CVE-2026-59973
mcp-from-openapi: Bypass of OpenAPI external $ref SSRF fix in latest FrontMCP and mcp-from-openapi
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.
Attack profile
How easy it is to exploit
- Attack vector
- Network
- Complexity
- Low
- Privileges needed
- Low
- User interaction
- None
What an attacker can affect
- Confidentiality
- High
- Integrity
- Low
- Availability
- None
Exploit likelihood
What each source reports
CVE List Score used
8.5
mcp-from-openapi: Bypass of OpenAPI external $ref SSRF fix in latest FrontMCP and mcp-from-openapi
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.
- Record
CVE-2026-59973- CVSS 3.1
- 8.5 High
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:L/A:N - Weakness
- CWE-918
- Updated
- 2026-11-02
EUVDEUVD-2026-78782
8.5
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.
- Record
EUVD-2026-78782- CVSS 3.1
- 8.5 High
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:L/A:N - Updated
- 2026-11-02
GitHub AdvisoriesGHSA-65h7-9wrw-629c
8.5
FrontMCP and mcp-from-openapi have bypass of OpenAPI external $ref SSRF fix
Summary
The published fix for GHSA-v6ph-xcq9-qxxj / CVE-2026-39885 added a direct hostname denylist for OpenAPI external $ref dereferencing, but the latest patched dependency mcp-from-openapi 2.3.0 still makes backend-origin requests to loopback when the target is reached through hostname resolution, redirects, or IPv4-mapped IPv6 syntax.
FrontMCP latest release v1.2.1 and current main still call OpenAPIToolGenerator.fromURL() and OpenAPIToolGenerator.fromJSON() from mcp-from-openapi 2.3.0 when loading OpenAPI adapters. An attacker who can cause a hosted or multi-user FrontMCP deployment to load an untrusted OpenAPI spec can trigger requests from the server to localhost or private services during tool generation.
This is a latest-version bypass of the previous fix. A direct http://127.0.0.1 $ref control is now denied and produces zero canary hits, while semantically equivalent loopback targets still reach the canary.
Latest versions checked
frontmcpnpm latest: 1.2.1@frontmcp/adaptersnpm latest: 1.2.1mcp-from-openapinpm latest: 2.3.0- FrontMCP release tag: v1.2.1, commit db323976c66297d684a3e63bbfe1db6b310f2944
- FrontMCP current main checked: c15b79abe8c6a3cb71d4b7a3bafb8190730dc756
The release tag and current main both keep mcp-from-openapi 2.3.0 in package.json and libs/adapters/package.json, and both keep the OpenAPI adapter forwarding untrusted url, spec, and loadOptions.refResolution into OpenAPIToolGenerator.
Technical details
FrontMCP's OpenAPI adapter reaches the affected dependency paths:
libs/adapters/src/openapi/openapi.adapter.tsimportsOpenAPIToolGeneratorfrommcp-from-openapi.loadOpenAPISpec()callsOpenAPIToolGenerator.fromURL(this.options.url, ...)and forwardsloadOptions.refResolution.- The same method calls
OpenAPIToolGenerator.fromJSON(this.options.spec, ...)and forwardsloadOptions.refResolution.
In mcp-from-openapi 2.3.0, the patched guard is applied before the HTTP resolver fetches an external $ref. It checks the parsed URL hostname string against deny patterns for direct local and private addresses. The resolver does not resolve hostnames before allow or deny decisions, does not pin the validated IP to the fetch, and does not revalidate redirect targets before following them. It also misses IPv4-mapped IPv6 loopback forms.
As a result, these URLs are accepted by the guard but cause a loopback request from the backend:
http://127.0.0.1.nip.io:<port>/schema.json, because the hostname string is not a direct IP even though it resolves to 127.0.0.1.http://127.0.0.1.nip.io:<port>/redirect, because the first host passes and the actual request follows a redirect tohttp://127.0.0.1:<port>/schema.json.http://[::ffff:127.0.0.1]:<port>/schema.jsonandhttp://[::ffff:7f00:1]:<port>/schema.json, because IPv4-mapped IPv6 loopback is not normalized and denied.
