What does the MarkItDown MCP server expose as its tool?

It exposes one tool: convert_to_markdown(uri), where uri can be any `http:`, `https:`, `file:`, or `data:` URI.

How can I run MarkItDown MCP in STDIO?

Run the server with: `markitdown-mcp` (STDIO mode is the default).

How can I run MarkItDown MCP with HTTP/Streamable/SSE support?

Run the server with: `markitdown-mcp --http --host 127.0.0.1 --port 3001`.

How do I debug the MCP server and inspect available tools?

Use the mcpinspector tool: `npx @modelcontextprotocol/inspector`. Then connect to the server and use the Tools tab to List Tools and run `convert_to_markdown` on a valid URI.

How do I run MarkItDown-MCP using Docker?

Build: `docker build -t markitdown-mcp:latest .` Run: `docker run -it --rm markitdown-mcp:latest` To access local files, mount a directory: `docker run -it --rm -v /home/user/data:/workdir markitdown-mcp:latest`

Back to Directory

MarkItDown MCP

Featured

MCP Markdown MarkItDown STDIO HTTP SSE Claude Desktop Docker CLI

View Source Visit Website

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

Compare Alternatives

ChainAware Behavioural Prediction MCP

Sequential Thinking MCP Server

Compare →

Similar MCP Tools

9 related tools

Graphiti MCP Server

Graphiti MCP Server is an experimental implementation that exposes Graphiti's real-time, temporally-aware knowledge graph capabilities through the MCP (Model Context Protocol) interface. It enables AI agents and MCP clients to interact with Graphiti's knowledge graph for structured extraction, reasoning, and memory across conversations, documents, and enterprise data. The server supports multiple backends (FalkorDB by default and Neo4j), a variety of LLM providers (OpenAI, Anthropic, Gemini, Groq, Azure OpenAI), and multiple embedder options, all accessible via an HTTP MCP endpoint at /mcp/ for broad client compatibility. It also includes queue-based asynchronous episode processing, rich entity types for structured data, and flexible configuration through config.yaml, environment variables, or CLI arguments.

Context7 MCP Server

Context7 MCP Server delivers up-to-date, code-first documentation and examples for LLMs and AI code editors by pulling content directly from the source. It supports multiple MCP clients and exposes tools that help you resolve library IDs and retrieve library documentation, ensuring prompts use current APIs and usage patterns. The repository provides installation and integration guides for Cursor, Claude Code, Opencode, and other clients, along with practical configuration samples and OAuth options for remote HTTP connections. This MCP server is designed to keep prompts in sync with the latest library docs, reducing hallucinations and outdated code snippets.

TrendRadar MCP

TrendRadar MCP is an AI-driven Model Context Protocol (MCP) based analysis server that exposes a suite of specialized tools for cross-platform news analysis, trend tracking, and intelligent push notifications. It integrates with TrendRadar’s multi-platform data aggregation (RSS and trending topics) and provides advanced AI-powered insights, sentiment analysis, and cross-platform correlation. The MCP server enables developers to query, analyze, and compare news across platforms using a consistent toolset, with ongoing updates that expand capabilities such as RSS querying, date parsing, and multi-date trend analysis. This documentation references the MCP module updates, tool additions, and architecture changes that enhance extensibility, cross-platform data handling, and AI-assisted reporting.

ChainAware Behavioural Prediction MCP

The ChainAware Behavioural Prediction MCP is an MCP-based server that provides AI-powered tools to analyze wallet behaviour prediction, fraud detection, and rug pull prediction. Designed for Web3 security and DeFi analytics, it enables developers and platforms to integrate risk assessment, predictive wallet behavior insights, and rug-pull detection through MCP-compatible clients. The server exposes three specialized tools and uses Server-Sent Events (SSE) for real-time responses, helping safeguard DeFi users, monitor liquidity risks, and score wallet or contract trustworthiness. Access to production endpoints is API-key gated, reflecting a private backend architecture that supports secure, scalable risk analytics across wallets, contracts, and pools.

Playwright MCP

Playwright MCP server. A Model Context Protocol (MCP) server that provides browser automation capabilities using Playwright. This server enables large language models (LLMs) to interact with web pages through structured accessibility snapshots, bypassing the need for screenshots or visually-tuned models. The server is designed to be fast, lightweight, and deterministic, offering LLM-friendly tooling and a rich set of browser automation capabilities via MCP tools. It supports standalone operation, containerized deployments, and integration with a variety of MCP clients (Claude Desktop, VS Code, Copilot, Cursor, Goose, Windsurf, and others).

Sequential Thinking MCP Server

Sequential Thinking MCP Server provides a dedicated MCP tool that guides problem-solving through a structured, step-by-step thinking process. It supports dynamic adjustment of the number of thoughts and allows revision and branching within a controlled workflow, making it ideal for complex analysis and solution hypothesis development. This server is designed to register a single tool, sequential_thinking, and is integrated with common MCP deployment methods (NPX, Docker) as well as editor integrations like Claude Desktop and VS Code for quick setup. The documentation provides exact configuration snippets, usage patterns, and building instructions to help you deploy and use the MCP server effectively, including Codex CLI, NPX, and Docker installation examples.

N8N MCP Server

An MCP (Model Context Protocol) server designed to integrate Claude Desktop, Claude Code, Windsurf, and Cursor with n8n workflows. This MCP enables users to build, test, and orchestrate complex workflows by exposing a set of tools that bridge Claude’s capabilities with n8n’s automation platform. The project emphasizes robust trigger handling, multi-tenant readiness, and progressive documentation to help developers understand how tools map to real-world workflow tasks. It also outlines future tooling integration points (such as getNodeEssentials and getNodeInfo) to further enhance node-structure awareness within MCP-powered automations.

Hugging Face MCP Server

Hugging Face Official MCP Server connects your large language models (LLMs) to the Hugging Face Hub and thousands of Gradio AI Applications, enabling seamless MCP (Model Context Protocol) integration across multiple transports. It supports STDIO, SSE (to be deprecated but still commonly deployed), StreamableHTTP, and StreamableHTTPJson, with the Web Application allowing dynamic tool management and status updates. This MCP server is designed to be run locally or in Docker, and it provides integrations with Claude Desktop, Claude Code, Gemini CLI (and its extension), VSCode, and Cursor, making it easy to configure and manage MCP-enabled tools and endpoints. Tools such as hf_doc_search and hf_doc_fetch can be enabled to enhance document discovery, and an optional Authenticate tool can be included to handle OAuth challenges when called.

Shadcn UI MCP Server v4

Shadcn UI v4 MCP Server is an advanced MCP (Model Context Protocol) server designed to give AI assistants comprehensive access to shadcn/ui v4 components, blocks, demos, and metadata. It enables multi-framework support (React, Svelte, Vue, and React Native) with fast, cache-friendly access to component source code, demos, and directory structures, empowering AI-driven development workflows. The project emphasizes production-readiness with Docker Compose, SSE transport for multi-client deployments, and smart caching to optimize GitHub API usage while providing rich metadata and usage patterns for rapid prototyping and learning across frameworks.