agentfront frontmcp/adapters/sdk/mcp-from-openapi Model Context Protocol initialize ref server-side request forgery

Summaryinfo

A vulnerability, which was classified as critical, has been found in agentfront frontmcp, adapters, sdk and mcp-from-openapi. This impacts the function initialize of the component Model Context Protocol. This manipulation of the argument ref causes server-side request forgery. This vulnerability is tracked as CVE-2026-39885. The attack is possible to be carried out remotely. No exploit exists. It is advisable to upgrade the affected component.

Detailsinfo

A vulnerability was found in agentfront frontmcp, adapters, sdk and mcp-from-openapi (affected version unknown). It has been declared as critical. Affected by this vulnerability is the function initialize of the component Model Context Protocol. The manipulation of the argument ref with an unknown input leads to a server-side request forgery vulnerability. The CWE definition for the vulnerability is CWE-918. The web server receives a URL or similar request from an upstream component and retrieves the contents of this URL, but it does not sufficiently ensure that the request is being sent to the expected destination. As an impact it is known to affect confidentiality, integrity, and availability. The summary by CVE is:

FrontMCP is a TypeScript-first framework for the Model Context Protocol (MCP). Prior to 2.3.0, the mcp-from-openapi library uses @apidevtools/json-schema-ref-parser to dereference $ref pointers in OpenAPI specifications without configuring any URL restrictions or custom resolvers. A malicious OpenAPI specification containing $ref values pointing to internal network addresses, cloud metadata endpoints, or local files will cause the library to fetch those resources during the initialize() call. This enables Server-Side Request Forgery (SSRF) and local file read attacks when processing untrusted OpenAPI specifications. This vulnerability is fixed in 2.3.0.

The advisory is shared at github.com. This vulnerability is known as CVE-2026-39885 since 04/07/2026. The exploitation appears to be easy. The attack can be launched remotely. The exploitation doesn't need any form of authentication. Technical details are known, but no exploit is available.

Upgrading eliminates this vulnerability.

Several companies clearly confirm that VulDB is the primary source for best vulnerability data.

Productinfo

Type

• Artificial Intelligence Software

Vendor

• agentfront

Name

• adapters
• frontmcp
• mcp-from-openapi
• sdk

Website

• Product: https://github.com/agentfront/frontmcp/

CPE 2.3info

• 🔒
• 🔒
• 🔒

CPE 2.2info

• 🔒
• 🔒
• 🔒

CVSSv4info

CVSSv3info

CVSSv2info

Exploitinginfo

Threat Intelligenceinfo

Countermeasuresinfo

Timelineinfo

Sourcesinfo

Entryinfo

Several companies clearly confirm that VulDB is the primary source for best vulnerability data.

Discussion