CVE-2026-77822 (GCVE-0-2026-77822)
Vulnerability from cvelistv5 – Published: 2026-09-04 15:15 – Updated: 2026-09-04 18:24
VLAI
EPSS
VEX
Title
IBM ContextForge MCP Gateway is affected by server-side request forgery (DNS rebinding) via the A2A agent invocation endpoint
Summary
IBM ContextForge MCP Gateway could allow a remote authenticated attacker to obtain sensitive information due to server-side request forgery via DNS rebinding.
Severity
8.2 (High)
SSVC
Exploitation: none
Automatable: no
Technical Impact: total
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-09-04 17:09 UTC
CWE
- CWE-918 - Server-Side Request Forgery (SSRF)
Assigner
References
1 reference
| URL | Tags |
|---|---|
| https://www.ibm.com/support/pages/node/7286055 | vendor-advisorypatch |
Impacted products
1 product
| Vendor | Product | Version | CPE status | |
|---|---|---|---|---|
| IBM | ContextForge MCP Gateway |
Affected:
<= v1.0.8
cpe:2.3:a:ibm:contextforge-mcp-gateway:*:*:*:*:*:*:*:* |
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-77822",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "no"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-09-04T17:09:15.348543Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-09-04T18:24:58.315Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"cpes": [
"cpe:2.3:a:ibm:contextforge-mcp-gateway:*:*:*:*:*:*:*:*"
],
"product": "ContextForge MCP Gateway",
"vendor": "IBM",
"versions": [
{
"status": "affected",
"version": "\u003c= v1.0.8"
}
]
}
],
"descriptions": [
{
"lang": "en",
"supportingMedia": [
{
"base64": false,
"type": "text/html",
"value": "\u003cp\u003eIBM ContextForge MCP Gateway could allow a remote authenticated attacker to obtain sensitive information due to server-side request forgery via DNS rebinding.\u003c/p\u003e"
}
],
"value": "IBM ContextForge MCP Gateway could allow a remote authenticated attacker to obtain sensitive information due to server-side request forgery via DNS rebinding."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "HIGH",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 8.2,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "LOW",
"scope": "CHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:C/C:H/I:H/A:N",
"version": "3.1"
},
"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": "2026-09-04T15:15:35.403Z",
"orgId": "9a959283-ebb5-44b6-b705-dcc2bbced522",
"shortName": "ibm"
},
"references": [
{
"tags": [
"vendor-advisory",
"patch"
],
"url": "https://www.ibm.com/support/pages/node/7286055"
}
],
"solutions": [
{
"lang": "en",
"supportingMedia": [
{
"base64": false,
"type": "text/html",
"value": "\u003cdiv\u003e\u003c/div\u003e\u003cp\u003e\u003cstrong\u003eIBM strongly recommends addressing the vulnerability now.\u003c/strong\u003e\u003c/p\u003e\u003cdiv\u003e\u003ctable\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd\u003e\u003cstrong\u003eProduct(s)\u003c/strong\u003e\u003c/td\u003e\u003ctd\u003e\u003cstrong\u003eVersion(s) number and/or range\u00a0\u003c/strong\u003e\u003c/td\u003e\u003ctd\u003e\u003cstrong\u003eRemediation/Fix/Instructions\u003c/strong\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd\u003eIBM ContextForge MCP Gateway\u003c/td\u003e\u003ctd\u003e\u0026lt;= v1.0.8\u003c/td\u003e\u003ctd\u003eUpgrade to v1.0.9\u00a0\n\u003cdiv\u003e\u003cdiv\u003e\u003ca href=\"https://github.com/IBM/mcp-context-forge/releases/tag/v1.0.9\" rel=\"nofollow\"\u003ehttps://github.com/IBM/mcp-context-forge/releases/tag/v1.0.9\u003c/a\u003e\u003c/div\u003e\u003c/div\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/table\u003e\u003c/div\u003e\u003cp\u003e\u00a0Note: \u0026lt;Component A / B names\u0026gt; are bundled with \u0026lt;Product profile name\u0026gt; to provide \u0026lt;feature / function description\u0026gt;\u003c/p\u003e\u003cp\u003e\u003c/p\u003e"
}
],
"value": "IBM strongly recommends addressing the vulnerability now.\n\nProduct(s)Version(s) number and/or range\u00a0Remediation/Fix/InstructionsIBM ContextForge MCP Gateway\u003c= v1.0.8Upgrade to v1.0.9\u00a0\n https://github.com/IBM/mcp-context-forge/releases/tag/v1.0.9 \n\n\n\n\n\n\n\n\u00a0Note: \u003cComponent A / B names\u003e are bundled with \u003cProduct profile name\u003e to provide \u003cfeature / function description\u003e"
