Markdownify MCP Server for Cursor: Setup & Config

What you can do with Markdownify in Cursor

Unify mixed documents and web material as Markdown, with explicit directory read boundaries.

• Transcribe audio as part of a document conversion workflow.
• Read existing Markdown within an explicitly allowed directory set.

Before you start: Markdownify in Cursor

• Bun
• A cloned repository with dependencies installed and the project built
• Python for the MarkItDown environment created during installation

Run bun install and bun run build first. The local installation uses markitdown[all]. Set allowed paths to restrict file reads; the slim published Docker image lacks audio and image extras.

Markdownify Cursor configuration

1. Choose Cursor configuration scope

   For Markdownify MCP Server, open Project: .cursor/mcp.json User: ~/.cursor/mcp.json. Merge into mcpServers at project or user scope.

2. Add Markdownify MCP Server to Cursor

   Use the markdownify-mcp entry below in mcpServers. Keep Markdownify MCP Server's documented stdio connection fields and your other Cursor entries.

3. Check Markdownify MCP Server in Cursor

   Markdownify MCP Server: Enable in Cursor’s MCP settings; inspect tools.

{
  "mcpServers": {
    "markdownify-mcp": {
      "command": "bun",
      "args": [
        "start"
      ],
      "env": {
        "MD_ALLOWED_PATHS": "<allowed directories separated by your platform path delimiter>"
      }
    }
  }
}

Markdownify tools available to Cursor

Markdownify's stored tool list documents 11 tools; compare it with Cursor's connected tool list, because the stored list is not a live check.

youtube-to-markdown

Find youtube-to-markdown under Markdownify in Cursor's MCP settings; inspect its arguments when the agent requests a call.

Extract a YouTube video's transcript into Markdown.

pdf-to-markdown

Find pdf-to-markdown under Markdownify in Cursor's MCP settings; inspect its arguments when the agent requests a call.

bing-search-to-markdown

Find bing-search-to-markdown under Markdownify in Cursor's MCP settings; inspect its arguments when the agent requests a call.

webpage-to-markdown

Find webpage-to-markdown under Markdownify in Cursor's MCP settings; inspect its arguments when the agent requests a call.

image-to-markdown

Find image-to-markdown under Markdownify in Cursor's MCP settings; inspect its arguments when the agent requests a call.

audio-to-markdown

Find audio-to-markdown under Markdownify in Cursor's MCP settings; inspect its arguments when the agent requests a call.

docx-to-markdown

Find docx-to-markdown under Markdownify in Cursor's MCP settings; inspect its arguments when the agent requests a call.

Transform a DOCX document into Markdown.

xlsx-to-markdown

Find xlsx-to-markdown under Markdownify in Cursor's MCP settings; inspect its arguments when the agent requests a call.

Represent spreadsheet content from XLSX as Markdown.

pptx-to-markdown

Find pptx-to-markdown under Markdownify in Cursor's MCP settings; inspect its arguments when the agent requests a call.

Transform presentation content from PPTX into Markdown.

get-markdown-file

Find get-markdown-file under Markdownify in Cursor's MCP settings; inspect its arguments when the agent requests a call.

Read an existing file with a .md or .markdown extension.

git-repo-to-markdown

Find git-repo-to-markdown under Markdownify in Cursor's MCP settings; inspect its arguments when the agent requests a call.

Convert repository content using the configured Repomix executable.

Markdownify: full stored tool descriptions

Troubleshooting Markdownify in Cursor

• Cursor must find bun for Markdownify MCP Server. Enable the project/user entry in MCP settings and inspect its tools.
• Review MD_ALLOWED_PATHS for Markdownify MCP Server before sharing project .cursor/mcp.json; project scope travels with the repository.
• Markdownify MCP Server uses stdio here: Cursor must keep the configured process running; protocol output belongs on stdout and diagnostics on stderr.
• Known limitation: File access is unrestricted unless allowed directories are configured.
• Known limitation: The published slim Docker image lacks audio transcription and image OCR extras.
• Known limitation: The full local installation involves JavaScript tooling and a Python conversion environment.
• General Cursor troubleshooting lives in the /clients/cursor guide.

Frequently asked questions