OpenAPIToolGenerator.fromURL() is also still unguarded for the initial OpenAPI spec URL. The PoC includes that as supporting evidence, but the primary report is the external $ref fix bypass.
Reproduction
The attached local PoC starts a loopback canary and loads generated OpenAPI specs using mcp-from-openapi 2.3.0. The request body schema contains a single external $ref for each test case. The canary records every backend-origin request.
Run:
cd /home/unkn0wn/security_audit/frontmcp-ssrf-poc
node repro-frontmcp-latest-ssrf-bypasses.mjs
Important output from a fresh run on 2026-05-25:
{"name":"direct-127-denied-control","kind":"external_ref","refUrl":"http://127.0.0.1:45117/schema.json","ok":false,"hitCount":0,"hits":[]}
{"name":"dns-name-to-127-bypass","kind":"external_ref","refUrl":"http://127.0.0.1.nip.io:45117/schema.json","ok":true,"hitCount":1,"hits":[{"url":"/schema.json","host":"127.0.0.1.nip.io:45117","authorization":null}]}…
- Record
GHSA-65h7-9wrw-629c- CVSS 3.1
- 8.5 High
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:L/A:N - Weakness
- CWE-918
- Updated
- 2026-11-02
NVD
8.5
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.
- Record
CVE-2026-59973- CVSS 3.1
- 8.5 High
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:L/A:N - Weakness
- CWE-918
- Updated
- 2026-11-02
OSV
8.5
mcp-from-openapi: Bypass of OpenAPI external $ref SSRF fix in latest FrontMCP and mcp-from-openapi
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.
- Record
CVE-2026-59973- CVSS 3.1
- 8.5 High
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:L/A:N - Weakness
- CWE-918
- Updated
- 2026-11-02
OSVGHSA-65h7-9wrw-629c
8.5
FrontMCP and mcp-from-openapi have bypass of OpenAPI external $ref SSRF fix
Summary
The published fix for GHSA-v6ph-xcq9-qxxj / CVE-2026-39885 added a direct hostname denylist for OpenAPI external $ref dereferencing, but the latest patched dependency mcp-from-openapi 2.3.0 still makes backend-origin requests to loopback when the target is reached through hostname resolution, redirects, or IPv4-mapped IPv6 syntax.
FrontMCP latest release v1.2.1 and current main still call OpenAPIToolGenerator.fromURL() and OpenAPIToolGenerator.fromJSON() from mcp-from-openapi 2.3.0 when loading OpenAPI adapters. An attacker who can cause a hosted or multi-user FrontMCP deployment to load an untrusted OpenAPI spec can trigger requests from the server to localhost or private services during tool generation.
This is a latest-version bypass of the previous fix. A direct http://127.0.0.1 $ref control is now denied and produces zero canary hits, while semantically equivalent loopback targets still reach the canary.
Latest versions checked
frontmcpnpm latest: 1.2.1@frontmcp/adaptersnpm latest: 1.2.1mcp-from-openapinpm latest: 2.3.0- FrontMCP release tag: v1.2.1, commit db323976c66297d684a3e63bbfe1db6b310f2944
- FrontMCP current main checked: c15b79abe8c6a3cb71d4b7a3bafb8190730dc756
The release tag and current main both keep mcp-from-openapi 2.3.0 in package.json and libs/adapters/package.json, and both keep the OpenAPI adapter forwarding untrusted url, spec, and loadOptions.refResolution into OpenAPIToolGenerator.