}
],
"title": "IBM ContextForge MCP Gateway is affected by server-side request forgery (DNS rebinding) via the A2A agent invocation endpoint",
"workarounds": [
{
"lang": "en",
"supportingMedia": [
{
"base64": false,
"type": "text/html",
"value": "\u003cdiv\u003e\u003cdiv\u003eOperators who cannot immediately upgrade can reduce exposure by:\u003c/div\u003e\u003cbr/\u003e\u003cdiv\u003e1. **Disable A2A** \u2014 set the environment variable `MCPGATEWAY_A2A_ENABLED=False` to disable the A2A subsystem entirely. This removes the vulnerable endpoint from the attack surface at the cost of A2A functionality.\u003c/div\u003e\u003cdiv\u003e2. **Restrict A2A create/invoke permissions** \u2014 revoke A2A creation and invocation rights from developer and team_admin roles in environments where A2A is not required.\u003c/div\u003e\u003cdiv\u003e3. **Network-level egress controls** \u2014 enforce outbound network policy at the host or cloud level to block the gateway process from reaching cloud metadata endpoints and private RFC 1918 address ranges, preventing exploitation of the DNS-rebinding window even if a rebind attempt succeeds.\u003c/div\u003e\u003cbr/\u003e\u003cdiv\u003eNone of these mitigations eliminate the underlying vulnerability; IBM strongly recommends upgrading to the fixed version.\u003c/div\u003e\u003c/div\u003e"
}
],
"value": "Operators who cannot immediately upgrade can reduce exposure by:\n\n\n1. **Disable A2A** \u2014 set the environment variable `MCPGATEWAY_A2A_ENABLED=False` to disable the A2A subsystem entirely. This removes the vulnerable endpoint from the attack surface at the cost of A2A functionality.\n\n2. **Restrict A2A create/invoke permissions** \u2014 revoke A2A creation and invocation rights from developer and team_admin roles in environments where A2A is not required.\n\n3. **Network-level egress controls** \u2014 enforce outbound network policy at the host or cloud level to block the gateway process from reaching cloud metadata endpoints and private RFC 1918 address ranges, preventing exploitation of the DNS-rebinding window even if a rebind attempt succeeds.\n\n\nNone of these mitigations eliminate the underlying vulnerability; IBM strongly recommends upgrading to the fixed version."
}
]
}
},
"cveMetadata": {
"assignerOrgId": "9a959283-ebb5-44b6-b705-dcc2bbced522",
"assignerShortName": "ibm",
"cveId": "CVE-2026-77822",
"datePublished": "2026-09-04T15:15:35.403Z",
"dateReserved": "2026-08-21T14:36:12.469Z",
"dateUpdated": "2026-09-04T18:24:58.315Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2",
"vulnerability-lookup:meta": {
"nvd": "{\"cve\":{\"id\":\"CVE-2026-77822\",\"sourceIdentifier\":\"psirt@us.ibm.com\",\"published\":\"2026-09-04T16:17:59.550\",\"lastModified\":\"2026-09-04T19:17:27.240\",\"vulnStatus\":\"Received\",\"cveTags\":[],\"descriptions\":[{\"lang\":\"en\",\"value\":\"IBM ContextForge MCP Gateway could allow a remote authenticated attacker to obtain sensitive information due to server-side request forgery via DNS rebinding.\"}],\"affected\":[{\"source\":\"psirt@us.ibm.com\",\"affectedData\":[{\"vendor\":\"IBM\",\"product\":\"ContextForge MCP Gateway\",\"cpes\":[\"cpe:2.3:a:ibm:contextforge-mcp-gateway:*:*:*:*:*:*:*:*\"],\"versions\":[{\"version\":\"\u003c= v1.0.8\",\"status\":\"affected\"}]}]}],\"metrics\":{\"cvssMetricV31\":[{\"source\":\"psirt@us.ibm.com\",\"type\":\"Secondary\",\"cvssData\":{\"version\":\"3.1\",\"vectorString\":\"CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:C/C:H/I:H/A:N\",\"baseScore\":8.2,\"baseSeverity\":\"HIGH\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"HIGH\",\"privilegesRequired\":\"LOW\",\"userInteraction\":\"NONE\",\"scope\":\"CHANGED\",\"confidentialityImpact\":\"HIGH\",\"integrityImpact\":\"HIGH\",\"availabilityImpact\":\"NONE\"},\"exploitabilityScore\":1.8,\"impactScore\":5.8}],\"ssvcV203\":[{\"source\":\"134c704f-9b21-4f2e-91b3-4a467353bcc0\",\"ssvcData\":{\"timestamp\":\"2026-09-04T17:09:15.348543Z\",\"id\":\"CVE-2026-77822\",\"options\":[{\"exploitation\":\"none\"},{\"automatable\":\"no\"},{\"technicalImpact\":\"total\"}],\"role\":\"CISA Coordinator\",\"version\":\"2.0.3\"}}]},\"weaknesses\":[{\"source\":\"psirt@us.ibm.com\",\"type\":\"Secondary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-918\"}]}],\"references\":[{\"url\":\"https://www.ibm.com/support/pages/node/7286055\",\"source\":\"psirt@us.ibm.com\"}]}}",
