none
Automatable: yes
Technical Impact: partial
CISA Coordinator (v2.0.3)
CWE
- CWE-770 - (Allocation of Resources Without Limits or Throttling)
Assigner
References
1 reference
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| mcp-toolbox |
Affected:
0.0.0 , ≤ 1.4.0
(semver)
|
Credits
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-14539",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-07-31T16:10:46.118537Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-07-31T16:11:48.201Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"defaultStatus": "unaffected",
"product": "mcp-toolbox",
"vendor": "Google",
"versions": [
{
"lessThanOrEqual": "1.4.0",
"status": "affected",
"version": "0.0.0",
"versionType": "semver"
}
]
}
],
"credits": [
{
"lang": "en",
"type": "finder",
"value": "HE WEI (\u30ae\u30ab\u30af)"
}
],
"descriptions": [
{
"lang": "en",
"supportingMedia": [
{
"base64": false,
"type": "text/html",
"value": "An allocation of resources without limits vulnerability in the HTTP handler component of Google mcp-toolbox versions up to and including 1.4.0 allows an unauthenticated attacker to cause a denial of service (DoS). The /mcp endpoint handler reads incoming payloads directly into system memory using an unrestricted buffer loop (io.ReadAll) without applying defensive constraints such as http.MaxBytesReader or pre-read Content-Length enforcement. By submitting a single, massive HTTP request body, an attacker can linearly consume available host memory until the runtime process is terminated by an Out-Of-Memory (OOM) error."
}
],
"value": "An allocation of resources without limits vulnerability in the HTTP handler component of Google mcp-toolbox versions up to and including 1.4.0 allows an unauthenticated attacker to cause a denial of service (DoS). The /mcp endpoint handler reads incoming payloads directly into system memory using an unrestricted buffer loop (io.ReadAll) without applying defensive constraints such as http.MaxBytesReader or pre-read Content-Length enforcement. By submitting a single, massive HTTP request body, an attacker can linearly consume available host memory until the runtime process is terminated by an Out-Of-Memory (OOM) error."
}
],
"impacts": [
{
"capecId": "CAPEC-130",
"descriptions": [
{
"lang": "en",
"value": "CAPEC-130 Excessive Allocation"
}
]
}
],
"metrics": [
{
"cvssV4_0": {
"Automatable": "NOT_DEFINED",
"Recovery": "NOT_DEFINED",
"Safety": "NOT_DEFINED",
"attackComplexity": "LOW",
"attackRequirements": "NONE",
"attackVector": "NETWORK",
"baseScore": 6.6,
"baseSeverity": "MEDIUM",
"exploitMaturity": "UNREPORTED",
"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:N/VI:N/VA:H/SC:N/SI:N/SA:N/E:U",
"version": "4.0",
"vulnAvailabilityImpact": "HIGH",
"vulnConfidentialityImpact": "NONE",
"vulnIntegrityImpact": "NONE",
"vulnerabilityResponseEffort": "NOT_DEFINED"
},
"format": "CVSS",
"scenarios": [
{
"lang": "en",
"value": "GENERAL"
}
]
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-770",
"description": "CWE-770 (Allocation of Resources Without Limits or Throttling)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-07-31T01:45:35.468Z",
"orgId": "14ed7db2-1595-443d-9d34-6215bf890778",
"shortName": "Google"
},
"references": [
{
"url": "https://github.com/googleapis/mcp-toolbox/pull/3216"
}
],
"source": {
"discovery": "UNKNOWN"
},
"title": "Denial of Service via Unrestricted Payload Buffering in MCP Toolbox",
"x_generator": {
"engine": "Vulnogram 1.0.2"
}
}
},
"cveMetadata": {
"assignerOrgId": "14ed7db2-1595-443d-9d34-6215bf890778",
"assignerShortName": "Google",
"cveId": "CVE-2026-14539",
"datePublished": "2026-07-31T01:45:35.468Z",
"dateReserved": "2026-07-03T02:17:44.796Z",
"dateUpdated": "2026-07-31T16:11:48.201Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-14538 (GCVE-0-2026-14538)
Vulnerability from cvelistv5 – Published: 2026-07-31 01:42 – Updated: 2026-07-31 16:09
VLAI
EPSS
VEX
Title
BigQuery Dataset Allowlist Bypass via Metadata Dry-Run in MCP Toolbox
Summary
An improper authorization and security-boundary bypass vulnerability in the bigquery-execute-sql tool component of Google mcp-toolbox versions 0.16.1 through 1.4.0 allows an authenticated attacker to bypass allowedDatasets validation checks. The toolbox relies on the BigQuery dry-run API to enforce dataset restrictions, but due to a fail-open logic flaw, it bypasses validation when the API returns an empty array for specialized constructs. This allows the attacker to extract structural DDL schemas for explicitly excluded datasets via INFORMATION_SCHEMA, and access downstream federated row data via EXTERNAL_QUERY connections.
