MarkItDown MCP Details

MarkItDown-MCP is a lightweight MCP (Model Context Protocol) server provided as the markitdown-mcp package. It exposes a STDIO, Streamable HTTP, and SSE MCP server designed for calling MarkItDown to convert content to Markdown. The package focuses on simplicity and accessibility, enabling you to run the MCP server locally via a simple CLI, or in Docker for containerized workflows, with integration options for Claude Desktop. The core capability is exposed through a single tool, convert_to_markdown(uri), which accepts a URI in http:, https:, file:, or data: schemes to fetch content and convert it to Markdown. This MCP server is easy to install with pip and can be used in various transport modes, including STDIO and HTTP/SSE, making it a flexible choice for automations and integrations.

Use Case

Use MarkItDown-MCP to convert documents and web resources to Markdown via a lightweight MCP server. Run the server in STDIO for local pipelines, or expose it over HTTP/SSE to be called by clients in different environments (e.g., Claude Desktop, other MCP clients). The main functionality is the convert_to_markdown(uri) tool, which accepts a URI and returns Markdown content. Example usage from the docs includes running the server in STDIO with markitdown-mcp, or in HTTP mode with markitdown-mcp --http --host 127.0.0.1 --port 3001. Debugging can be performed with the mcpinspector tool (npx @modelcontextprotocol/inspector) to List Tools and invoke convert_to_markdown on a valid URI. The documentation also provides Claude Desktop configuration JSON blocks for running the MCP in Docker and mounting local data directories.

Available Tools (2)

Examples & Tutorials

Code examples directly from the docs:

  • Install via pip:

  • pip install markitdown-mcp

  • Run MCP server in STDIO (default):

  • markitdown-mcp

  • Run MCP server with HTTP/Streamable/SSE:

  • markitdown-mcp --http --host 127.0.0.1 --port 3001

  • Docker: build and run the image:

  • docker build -t markitdown-mcp:latest .

    docker run -it --rm markitdown-mcp:latest

  • Access local files in Docker by mounting a host directory:

  • docker run -it --rm -v /home/user/data:/workdir markitdown-mcp:latest

  • Claude Desktop integration (JSON example 1):

  • {
    "mcpServers": {
    "markitdown": {
    "command": "docker",
    "args": [\\
    "run",\\
    "--rm",\\
    "-i",\\
    "markitdown-mcp:latest"\\
    ]
    }
    }
    }

  • Claude Desktop integration (JSON example 2 with data mount):

  • {
    "mcpServers": {
    "markitdown": {
    "command": "docker",
    "args": [\\
    "run",\\
    "--rm",\\
    "-i",\\
    "-v",\\
    "/home/user/data:/workdir",\\
    "markitdown-mcp:latest"\\
    ]
    }
    }
    }

  • Debugging with mcpinspector:

  • npx @modelcontextprotocol/inspector

    Then connect and use the Tools tab to List Tools and run:
    convert_to_markdown

  • Debug transport examples (from the inspector flow):

  • STDIO transport example:

  • Select STDIO as the transport type,
    input the command: markitdown-mcp

  • Streamable HTTP example:

  • Select Streamable HTTP as the transport type,
    input the URL: http://127.0.0.1:3001/mcp

  • SSE example:

  • Select SSE as the transport type,
    input the URL: http://127.0.0.1:3001/sse

    Installation Guide

    Step-by-step installation and setup from the docs:

    1) Install via pip:

    pip install markitdown-mcp

    2) Run the MCP server in STDIO (default):

    markitdown-mcp

    3) Run the MCP server with HTTP/Streamable/SSE:

    markitdown-mcp --http --host 127.0.0.1 --port 3001

    4) Running in Docker:

    docker build -t markitdown-mcp:latest .

    docker run -it --rm markitdown-mcp:latest

    5) For local data access inside Docker, mount a host directory:

    docker run -it --rm -v /home/user/data:/workdir markitdown-mcp:latest
    `

    Integration Guides

    Frequently Asked Questions

    Is this your MCP?

    Claim ownership and get verified badge

    Repository Stats
    Important Notes

    Security considerations: The server does not support authentication and runs with the privileges of the user running it. When using SSE or Streamable HTTP, it is recommended to bind the server to localhost for security.

    Prerequisites

    pip (Python package installer) is required. Install the MCP package with: pip install markitdown-mcp.

    Details
    Last Updated1/2/2026
    Websitegithub.com
    SourceGitHub

    Compare Alternatives

    Similar MCP Tools

    6 related tools
    Anki MCP Server

    Anki MCP Server

    A Model Context Protocol (MCP) server that enables AI assistants to interact with Anki, the spaced repetition flashcard application. The Anki MCP Server allows AI models to access Anki's card data, enabling features like automated flashcard creation, review, and management.

    1MCP Agent

    1MCP Agent

    A unified Model Context Protocol server implementation that aggregates multiple MCP servers into one. The 1mcp-app/agent is an open-source project that provides a single entry point for multiple MCP servers, making it easier to manage and interact with various AI models and tools.

    Roundtable AI MCP Server

    Roundtable AI MCP Server

    Roundtable AI MCP Server is a zero-configuration local MCP server that unifies multiple AI coding assistants (Codex, Claude Code, Cursor, Gemini) through intelligent auto-discovery and a standardized interface. It coordinates specialized sub-agents from within your IDE to solve engineering problems in parallel, sharing context and synthesizing responses into a single, high-quality output. This documentation details installation, available MCP tools, integration with popular IDEs, and a broad ecosystem of specialized tools and CLIs that can be invoked as part of a roundtable-powered workflow, enabling developers to delegate tasks to the right AI for each facet of a problem without leaving their development environment.

    MCPJungle

    MCPJungle

    MCPJungle is a self-hosted MCP Gateway and Registry for AI agents. It serves as a central registry and gateway to manage Model Context Protocol (MCP) servers and the tools they expose. By consolidating MCP server registration, tool discovery, and access control, MCPJungle enables AI agents and clients to discover, group, and securely invoke tools from a single, unified gateway. The project provides a CLI, Docker-based deployment options, and enterprise-ready features such as tool grouping, access control, and observability to streamline MCP-based workflows across organizations.

    mcpmcp-server

    mcpmcp-server

    mcpmcp-server is a focused solution for discovering, setting up, and integrating MCP servers with your favorite clients to unlock AI-powered workflows. It streamlines how you connect MCP-powered servers to popular clients, enabling seamless AI-assisted interactions across your daily tools. The project emphasizes an approachable, config-driven approach to linking MCP servers with clients like Claude Desktop, while directing you to the homepage for variations across apps and platforms. This README highlights a practical JSON configuration example and notes on supported environments, helping you get started quickly and confidently.

    Imagen3-MCP

    Imagen3-MCP

    Imagen3-MCP is an image generation service based on Google's Imagen 3.0 that exposes its functionality through MCP (Model Control Protocol). The project provides a server to run a local MCP service that accesses Google Gemini-powered image generation, enabling developers to integrate advanced image synthesis into their applications. The documentation covers prerequisites (Gemini API key), installation steps for Cherry Studio, and a Cursor-based JSON configuration example for embedding the MCP server in broader tooling. This MCP is designed to be deployment-friendly, with configurable environment variables and optional proxy settings to adapt to various network environments.