"vulnrichment": {
"containers": "{\"cna\": {\"providerMetadata\": {\"orgId\": \"9a959283-ebb5-44b6-b705-dcc2bbced522\", \"shortName\": \"ibm\", \"dateUpdated\": \"2026-09-04T15:15:35.403Z\"}, \"title\": \"IBM ContextForge MCP Gateway is affected by server-side request forgery (DNS rebinding) via the A2A agent invocation endpoint\", \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"cweId\": \"CWE-918\", \"description\": \"CWE-918 Server-Side Request Forgery (SSRF)\", \"type\": \"CWE\"}]}], \"affected\": [{\"vendor\": \"IBM\", \"product\": \"ContextForge MCP Gateway\", \"versions\": [{\"status\": \"affected\", \"version\": \"\u003c= v1.0.8\"}], \"cpes\": [\"cpe:2.3:a:ibm:contextforge-mcp-gateway:*:*:*:*:*:*:*:*\"]}], \"descriptions\": [{\"lang\": \"en\", \"value\": \"IBM ContextForge MCP Gateway could allow a remote authenticated attacker to obtain sensitive information due to server-side request forgery via DNS rebinding.\", \"supportingMedia\": [{\"type\": \"text/html\", \"base64\": false, \"value\": \"\u003cp\u003eIBM ContextForge MCP Gateway could allow a remote authenticated attacker to obtain sensitive information due to server-side request forgery via DNS rebinding.\u003c/p\u003e\"}]}], \"references\": [{\"url\": \"https://www.ibm.com/support/pages/node/7286055\", \"tags\": [\"vendor-advisory\", \"patch\"]}], \"metrics\": [{\"format\": \"CVSS\", \"scenarios\": [{\"lang\": \"en\", \"value\": \"GENERAL\"}], \"cvssV3_1\": {\"version\": \"3.1\", \"attackVector\": \"NETWORK\", \"attackComplexity\": \"HIGH\", \"privilegesRequired\": \"LOW\", \"userInteraction\": \"NONE\", \"scope\": \"CHANGED\", \"confidentialityImpact\": \"HIGH\", \"integrityImpact\": \"HIGH\", \"availabilityImpact\": \"NONE\", \"baseSeverity\": \"HIGH\", \"baseScore\": 8.2, \"vectorString\": \"CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:C/C:H/I:H/A:N\"}}], \"workarounds\": [{\"lang\": \"en\", \"value\": \"Operators who cannot immediately upgrade can reduce exposure by:\\n\\n\\n1. **Disable A2A** \\u2014 set the environment variable `MCPGATEWAY_A2A_ENABLED=False` to disable the A2A subsystem entirely. This removes the vulnerable endpoint from the attack surface at the cost of A2A functionality.\\n\\n2. **Restrict A2A create/invoke permissions** \\u2014 revoke A2A creation and invocation rights from developer and team_admin roles in environments where A2A is not required.\\n\\n3. **Network-level egress controls** \\u2014 enforce outbound network policy at the host or cloud level to block the gateway process from reaching cloud metadata endpoints and private RFC 1918 address ranges, preventing exploitation of the DNS-rebinding window even if a rebind attempt succeeds.\\n\\n\\nNone of these mitigations eliminate the underlying vulnerability; IBM strongly recommends upgrading to the fixed version.\", \"supportingMedia\": [{\"type\": \"text/html\", \"base64\": false, \"value\": \"\u003cdiv\u003e\u003cdiv\u003eOperators who cannot immediately upgrade can reduce exposure by:\u003c/div\u003e\u003cbr/\u003e\u003cdiv\u003e1. **Disable A2A** \\u2014 set the environment variable `MCPGATEWAY_A2A_ENABLED=False` to disable the A2A subsystem entirely. This removes the vulnerable endpoint from the attack surface at the cost of A2A functionality.\u003c/div\u003e\u003cdiv\u003e2. **Restrict A2A create/invoke permissions** \\u2014 revoke A2A creation and invocation rights from developer and team_admin roles in environments where A2A is not required.\u003c/div\u003e\u003cdiv\u003e3. **Network-level egress controls** \\u2014 enforce outbound network policy at the host or cloud level to block the gateway process from reaching cloud metadata endpoints and private RFC 1918 address ranges, preventing exploitation of the DNS-rebinding window even if a rebind attempt succeeds.