Severity
SSVC
Exploitation: none
Automatable: no
Technical Impact: partial
CISA Coordinator (v2.0.3)
Assigner
References
1 reference
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| mcp-toolbox |
Affected:
0.16.1 , ≤ 1.4.0
(semver)
|
Credits
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-14538",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-07-31T16:09:10.915078Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-07-31T16:09:31.250Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"defaultStatus": "unaffected",
"product": "mcp-toolbox",
"vendor": "Google",
"versions": [
{
"lessThanOrEqual": "1.4.0",
"status": "affected",
"version": "0.16.1",
"versionType": "semver"
}
]
}
],
"credits": [
{
"lang": "en",
"type": "finder",
"value": "HE WEI (\u30ae\u30ab\u30af)"
}
],
"descriptions": [
{
"lang": "en",
"supportingMedia": [
{
"base64": false,
"type": "text/html",
"value": "An improper authorization and security-boundary bypass vulnerability in the bigquery-execute-sql tool component of Google mcp-toolbox versions 0.16.1 through 1.4.0 allows an authenticated attacker to bypass allowedDatasets validation checks. The toolbox relies on the BigQuery dry-run API to enforce dataset restrictions, but due to a fail-open logic flaw, it bypasses validation when the API returns an empty array for specialized constructs. This allows the attacker to extract structural DDL schemas for explicitly excluded datasets via INFORMATION_SCHEMA, and access downstream federated row data via EXTERNAL_QUERY connections."
}
],
"value": "An improper authorization and security-boundary bypass vulnerability in the bigquery-execute-sql tool component of Google mcp-toolbox versions 0.16.1 through 1.4.0 allows an authenticated attacker to bypass allowedDatasets validation checks. The toolbox relies on the BigQuery dry-run API to enforce dataset restrictions, but due to a fail-open logic flaw, it bypasses validation when the API returns an empty array for specialized constructs. This allows the attacker to extract structural DDL schemas for explicitly excluded datasets via INFORMATION_SCHEMA, and access downstream federated row data via EXTERNAL_QUERY connections."
}
],
"impacts": [
{
"capecId": "CAPEC-180",
"descriptions": [
{
"lang": "en",
"value": "CAPEC-180 Exploiting Incorrectly Configured Access Control Security Levels"
}
]
}
],
"metrics": [
{
"cvssV4_0": {
"Automatable": "NOT_DEFINED",
"Recovery": "NOT_DEFINED",
"Safety": "NOT_DEFINED",
"attackComplexity": "LOW",
"attackRequirements": "NONE",
"attackVector": "NETWORK",
"baseScore": 5.7,
"baseSeverity": "MEDIUM",
"exploitMaturity": "UNREPORTED",
"privilegesRequired": "LOW",
"providerUrgency": "NOT_DEFINED",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "HIGH",
"subIntegrityImpact": "NONE",
"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:N/SA:N/E:U",
"version": "4.0",
"vulnAvailabilityImpact": "NONE",
"vulnConfidentialityImpact": "HIGH",
"vulnIntegrityImpact": "NONE",
"vulnerabilityResponseEffort": "NOT_DEFINED"
},
"format": "CVSS",
"scenarios": [
{
"lang": "en",
"value": "GENERAL"
}
]
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-285",
"description": "CWE-285 (Improper Authorization)",
"lang": "en",
"type": "CWE"
},
{
"cweId": "CWE-863",
"description": "CWE-863 (Incorrect Authorization)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-07-31T01:42:29.707Z",
"orgId": "14ed7db2-1595-443d-9d34-6215bf890778",
"shortName": "Google"
},
"references": [
{
"url": "https://github.com/googleapis/mcp-toolbox/pull/3452"
}
],
"source": {
"discovery": "UNKNOWN"
},
"title": "BigQuery Dataset Allowlist Bypass via Metadata Dry-Run in MCP Toolbox",
"x_generator": {
"engine": "Vulnogram 1.0.2"
}
}
},
"cveMetadata": {
"assignerOrgId": "14ed7db2-1595-443d-9d34-6215bf890778",
"assignerShortName": "Google",
"cveId": "CVE-2026-14538",
"datePublished": "2026-07-31T01:42:29.707Z",
"dateReserved": "2026-07-03T02:06:17.583Z",
"dateUpdated": "2026-07-31T16:09:31.250Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-14537 (GCVE-0-2026-14537)
Vulnerability from cvelistv5 – Published: 2026-07-31 01:38 – Updated: 2026-07-31 16:08
VLAI
EPSS
VEX
Title
Authorization Bypass in MCP Toolbox Legacy HTTP Endpoints
Summary
Incorrect Authorization in the direct HTTP API tool invocation endpoint in Google mcp-toolbox versions v1.3.0 and v1.4.0 allows an unauthenticated attacker to invoke tools protected by the scopeRequired feature via sending tool invocation requests through legacy HTTP endpoints when the --enable-api flag is active.
