Search

Find a vulnerability

Search criteria

    2 vulnerabilities by mcp-use

    CVE-2026-81091 (GCVE-0-2026-81091)

    Vulnerability from nvd – Published: 2026-08-27 14:50 – Updated: 2026-08-29 11:48
    VLAI
    Title
    mcp-use Inspector Proxy Server-Side Request Forgery via Caller-Supplied Target URL
    Summary
    The proxy middleware in mcp-use's inspector forwards requests to a destination the caller names. mountMcpProxy in libraries/typescript/packages/inspector/src/server/proxy/mcp-proxy.ts read the target from the X-Target-URL header or the __mcp_target parameter and proxied to it without inspecting the host, so loopback, link-local and private addresses were all accepted, as were names that resolve to them, and the validation was not reapplied to a redirect the destination returned. A caller could therefore make the server issue requests to addresses reachable only from the host it runs on and read the responses. The current code calls isSafeProxyTarget, which checks the resolved address against private, loopback and link-local ranges before proxying and bounds the number of redirects followed.
    SSVC
    Exploitation: none Automatable: yes Technical Impact: partial
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-08-27 18:12 UTC
    CWE
    • CWE-918 - Server-Side Request Forgery (SSRF)
    Impacted products
    Vendor Product Version
    mcp-use mcp-use Affected: 0 , ≤ 2.3.2 (semver)
    Create a notification for this product.
    Date Public
    2026-08-26 00:00
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-81091",
                    "options": [
                      {
                        "Exploitation": "none"
                      },
                      {
                        "Automatable": "yes"
                      },
                      {
                        "Technical Impact": "partial"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-08-27T18:12:16.289778Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-08-27T18:12:23.691Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "collectionURL": "https://github.com/mcp-use/mcp-use",
              "defaultStatus": "unaffected",
              "product": "mcp-use",
              "repo": "https://github.com/mcp-use/mcp-use",
              "vendor": "mcp-use",
              "versions": [
                {
                  "lessThanOrEqual": "2.3.2",
                  "status": "affected",
                  "version": "0",
                  "versionType": "semver"
                }
              ]
            }
          ],
          "credits": [
            {
              "lang": "en",
              "type": "finder",
              "value": "Yotam Perkal (Pluto Security)"
            }
          ],
          "datePublic": "2026-08-26T00:00:00.000Z",
          "descriptions": [
            {
              "lang": "en",
              "value": "The proxy middleware in mcp-use\u0027s inspector forwards requests to a destination the caller names. mountMcpProxy in libraries/typescript/packages/inspector/src/server/proxy/mcp-proxy.ts read the target from the X-Target-URL header or the __mcp_target parameter and proxied to it without inspecting the host, so loopback, link-local and private addresses were all accepted, as were names that resolve to them, and the validation was not reapplied to a redirect the destination returned. A caller could therefore make the server issue requests to addresses reachable only from the host it runs on and read the responses. The current code calls isSafeProxyTarget, which checks the resolved address against private, loopback and link-local ranges before proxying and bounds the number of redirects followed."
            }
          ],
          "metrics": [
            {
              "cvssV4_0": {
                "Automatable": "NOT_DEFINED",
                "Recovery": "NOT_DEFINED",
                "Safety": "NOT_DEFINED",
                "attackComplexity": "LOW",
                "attackRequirements": "NONE",
                "attackVector": "NETWORK",
                "baseScore": 8.7,
                "baseSeverity": "HIGH",
                "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:N/VA:N/SC:N/SI:N/SA:N",
                "version": "4.0",
                "vulnAvailabilityImpact": "NONE",
                "vulnConfidentialityImpact": "HIGH",
                "vulnIntegrityImpact": "NONE",
                "vulnerabilityResponseEffort": "NOT_DEFINED"
              },
              "format": "CVSS",
              "scenarios": [
                {
                  "lang": "en",
                  "value": "GENERAL"
                }
              ]
            },
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "NONE",
                "baseScore": 8.6,
                "baseSeverity": "HIGH",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "NONE",
                "privilegesRequired": "NONE",
                "scope": "CHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:N/A:N",
                "version": "3.1"
              },
              "format": "CVSS",
              "scenarios": [
                {
                  "lang": "en",
                  "value": "GENERAL"
                }
              ]
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-918",
                  "description": "Server-Side Request Forgery (SSRF)",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-08-29T11:48:07.418Z",
            "orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
            "shortName": "VulnCheck"
          },
          "references": [
            {
              "tags": [
                "product"
              ],
              "url": "https://github.com/mcp-use/mcp-use"
            },
            {
              "name": "GitHub Security Advisory (GHSA-f2jg-rm2x-hc5p)",
              "tags": [
                "vendor-advisory"
              ],
              "url": "https://github.com/mcp-use/mcp-use/security/advisories/GHSA-f2jg-rm2x-hc5p"
            },
            {
              "name": "VulnCheck Advisory: mcp-use Inspector Proxy Server-Side Request Forgery via Caller-Supplied Target URL",
              "tags": [
                "third-party-advisory"
              ],
              "url": "https://www.vulncheck.com/advisories/mcp-use-inspector-proxy-server-side-request-forgery-via-caller-supplied-target-url"
            }
          ],
          "source": {
            "discovery": "UNKNOWN"
          },
          "title": "mcp-use Inspector Proxy Server-Side Request Forgery via Caller-Supplied Target URL",
          "x_generator": {
            "engine": "vulncheck-endgame"
          }
        }
      },
      "cveMetadata": {
        "assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
        "assignerShortName": "VulnCheck",
        "cveId": "CVE-2026-81091",
        "datePublished": "2026-08-27T14:50:32.568Z",
        "dateReserved": "2026-08-26T16:00:30.592Z",
        "dateUpdated": "2026-08-29T11:48:07.418Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }

