Browse / Tool and Agent Misuse / CVE-2025-5276
Markdownify MCP Server allows Server-Side Request Forgery (SSRF) via the Markdownify.get() function
- Class
- Tool and Agent Misuse (filed by a model that read the advisory)
- Technique
- Server-side request forgery
- Also involves
- MCP and Tool Server Flaws, Indirect Prompt Injection
- Affected
- mcp-markdownify-server (npm)
- CVSS
- CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:N/A:N
- EPSS
- 0.4% chance of exploitation in 30 days
How it works, in short
Attacker-authored prompt content makes the MCP host call the server's conversion tools, which fetch attacker-chosen URLs and return the responses. (Our summary, written by a model. The source text is below.)
Details
All versions of the package mcp-markdownify-server are vulnerable to Server-Side Request Forgery (SSRF) via the Markdownify.get() function. An attacker can craft a prompt that, once accessed by the MCP host, can invoke the webpage-to-markdown, bing-search-to-markdown, and youtube-to-markdown tools to issue requests and read the responses to attacker-controlled URLs, potentially leaking sensitive information.
References
- https://nvd.nist.gov/vuln/detail/CVE-2025-5276
- https://github.com/zcaceres/markdownify-mcp/commit/0284aa8f34d32c65e20d8cda2d429b7943c9af03
- https://github.com/zcaceres/markdownify-mcp
- https://github.com/zcaceres/markdownify-mcp/blob/224cf89f0d58616d2a5522f60f184e8391d1c9e3/src/server.ts#L20C17-L20C29
- https://security.snyk.io/vuln/SNYK-JS-MCPMARKDOWNIFYSERVER-10249387
Source: GitHub Advisory Database, used under CC BY 4.0.