CVE-2026-34163 (GCVE-0-2026-34163)
Vulnerability from cvelistv5 – Published: 2026-03-31 13:43 – Updated: 2026-03-31 15:37
VLAI?
Title
Server-Side Request Forgery via MCP Tools Endpoint in FastGPT
Summary
FastGPT is an AI Agent building platform. Prior to version 4.14.9.5, FastGPT's MCP (Model Context Protocol) tools endpoints (/api/core/app/mcpTools/getTools and /api/core/app/mcpTools/runTool) accept a user-supplied URL parameter and make server-side HTTP requests to it without validating whether the URL points to an internal/private network address. Although the application has a dedicated isInternalAddress() function for SSRF protection (used in other endpoints like the HTTP workflow node), the MCP tools endpoints do not call this function. An authenticated attacker can use these endpoints to scan internal networks, access cloud metadata services, and interact with internal services such as MongoDB and Redis. This issue has been patched in version 4.14.9.5.
Severity ?
7.7 (High)
CWE
- CWE-918 - Server-Side Request Forgery (SSRF)
Assigner
References
| URL | Tags | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
|
||||||||||||||
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-34163",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-03-31T15:37:50.933430Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-03-31T15:37:59.791Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "FastGPT",
"vendor": "labring",
"versions": [
{
"status": "affected",
"version": "\u003c 4.14.9.5"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "FastGPT is an AI Agent building platform. Prior to version 4.14.9.5, FastGPT\u0027s MCP (Model Context Protocol) tools endpoints (/api/core/app/mcpTools/getTools and /api/core/app/mcpTools/runTool) accept a user-supplied URL parameter and make server-side HTTP requests to it without validating whether the URL points to an internal/private network address. Although the application has a dedicated isInternalAddress() function for SSRF protection (used in other endpoints like the HTTP workflow node), the MCP tools endpoints do not call this function. An authenticated attacker can use these endpoints to scan internal networks, access cloud metadata services, and interact with internal services such as MongoDB and Redis. This issue has been patched in version 4.14.9.5."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 7.7,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "NONE",
"privilegesRequired": "LOW",
"scope": "CHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:N",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-918",
"description": "CWE-918: Server-Side Request Forgery (SSRF)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-03-31T13:43:11.068Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/labring/FastGPT/security/advisories/GHSA-x9vj-5m4j-9mfv",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/labring/FastGPT/security/advisories/GHSA-x9vj-5m4j-9mfv"
},
{
"name": "https://github.com/labring/FastGPT/pull/6640",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/labring/FastGPT/pull/6640"
},
{
"name": "https://github.com/labring/FastGPT/commit/bc7eae2ed61481a5e322208829be291faec58c00",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/labring/FastGPT/commit/bc7eae2ed61481a5e322208829be291faec58c00"
},
{
"name": "https://github.com/labring/FastGPT/releases/tag/v4.14.9.5",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/labring/FastGPT/releases/tag/v4.14.9.5"
}
],
"source": {
"advisory": "GHSA-x9vj-5m4j-9mfv",
"discovery": "UNKNOWN"
},
"title": "Server-Side Request Forgery via MCP Tools Endpoint in FastGPT"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-34163",
"datePublished": "2026-03-31T13:43:11.068Z",
"dateReserved": "2026-03-25T20:12:04.197Z",
"dateUpdated": "2026-03-31T15:37:59.791Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2",
"vulnerability-lookup:meta": {
"nvd": "{\"cve\":{\"id\":\"CVE-2026-34163\",\"sourceIdentifier\":\"security-advisories@github.com\",\"published\":\"2026-03-31T15:16:17.170\",\"lastModified\":\"2026-04-01T18:28:47.027\",\"vulnStatus\":\"Analyzed\",\"cveTags\":[],\"descriptions\":[{\"lang\":\"en\",\"value\":\"FastGPT is an AI Agent building platform. Prior to version 4.14.9.5, FastGPT\u0027s MCP (Model Context Protocol) tools endpoints (/api/core/app/mcpTools/getTools and /api/core/app/mcpTools/runTool) accept a user-supplied URL parameter and make server-side HTTP requests to it without validating whether the URL points to an internal/private network address. Although the application has a dedicated isInternalAddress() function for SSRF protection (used in other endpoints like the HTTP workflow node), the MCP tools endpoints do not call this function. An authenticated attacker can use these endpoints to scan internal networks, access cloud metadata services, and interact with internal services such as MongoDB and Redis. This issue has been patched in version 4.14.9.5.