Skip to content
Fencer Intel
high 8.5

CVE-2026-59973 json

mcp-from-openapi: Bypass of OpenAPI external $ref SSRF fix in latest FrontMCP and mcp-from-openapi

published 2mo ago modified last mo. also EUVD-2026-78782 , GHSA-65h7-9wrw-629c

cvss
8.5
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.4%
EPSS 0.4% chance of exploitation in 30 days, percentile 33%
public exploits
0
none known

Summary

FrontMCP is a TypeScript-first framework for the Model Context Protocol (MCP). From mcp-from-openapi 2.3.0 until 2.5.0 and from frontmcp and @frontmcp/adapters 1.2.1 until 1.5.0, libs/adapters/src/openapi/openapi.adapter.ts loadOpenAPISpec() forwards untrusted OpenAPI url and spec inputs and loadOptions.refResolution to OpenAPIToolGenerator.fromURL() and OpenAPIToolGenerator.fromJSON(). The external $ref guard checks parsed hostname strings without resolving addresses, pinning validated addresses, revalidating redirect targets, or normalizing IPv4-mapped IPv6. An authenticated user who can import or configure an OpenAPI specification in a hosted or multi-user deployment can use DNS-to-loopback resolution, redirect-to-loopback behavior, or IPv4-mapped IPv6 loopback forms to cause backend-origin requests to internal services. This can expose internal administrative APIs, metadata-like services, and other private network endpoints. The practical impact is lower when only a trusted local administrator can configure OpenAPI specs, and disabling external reference protocols prevents the external $ref request. This issue is fixed in mcp-from-openapi 2.5.0 and frontmcp and @frontmcp/adapters 1.5.0.

Patch / fix

  • npm mcp-from-openapi 2.5.0
  • npm @frontmcp/adapters 1.5.0
  • npm frontmcp 1.5.0
  • agentfront @frontmcp/adapters 1.5.0
  • agentfront @frontmcp/sdk 1.5.0
  • agentfront frontmcp 1.5.0
  • frontmcp mcp-from-openapi 1.5.0

Is CVE-2026-59973 in your dependencies? Fencer shows which of your repositories are affected as soon as an advisory lands, and opens the fix as a pull request.

Check with Fencer

CISA SSVC

Exploitation
Proof of concept is public
Automatable
no
Technical impact
partial
Assessed
last mo.

Exploit prediction

0.39% chance of exploitation in the next 30 days, higher than 33% of all scored CVEs (FIRST EPSS, 2026-11-11).

Exploits and checks

  • github.com https://github.com/agentfront/frontmcp/security/advisories/GHSA-65h7-9wrw-629c referenced PoC, tagged "exploit" by a source, unverified

CVSS scores

assigned by version score vector
CNA 3.1 8.5 CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:L/A:N
GitHub 3.1 8.5 CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:L/A:N

Affected packages

ecosystem package affected fixed in
npm mcp-from-openapi
>=2.3.0, <2.5.0
2.5.0
npm @frontmcp/adapters
>=1.2.1, <1.5.0
1.5.0
npm frontmcp
>=1.2.1, <1.5.0
1.5.0

Affected products

  • agentfront frontmcp
  • agentfront mcp-from-openapi
  • @frontmcp adapters

Classification

Weakness
  • CWE-918 Server-Side Request Forgery

References

Sources

Fencer Intel keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.

CPEs and fixed versions use Anchore's correction of NVD's data: Added CPE configurations because not yet analyzed by NVD.