mcp-md-converter
Converts Markdown files to PDF or Google Docs via headless Chromium and Google Drive import.
README
mcp-md-converter
MCP server exposing two tools so an AI coding agent (Claude Code, etc.) can turn a Markdown file it just wrote into a PDF or a Google Doc.
md_to_pdf— renders Markdown → HTML → PDF locally via headless Chromium (puppeteer). No network, no Google account needed.md_to_gdoc— uploads Markdown (as HTML) to Google Drive, which auto-converts it into a native, formatted Google Doc (headings, lists, tables, code blocks).
1. Install
cd mcp-md-converter
npm install
npm run build
2. Google auth (only needed for md_to_gdoc)
- In Google Cloud Console, create/select a project.
- Enable the Google Drive API.
- Create OAuth client credentials → Application type Desktop app.
- Download the JSON and save it as:
~/.mcp-md-converter/credentials.json - Run the one-time login:
This opens a browser, you approve access, and anpm run authtoken.jsonis cached in~/.mcp-md-converter/. Refresh tokens auto-renew after that — no repeat login.
Scope used: drive.file (the app can only see/create files it makes — not your whole Drive).
3. Register with Claude Code
claude mcp add md-converter -- node /Users/bheshrajneupane/Agent/mcp-md-converter/dist/main.js
Or add directly to your MCP config (.mcp.json / Claude Code settings):
{
"mcpServers": {
"md-converter": {
"command": "node",
"args": ["/Users/bheshrajneupane/Agent/mcp-md-converter/dist/main.js"]
}
}
}
4. Usage
Once registered, ask the agent things like:
- "Convert README.md to a PDF at ~/Desktop/readme.pdf"
- "Turn this markdown into a Google Doc titled 'Design Spec'"
Tool params:
| Tool | Params |
|---|---|
md_to_pdf |
markdown_path | markdown, out_path (required), title |
md_to_gdoc |
markdown_path | markdown, title, folder_id (optional Drive folder) |
Troubleshooting
- PDF render fails to launch Chromium (sandboxed/restricted shells, some CI):
point puppeteer at a system Chrome install instead of its bundled one:
Set this env var wherever the MCP server process launches (shell profile, or in theexport PUPPETEER_EXECUTABLE_PATH="/Applications/Google Chrome.app/Contents/MacOS/Google Chrome"mcpServersconfig'senvblock).
Notes
- PDF rendering downloads a Chromium build via puppeteer on
npm install(~150MB, one-time). - Google Doc conversion relies on Drive's HTML→Docs import, so formatting fidelity matches what you'd get pasting HTML into Drive's "New > File upload" — solid for headings, lists, tables, bold/italic, code blocks; very exotic Markdown extensions may not map 1:1.
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.
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.
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.
E2B
Using MCP to run code via e2b.
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.