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

Prop Firm Deal Finder

Compare →

MarkItDown MCP

mcp-server-with-spring-ai

Similar MCP Tools

9 related tools

Skyvern MCP

Skyvern is the complete browser MCP for AI agents. 75+ tools for clicking, filling forms, extracting structured data, logging in with 2FA, uploading files, drag-and-drop, running JavaScript, inspecting network traffic, multi-tab browsing, and building reusable cached workflows. First workflow run uses AI; subsequent runs replay a cached script with zero LLM calls.

pageguard-mcp

pageguard-mcp is an MCP (Model Context Protocol) server that exposes PageGuard privacy compliance scanning as a set of tools for AI coding assistants. It enables seamless integration with Claude Code, Cursor, Windsurf, ChatGPT, and any MCP-compatible environment. The server supports local scans, live URL scans, and AI-generated privacy-related documents, helping developers identify tracking technologies, cookies, and third-party data processing, while also producing tailored privacy policies and compliance materials. With its straightforward MCP configuration and free local scanning capability, pageguard-mcp is designed to empower teams to maintain privacy compliance across their projects and websites.

Prop Firm Deal Finder

Prop Firm Deal Finder (PFDF) is a free MCP server that gives AI assistants real-time access to live discount codes across 20+ proprietary trading firms. It provides 6 tools: get_deals (all current discounts), search_firms (search by name/asset class), compare_firms (side-by-side comparison of challenges), find_cheapest (cheapest challenge by account size with PFDF code applied), get_firm_details (15+ data points per firm), and get_discount_code (universal PFDF code). Covers firms like Topstep, Apex Trader Funding, MyFundedFutures, FTMO, The Funded Trader, and 14 more. No API key required. Install via npx propfirmdealfinder-mcp-server or connect remotely at https://web-production-6607c.up.railway.app/mcp

mcp-server-with-spring-ai

mcp-server-with-spring-ai is a Spring Boot integrated MCP (Model Context Protocol) server example that showcases how to expose executable tools from an MCP server to clients (including LLMs) and how to wire a MCP client to consume those tools. The documentation explains MCP at a high level, outlines the three-layer MCP Java SDK architecture (Client/Server Layer, Session Layer, Transport Layer), and demonstrates two sample tools implemented in SellerAccountTools. This repo emphasizes how an MCP server can connect to external data sources (e.g., a PostgreSQL DB) and expose tools that an AI model can invoke to retrieve data, with the example illustrating tool invocation and automatic tool selection by prompts.

OpenClaw MCP Server

OpenClaw MCP Server is a secure Model Context Protocol (MCP) bridge that connects Claude.ai with a self-hosted OpenClaw assistant, enabling OAuth2 authentication and safe, controlled communication between the Claude AI ecosystem and your local or hosted OpenClaw deployment. This MCP server acts as an orchestration layer that exposes MCP tools to Claude.ai, manages authentication, and enforces security boundaries like CORS and transport options. It is designed to be deployed via Docker or run locally, with detailed installation, configuration, and security guidance provided in the documentation. By serving as a bridge, it enables Claude.ai to delegate tasks to your OpenClaw bot while preserving control over data flow and access controls, in line with MCP specifications and best security practices.

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.