\u003c/div\u003e\u003cbr/\u003e\u003cdiv\u003eNone of these mitigations eliminate the underlying vulnerability; IBM strongly recommends upgrading to the fixed version.\u003c/div\u003e\u003c/div\u003e\"}]}], \"solutions\": [{\"lang\": \"en\", \"value\": \"IBM strongly recommends addressing the vulnerability now.\\n\\nProduct(s)Version(s) number and/or range\\u00a0Remediation/Fix/InstructionsIBM ContextForge MCP Gateway\u003c= v1.0.8Upgrade to v1.0.9\\u00a0\\n https://github.com/IBM/mcp-context-forge/releases/tag/v1.0.9 \\n\\n\\n\\n\\n\\n\\n\\n\\u00a0Note: \u003cComponent A / B names\u003e are bundled with \u003cProduct profile name\u003e to provide \u003cfeature / function description\u003e\", \"supportingMedia\": [{\"type\": \"text/html\", \"base64\": false, \"value\": \"\u003cdiv\u003e\u003c/div\u003e\u003cp\u003e\u003cstrong\u003eIBM strongly recommends addressing the vulnerability now.\u003c/strong\u003e\u003c/p\u003e\u003cdiv\u003e\u003ctable\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd\u003e\u003cstrong\u003eProduct(s)\u003c/strong\u003e\u003c/td\u003e\u003ctd\u003e\u003cstrong\u003eVersion(s) number and/or range\\u00a0\u003c/strong\u003e\u003c/td\u003e\u003ctd\u003e\u003cstrong\u003eRemediation/Fix/Instructions\u003c/strong\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd\u003eIBM ContextForge MCP Gateway\u003c/td\u003e\u003ctd\u003e\u0026lt;= v1.0.8\u003c/td\u003e\u003ctd\u003eUpgrade to v1.0.9\\u00a0\\n\u003cdiv\u003e\u003cdiv\u003e\u003ca href=\\\"https://github.com/IBM/mcp-context-forge/releases/tag/v1.0.9\\\" rel=\\\"nofollow\\\"\u003ehttps://github.com/IBM/mcp-context-forge/releases/tag/v1.0.9\u003c/a\u003e\u003c/div\u003e\u003c/div\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/table\u003e\u003c/div\u003e\u003cp\u003e\\u00a0Note: \u0026lt;Component A / B names\u0026gt; are bundled with \u0026lt;Product profile name\u0026gt; to provide \u0026lt;feature / function description\u0026gt;\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\"}]}]}, \"adp\": [{\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2026-77822\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"none\"}, {\"Automatable\": \"no\"}, {\"Technical Impact\": \"total\"}], \"version\": \"2.0.3\", \"timestamp\": \"2026-09-04T17:09:15.348543Z\"}}}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2026-09-04T17:09:16.341Z\"}}]}",
"cveMetadata": "{\"cveId\": \"CVE-2026-77822\", \"assignerOrgId\": \"9a959283-ebb5-44b6-b705-dcc2bbced522\", \"state\": \"PUBLISHED\", \"assignerShortName\": \"ibm\", \"dateReserved\": \"2026-08-21T14:36:12.469Z\", \"datePublished\": \"2026-09-04T15:15:35.403Z\", \"dateUpdated\": \"2026-09-04T18:24:58.315Z\"}",
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
}
}
Loading…
Loading…
Experimental. This forecast is provided for visualization only and may change without notice. Do not use it for operational decisions.
Forecast uses a logistic model when the trend is rising, or an exponential decay model when the trend is falling. Fitted via linearized least squares.
Sightings
| Author | Source | Type | Date | Other |
|---|
Nomenclature
- Seen: The vulnerability was mentioned, discussed, or observed by the user.
- Confirmed: The vulnerability has been validated from an analyst's perspective.
- Published Proof of Concept: A public proof of concept is available for this vulnerability.
- Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
- Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
- Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
- Not confirmed: The user expressed doubt about the validity of the vulnerability.
- Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.
Loading…
The MITRE ATT&CK techniques below are AI-generated suggestions, inferred from the description of the
vulnerability by the CIRCL/vulnerability-attack-technique-classification-roberta-base
model, served locally by ML-Gateway.
They have not been verified by an analyst and are provided for guidance only.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Loading…
Loading…