Document MCP Server

Convert documents to Markdown using MarkItDown

Local serverstdioPython

What is the Document MCP server?

Convert documents to Markdown using MarkItDown. That is what the document mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The short version

Convert documents to Markdown inside Cursor, VS Code, and any MCP client.

Once connected, your agent converts files locally and returns structured text — nothing is sent to a conversion API.

  • 🏠 Local-first — files stay on your machine; no third-party conversion service
  • 📎 Broad format coverage — PDF, Office, CSV/JSON/text, Outlook .msg, audio, YouTube, and more (via MarkItDown)
  • 🔀 Two workflows — save Markdown next to the source, or preview in chat only
  • 📋 Copy-paste setup — step-by-step install for Cursor, VS Code, and Claude Desktop
  • 📦 Registry published — listed on the official MCP Registry
  • ⚖️ MIT licensed — free for personal and commercial use

The tools it exposes

The server publishes 2 tools. What each one is for:

  • convert_to_markdown — Converts a file or URL to Markdown and saves output (.md beside source, or youtube-{id}.md for YouTube URLs)
  • preview_markdown — Returns Markdown in the chat response only

Getting it running

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.

What it needs from you

Configuration is passed through the environment: REPO_PATH. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

  1. Install uv (includes uvx). Windows (PowerShell): macOS / Linux: 2. Verify uvx works (open a new terminal after installing): 3. Optional — test the server (it will sit idle with no output; that is normal for stdio MCP): Press Ctrl+C to stop. ---

How it compares

Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Document's toolset — convert_to_markdown, preview_markdown — is a fair guide to whether it matches your workflow. It is maintained by Zahid-Abbas-Ali-Baig; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
convert_to_markdownConverts a file or URL to Markdown and saves output (.md beside source, or youtube-{id}.md for YouTube URLs)
preview_markdownReturns Markdown in the chat response only

How to install the Document MCP server

**macOS / Linux:**

```json
{
  "mcpServers": {
    "document-converter": {
      "command": "REPO_PATH/.venv/bin/python",
      "args": ["REPO_PATH/server.py"]
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

  1. Install uv (includes uvx). Windows (PowerShell): macOS / Linux: 2. Verify uvx works (open a new terminal after installing): 3. Optional — test the server (it will sit idle with no output; that is normal for stdio MCP): Press Ctrl+C to stop. ---
VariableDescriptionRequired
REPO_PATHFilesystem location the server is allowed to use.Optional

Example prompts to try

  • Use Document to convert to markdown.
  • Use Document to preview markdown.

Frequently asked questions

It connects Document to MCP-compatible AI assistants such as Claude and Cursor, exposing 2 tools (convert_to_markdown, preview_markdown) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Document directly.