\"}],\"metrics\":{\"cvssMetricV31\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Secondary\",\"cvssData\":{\"version\":\"3.1\",\"vectorString\":\"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:N\",\"baseScore\":7.7,\"baseSeverity\":\"HIGH\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"LOW\",\"privilegesRequired\":\"LOW\",\"userInteraction\":\"NONE\",\"scope\":\"CHANGED\",\"confidentialityImpact\":\"HIGH\",\"integrityImpact\":\"NONE\",\"availabilityImpact\":\"NONE\"},\"exploitabilityScore\":3.1,\"impactScore\":4.0},{\"source\":\"nvd@nist.gov\",\"type\":\"Primary\",\"cvssData\":{\"version\":\"3.1\",\"vectorString\":\"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:N\",\"baseScore\":7.7,\"baseSeverity\":\"HIGH\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"LOW\",\"privilegesRequired\":\"LOW\",\"userInteraction\":\"NONE\",\"scope\":\"CHANGED\",\"confidentialityImpact\":\"HIGH\",\"integrityImpact\":\"NONE\",\"availabilityImpact\":\"NONE\"},\"exploitabilityScore\":3.1,\"impactScore\":4.0}]},\"weaknesses\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Primary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-918\"}]}],\"configurations\":[{\"nodes\":[{\"operator\":\"OR\",\"negate\":false,\"cpeMatch\":[{\"vulnerable\":true,\"criteria\":\"cpe:2.3:a:fastgpt:fastgpt:*:*:*:*:*:*:*:*\",\"versionEndExcluding\":\"4.14.9.5\",\"matchCriteriaId\":\"DE20269A-5497-4727-B3DD-3EDC1E1F234E\"}]}]}],\"references\":[{\"url\":\"https://github.com/labring/FastGPT/commit/bc7eae2ed61481a5e322208829be291faec58c00\",\"source\":\"security-advisories@github.com\",\"tags\":[\"Patch\"]},{\"url\":\"https://github.com/labring/FastGPT/pull/6640\",\"source\":\"security-advisories@github.com\",\"tags\":[\"Issue Tracking\",\"Patch\"]},{\"url\":\"https://github.com/labring/FastGPT/releases/tag/v4.14.9.5\",\"source\":\"security-advisories@github.com\",\"tags\":[\"Product\",\"Release Notes\"]},{\"url\":\"https://github.com/labring/FastGPT/security/advisories/GHSA-x9vj-5m4j-9mfv\",\"source\":\"security-advisories@github.com\",\"tags\":[\"Exploit\",\"Mitigation\",\"Vendor Advisory\"]}]}}",
"vulnrichment": {
"containers": "{\"adp\": [{\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2026-34163\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"poc\"}, {\"Automatable\": \"no\"}, {\"Technical Impact\": \"partial\"}], \"version\": \"2.0.3\", \"timestamp\": \"2026-03-31T15:37:50.933430Z\"}}}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2026-03-31T15:37:55.690Z\"}}], \"cna\": {\"title\": \"Server-Side Request Forgery via MCP Tools Endpoint in FastGPT\", \"source\": {\"advisory\": \"GHSA-x9vj-5m4j-9mfv\", \"discovery\": \"UNKNOWN\"}, \"metrics\": [{\"cvssV3_1\": {\"scope\": \"CHANGED\", \"version\": \"3.1\", \"baseScore\": 7.7, \"attackVector\": \"NETWORK\", \"baseSeverity\": \"HIGH\", \"vectorString\": \"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:N\", \"integrityImpact\": \"NONE\", \"userInteraction\": \"NONE\", \"attackComplexity\": \"LOW\", \"availabilityImpact\": \"NONE\", \"privilegesRequired\": \"LOW\", \"confidentialityImpact\": \"HIGH\"}}], \"affected\": [{\"vendor\": \"labring\", \"product\": \"FastGPT\", \"versions\": [{\"status\": \"affected\", \"version\": \"\u003c 4.14.9.5\"}]}], \"references\": [{\"url\": \"https://github.com/labring/FastGPT/security/advisories/GHSA-x9vj-5m4j-9mfv\", \"name\": \"https://github.com/labring/FastGPT/security/advisories/GHSA-x9vj-5m4j-9mfv\", \"tags\": [\"x_refsource_CONFIRM\"]}, {\"url\": \"https://github.com/labring/FastGPT/pull/6640\", \"name\": \"https://github.com/labring/FastGPT/pull/6640\", \"tags\": [\"x_refsource_MISC\"]}, {\"url\": \"https://github.com/labring/FastGPT/commit/bc7eae2ed61481a5e322208829be291faec58c00\", \"name\": \"https://github.com/labring/FastGPT/commit/bc7eae2ed61481a5e322208829be291faec58c00\", \"tags\": [\"x_refsource_MISC\"]}, {\"url\": \"https://github.com/labring/FastGPT/releases/tag/v4.14.9.5\", \"name\": \"https://github.com/labring/FastGPT/releases/tag/v4.14.9.5\", \"tags\": [\"x_refsource_MISC\"]}], \"descriptions\": [{\"lang\": \"en\", \"value\": \"FastGPT is an AI Agent building platform. Prior to version 4.14.9.5, FastGPT\u0027s MCP (Model Context Protocol) tools endpoints (/api/core/app/mcpTools/getTools and /api/core/app/mcpTools/runTool) accept a user-supplied URL parameter and make server-side HTTP requests to it without validating whether the URL points to an internal/private network address. Although the application has a dedicated isInternalAddress() function for SSRF protection (used in other endpoints like the HTTP workflow node), the MCP tools endpoints do not call this function. An authenticated attacker can use these endpoints to scan internal networks, access cloud metadata services, and interact with internal services such as MongoDB and Redis. This issue has been patched in version 4.14.9.5.\"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-918\", \"description\": \"CWE-918: Server-Side Request Forgery (SSRF)\"}]}], \"providerMetadata\": {\"orgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"shortName\": \"GitHub_M\", \"dateUpdated\": \"2026-03-31T13:43:11.068Z\"}}}",
"cveMetadata": "{\"cveId\": \"CVE-2026-34163\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2026-03-31T15:37:59.791Z\", \"dateReserved\": \"2026-03-25T20:12:04.197Z\", \"assignerOrgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"datePublished\": \"2026-03-31T13:43:11.068Z\", \"assignerShortName\": \"GitHub_M\"}",
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
}
}
Loading…
Loading…
Sightings
| Author | Source | Type | Date |
|---|
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…
Loading…