GitHub Style Markdown Preview MCP App
Enables the previewing of GitHub Flavored Markdown (GFM) as an MCP application. It provides a tool to render and visualize Markdown content using authentic GitHub styling and CSS.
README
GitHub Style Markdown Preview MCP App
GitHub Flavored Markdown (GFM) preview as an MCP App.
Docs: https://modelcontextprotocol.io/docs/extensions/apps
Usage
npm run build # Build UI and server
npm run serve # Start server on http://localhost:3001/mcp
npm run dev # Build & serve with watch mode
Connect to Claude
-
Start the tunnel:
npx cloudflared tunnel --url http://localhost:3001 -
Copy the generated URL (e.g.,
https://random-name.trycloudflare.com) -
In Claude web, go to Settings > Connectors > Add custom connector
-
Enter the URL with
/mcppath:https://<your-url>.trycloudflare.com/mcp
Packages
Dependencies
| Package | Description |
|---|---|
@modelcontextprotocol/ext-apps |
MCP Apps SDK (server + client) |
@modelcontextprotocol/sdk |
MCP SDK core |
react, react-dom |
React UI framework |
react-markdown |
Markdown renderer for React |
remark-gfm |
GitHub Flavored Markdown plugin |
github-markdown-css |
GitHub style CSS |
express, cors |
HTTP server |
zod |
Schema validation |
Dev Dependencies
| Package | Description |
|---|---|
vite |
Build tool |
vite-plugin-singlefile |
Bundle into single HTML |
@vitejs/plugin-react |
Vite React plugin |
esbuild |
Server bundler |
concurrently |
Run multiple commands |
cross-env |
Cross-platform env vars |
tsx |
TypeScript execution |
typescript |
TypeScript compiler |
Files
| File | Description |
|---|---|
main.ts |
Entry point (HTTP/stdio transport) |
server.ts |
MCP server with preview-markdown tool |
mcp-app.html |
UI entry point |
src/mcp-app.tsx |
React app using useApp hook |
src/markdown.tsx |
Markdown component with GFM support |
src/global.css |
GitHub markdown styling |
vite.config.ts |
Vite bundler config |
tsconfig.json |
TypeScript config |
tsconfig.server.json |
Server build config |
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.