    CVE-2026-81091 (GCVE-0-2026-81091)

    Vulnerability from cvelistv5 – Published: 2026-08-27 14:50 – Updated: 2026-08-29 11:48
    VLAI
    Title
    mcp-use Inspector Proxy Server-Side Request Forgery via Caller-Supplied Target URL
    Summary
    The proxy middleware in mcp-use's inspector forwards requests to a destination the caller names. mountMcpProxy in libraries/typescript/packages/inspector/src/server/proxy/mcp-proxy.ts read the target from the X-Target-URL header or the __mcp_target parameter and proxied to it without inspecting the host, so loopback, link-local and private addresses were all accepted, as were names that resolve to them, and the validation was not reapplied to a redirect the destination returned. A caller could therefore make the server issue requests to addresses reachable only from the host it runs on and read the responses. The current code calls isSafeProxyTarget, which checks the resolved address against private, loopback and link-local ranges before proxying and bounds the number of redirects followed.
    SSVC
    Exploitation: none Automatable: yes Technical Impact: partial
    CISA Coordinator · CISA-ADP (v2.0.3)
    Decision recorded 2026-08-27 18:12 UTC
    CWE
    • CWE-918 - Server-Side Request Forgery (SSRF)
    Impacted products
    Vendor Product Version
    mcp-use mcp-use Affected: 0 , ≤ 2.3.2 (semver)
    Create a notification for this product.
    Date Public
    2026-08-26 00:00
    Show details on NVD website

