MDX MCP Server
Enables LLMs to read, search, convert, and extract metadata from MDX files, providing seamless interaction with MDX content through tools that convert MDX to clean Markdown format with built-in security and cross-platform compatibility.
README
<div align="center"> <h1>MDX MCP Server</h1> <p>Universal MCP server for intelligent MDX file processing and analysis</p> </div>
<div align="center"> <img src="https://img.shields.io/badge/Node.js-20%2B-green?style=for-the-badge&logo=node.js&logoColor=white"> <img src="https://img.shields.io/badge/License-MIT-blue?style=for-the-badge"> <img src="https://img.shields.io/badge/Platforms-Win%20%7C%20macOS%20%7C%20Linux-blue?style=for-the-badge"> <a href="https://github.com/LLMTooling/mdx-mcp-server/actions/workflows/test.yml"> <img src="https://img.shields.io/github/actions/workflow/status/LLMTooling/mdx-mcp-server/test.yml?style=for-the-badge&label=Tests"> </a> </div>
<div align="center"> <h2>Overview</h2> </div>
<div align="center">
MDX MCP Server is a powerful Model Context Protocol server that enables LLMs to seamlessly interact with, search, and process MDX files. It provides robust tools for reading MDX content as clean Markdown, performing contextual searches, converting files, and extracting metadata, all with built-in cross-platform compatibility and security.
</div>
<div align="center"> <h2>Core Features</h2> </div>
<div align="center"> <table> <tr> <th>Feature</th> <th>Description</th> </tr> <tr> <td>MDX Reading</td> <td>Convert MDX to clean Markdown format on the fly</td> </tr> <tr> <td>Contextual Search</td> <td>Find content within MDX files with surrounding context</td> </tr> <tr> <td>Format Conversion</td> <td>Convert and save MDX files to standard Markdown</td> </tr> <tr> <td>Metadata Extraction</td> <td>Parse and retrieve YAML frontmatter</td> </tr> <tr> <td>Cross-Platform</td> <td>Native support for Windows, Linux, and macOS</td> </tr> <tr> <td>Path Safety</td> <td>Secure path resolution preventing directory traversal</td> </tr> </table> </div>
<div align="center"> <h2>MCP Tools</h2> </div>
<div align="center">
The server exposes the following tools through the Model Context Protocol interface.
</div>
<div align="center"> <table> <tr> <th>Tool</th> <th>Description</th> <th>Key Parameters</th> </tr> <tr> <td><code>read_mdx</code></td> <td>Read an MDX file and return its contents as Markdown</td> <td>path</td> </tr> <tr> <td><code>search_mdx</code></td> <td>Search for content within an MDX file</td> <td>path, query, contextLines</td> </tr> <tr> <td><code>convert_mdx_to_md</code></td> <td>Convert an MDX file to a Markdown file on disk</td> <td>sourcePath, outputPath</td> </tr> <tr> <td><code>get_mdx_frontmatter</code></td> <td>Extract YAML frontmatter from an MDX file</td> <td>path</td> </tr> </table> </div>
<div align="center"> <h2>Tool Usage Examples</h2> </div>
<div align="center">
See how the tools can be leveraged to interact with MDX files.
</div>
// Read an MDX file
{
"name": "read_mdx",
"arguments": {
"path": "docs/introduction.mdx"
}
}
// Search with context
{
"name": "search_mdx",
"arguments": {
"path": "docs/guide.mdx",
"query": "installation",
"contextLines": 2
}
}
// Convert MDX to Markdown
{
"name": "convert_mdx_to_md",
"arguments": {
"sourcePath": "docs/guide.mdx",
"outputPath": "output/guide.md"
}
}
// Extract metadata
{
"name": "get_mdx_frontmatter",
"arguments": {
"path": "docs/article.mdx"
}
}
<div align="center"> <h2>Installation</h2> </div>
<div align="center">
Prerequisites
</div>
Ensure you have Node.js installed:
# Node.js >= 20.19.0 is required
node --version
<div align="center">
Install the MCP Server
</div>
npm install
npm run build
<div align="center"> <h2>Configuration</h2> </div>
Add to your MCP settings file (e.g., claude_desktop_config.json):
{
"mcpServers": {
"mdx": {
"command": "node",
"args": ["/absolute/path/to/mdx-mcp-server/dist/index.js"],
"env": {
"WORKSPACE_ROOT": "/path/to/your/workspace"
}
}
}
}
<div align="center"> <h2>Development</h2> </div>
# Clone the repository
git clone https://github.com/LLMTooling/mdx-mcp-server.git
cd mdx-mcp-server
# Install dependencies
npm install
# Build the project
npm run build
# Run tests
npm test
# Run tests in watch mode
npm run test:watch
<div align="center"> <h2>Architecture</h2> </div>
<div align="center">
The server follows a modular architecture ensuring clean separation of concerns.
</div>
<div align="center"> <table> <tr> <th>Component</th> <th>Responsibility</th> </tr> <tr> <td>Server Entry</td> <td>Main MCP server setup and configuration (<code>src/index.ts</code>)</td> </tr> <tr> <td>Tools Module</td> <td>Implementation of individual MCP tools (<code>src/tools/</code>)</td> </tr> <tr> <td>Path Resolver</td> <td>Cross-platform path handling and security (<code>src/utils/path-resolver.ts</code>)</td> </tr> <tr> <td>MDX Processor</td> <td>Core MDX processing logic (<code>src/utils/mdx-processor.ts</code>)</td> </tr> </table> </div>
<div align="center"> <h2>Contributing</h2> </div>
<div align="center">
Contributions are welcome! Please feel free to submit issues or pull requests.
</div>
<div align="center"> <h2>License</h2> </div>
<div align="center">
MIT License
</div>
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
E2B
Using MCP to run code via e2b.