Severity
SSVC
Exploitation: none
Automatable: yes
Technical Impact: total
CISA Coordinator (v2.0.3)
CWE
- CWE-863 - (Incorrect Authorization)
Assigner
References
1 reference
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| mcp-toolbox |
Affected:
1.3.0
Affected: v1.4.0 |
Credits
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-14537",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-07-31T16:04:28.390948Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-07-31T16:08:17.628Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"defaultStatus": "unaffected",
"product": "mcp-toolbox",
"vendor": "Google",
"versions": [
{
"status": "affected",
"version": "1.3.0"
},
{
"status": "affected",
"version": "v1.4.0"
}
]
}
],
"credits": [
{
"lang": "en",
"type": "finder",
"value": "HE WEI (\u30ae\u30ab\u30af)"
},
{
"lang": "en",
"type": "reporter",
"value": "David Carliez"
}
],
"descriptions": [
{
"lang": "en",
"supportingMedia": [
{
"base64": false,
"type": "text/html",
"value": "Incorrect Authorization in the direct HTTP API tool invocation endpoint in Google mcp-toolbox versions v1.3.0 and v1.4.0 allows an unauthenticated attacker to invoke tools protected by the scopeRequired feature via sending tool invocation requests through legacy HTTP endpoints when the --enable-api flag is active."
}
],
"value": "Incorrect Authorization in the direct HTTP API tool invocation endpoint in Google mcp-toolbox versions v1.3.0 and v1.4.0 allows an unauthenticated attacker to invoke tools protected by the scopeRequired feature via sending tool invocation requests through legacy HTTP endpoints when the --enable-api flag is active."
}
],
"impacts": [
{
"capecId": "CAPEC-180",
"descriptions": [
{
"lang": "en",
"value": "CAPEC-180 Exploiting Incorrectly Configured Access Control Security Levels"
}
]
}
],
"metrics": [
{
"cvssV4_0": {
"Automatable": "NOT_DEFINED",
"Recovery": "NOT_DEFINED",
"Safety": "NOT_DEFINED",
"attackComplexity": "LOW",
"attackRequirements": "NONE",
"attackVector": "NETWORK",
"baseScore": 8.1,
"baseSeverity": "HIGH",
"exploitMaturity": "UNREPORTED",
"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:H/SC:N/SI:N/SA:N/E:U",
"version": "4.0",
"vulnAvailabilityImpact": "HIGH",
"vulnConfidentialityImpact": "HIGH",
"vulnIntegrityImpact": "HIGH",
"vulnerabilityResponseEffort": "NOT_DEFINED"
},
"format": "CVSS",
"scenarios": [
{
"lang": "en",
"value": "GENERAL"
}
]
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-863",
"description": "CWE-863 (Incorrect Authorization)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-07-31T01:38:18.978Z",
"orgId": "14ed7db2-1595-443d-9d34-6215bf890778",
"shortName": "Google"
},
"references": [
{
"url": "https://github.com/googleapis/mcp-toolbox/pull/3435"
}
],
"source": {
"discovery": "UNKNOWN"
},
"title": "Authorization Bypass in MCP Toolbox Legacy HTTP Endpoints",
"x_generator": {
"engine": "Vulnogram 1.0.2"
}
}
},
"cveMetadata": {
"assignerOrgId": "14ed7db2-1595-443d-9d34-6215bf890778",
"assignerShortName": "Google",
"cveId": "CVE-2026-14537",
"datePublished": "2026-07-31T01:38:18.978Z",
"dateReserved": "2026-07-03T01:40:43.351Z",
"dateUpdated": "2026-07-31T16:08:17.628Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}