Technical details
FrontMCP's OpenAPI adapter reaches the affected dependency paths:
libs/adapters/src/openapi/openapi.adapter.tsimportsOpenAPIToolGeneratorfrommcp-from-openapi.loadOpenAPISpec()callsOpenAPIToolGenerator.fromURL(this.options.url, ...)and forwardsloadOptions.refResolution.- The same method calls
OpenAPIToolGenerator.fromJSON(this.options.spec, ...)and forwardsloadOptions.refResolution.
In mcp-from-openapi 2.3.0, the patched guard is applied before the HTTP resolver fetches an external $ref. It checks the parsed URL hostname string against deny patterns for direct local and private addresses. The resolver does not resolve hostnames before allow or deny decisions, does not pin the validated IP to the fetch, and does not revalidate redirect targets before following them. It also misses IPv4-mapped IPv6 loopback forms.
As a result, these URLs are accepted by the guard but cause a loopback request from the backend:
http://127.0.0.1.nip.io:<port>/schema.json, because the hostname string is not a direct IP even though it resolves to 127.0.0.1.http://127.0.0.1.nip.io:<port>/redirect, because the first host passes and the actual request follows a redirect tohttp://127.0.0.1:<port>/schema.json.http://[::ffff:127.0.0.1]:<port>/schema.jsonandhttp://[::ffff:7f00:1]:<port>/schema.json, because IPv4-mapped IPv6 loopback is not normalized and denied.
OpenAPIToolGenerator.fromURL() is also still unguarded for the initial OpenAPI spec URL. The PoC includes that as supporting evidence, but the primary report is the external $ref fix bypass.
Reproduction
The attached local PoC starts a loopback canary and loads generated OpenAPI specs using mcp-from-openapi 2.3.0. The request body schema contains a single external $ref for each test case. The canary records every backend-origin request.
Run:
cd /home/unkn0wn/security_audit/frontmcp-ssrf-poc
node repro-frontmcp-latest-ssrf-bypasses.mjs
Important output from a fresh run on 2026-05-25:
{"name":"direct-127-denied-control","kind":"external_ref","refUrl":"http://127.0.0.1:45117/schema.json","ok":false,"hitCount":0,"hits":[]}
{"name":"dns-name-to-127-bypass","kind":"external_ref","refUrl":"http://127.0.0.1.nip.io:45117/schema.json","ok":true,"hitCount":1,"hits":[{"url":"/schema.json","host":"127.0.0.1.nip.io:45117","authorization":null}]}…
- Record
GHSA-65h7-9wrw-629c- CVSS 3.1
- 8.5 High
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:L/A:N - Weakness
- CWE-918
- Updated
- 2026-11-02
Affected products
Affected packages
| Package | Affected | Fixed |
|---|---|---|
mcp-from-openapinpm |
2.3.0 up to 2.5.0 | 2.5.0 |
@frontmcp/adaptersnpm |
1.2.1 up to 1.5.0 | 1.5.0 |
frontmcpnpm |
1.2.1 up to 1.5.0 | 1.5.0 |
History
| Recorded | Changed | Sources |
|---|---|---|
| first indexed | CVE List, EUVD, GitHub Advisories, NVD, OSV |
Dates are when Every CVE recorded each change. Upstream dates may differ.
In short
CVE-2026-59973 is a high vulnerability (CVSS 8.5) in @frontmcp Adapters, published September 11, 2026. No source lists public exploit code. EPSS puts the chance of exploitation in the next 30 days at 0.39%, the 33rd percentile. Fixed in mcp-from-openapi 2.5.0.
References
github.com/agentfront/frontmcp/security/advisories/GHSA-65h7-9wrw-629c
github.com/agentfront/frontmcp/pull/496
github.com/agentfront/mcp-from-openapi/pull/7
github.com/agentfront/frontmcp/commit/96a78eaa5c6c4bc51cced557d83d1a03344cb03d
github.com/agentfront/mcp-from-openapi/commit/be3409cce6e97642696d4ee5a4e4e2712490b277
github.com/agentfront/frontmcp/releases/tag/v1.5.0
Left out here: the rest of 2 source descriptions. The JSON record has them.