    {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-81091",
                    "options": [
                      {
                        "Exploitation": "none"
                      },
                      {
                        "Automatable": "yes"
                      },
                      {
                        "Technical Impact": "partial"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-08-27T18:12:16.289778Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-08-27T18:12:23.691Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "collectionURL": "https://github.com/mcp-use/mcp-use",
              "defaultStatus": "unaffected",
              "product": "mcp-use",
              "repo": "https://github.com/mcp-use/mcp-use",
              "vendor": "mcp-use",
              "versions": [
                {
                  "lessThanOrEqual": "2.3.2",
                  "status": "affected",
                  "version": "0",
                  "versionType": "semver"
                }
              ]
            }
          ],
          "credits": [
            {
              "lang": "en",
              "type": "finder",
              "value": "Yotam Perkal (Pluto Security)"
            }
          ],
          "datePublic": "2026-08-26T00:00:00.000Z",
          "descriptions": [
            {
              "lang": "en",
              "value": "The proxy middleware in mcp-use\u0027s inspector forwards requests to a destination the caller names. mountMcpProxy in libraries/typescript/packages/inspector/src/server/proxy/mcp-proxy.ts read the target from the X-Target-URL header or the __mcp_target parameter and proxied to it without inspecting the host, so loopback, link-local and private addresses were all accepted, as were names that resolve to them, and the validation was not reapplied to a redirect the destination returned. A caller could therefore make the server issue requests to addresses reachable only from the host it runs on and read the responses. The current code calls isSafeProxyTarget, which checks the resolved address against private, loopback and link-local ranges before proxying and bounds the number of redirects followed."
            }
          ],
          "metrics": [
            {
              "cvssV4_0": {
                "Automatable": "NOT_DEFINED",
                "Recovery": "NOT_DEFINED",
                "Safety": "NOT_DEFINED",
                "attackComplexity": "LOW",
                "attackRequirements": "NONE",
                "attackVector": "NETWORK",
                "baseScore": 8.7,
                "baseSeverity": "HIGH",
                "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:N/VA:N/SC:N/SI:N/SA:N",
                "version": "4.0",
                "vulnAvailabilityImpact": "NONE",
                "vulnConfidentialityImpact": "HIGH",
                "vulnIntegrityImpact": "NONE",
                "vulnerabilityResponseEffort": "NOT_DEFINED"
              },
              "format": "CVSS",
              "scenarios": [
                {
                  "lang": "en",
                  "value": "GENERAL"
                }
              ]
            },
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "NONE",
                "baseScore": 8.6,
                "baseSeverity": "HIGH",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "NONE",
                "privilegesRequired": "NONE",
                "scope": "CHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:N/A:N",
                "version": "3.1"
              },
              "format": "CVSS",
              "scenarios": [
                {
                  "lang": "en",
                  "value": "GENERAL"
                }
              ]
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-918",
                  "description": "Server-Side Request Forgery (SSRF)",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-08-29T11:48:07.418Z",
            "orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
            "shortName": "VulnCheck"
          },
          "references": [
            {
              "tags": [
                "product"
              ],
              "url": "https://github.com/mcp-use/mcp-use"
            },
            {
              "name": "GitHub Security Advisory (GHSA-f2jg-rm2x-hc5p)",
              "tags": [
                "vendor-advisory"
              ],
              "url": "https://github.com/mcp-use/mcp-use/security/advisories/GHSA-f2jg-rm2x-hc5p"
            },
            {
              "name": "VulnCheck Advisory: mcp-use Inspector Proxy Server-Side Request Forgery via Caller-Supplied Target URL",
              "tags": [
                "third-party-advisory"
              ],
              "url": "https://www.vulncheck.com/advisories/mcp-use-inspector-proxy-server-side-request-forgery-via-caller-supplied-target-url"
            }
          ],
          "source": {
            "discovery": "UNKNOWN"
          },
          "title": "mcp-use Inspector Proxy Server-Side Request Forgery via Caller-Supplied Target URL",
          "x_generator": {
            "engine": "vulncheck-endgame"
          }
        }
      },
      "cveMetadata": {
        "assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
        "assignerShortName": "VulnCheck",
        "cveId": "CVE-2026-81091",
        "datePublished": "2026-08-27T14:50:32.568Z",
        "dateReserved": "2026-08-26T16:00:30.592Z",
        "dateUpdated": "2026-08-29T11:48:07.418Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }