dodopayments/contextmcp

**Self-hosted MCP server for your documentation.** Index your documentation from across the sources and serve it via the Model Context Protocol (MCP) and REST API.
Quick Start
What is ContextMCP?
ContextMCP creates a searchable knowledge base from your documentation that AI assistants can query via the Model Context Protocol (MCP).
Supported Content Types
| Parser | Content Types | Examples |
| ---------- | --------------------- | ------------------------------ |
| mdx | MDX/JSX documentation | Mintlify, Fumadocs, Docusaurus |
| markdown | Plain Markdown files | READMEs, CHANGELOGs |
| openapi | OpenAPI/Swagger specs | API reference docs |
How It Works
1. **Parse** - Extract content from your docs, APIs, and READMEs
2. **Chunk** - Split into semantic chunks optimized for search
3. **Embed** - Generate embeddings using OpenAI or Gemini
4. **Store** - Upload to Pinecone vector database
5. **Search** - Query via MCP from AI assistants
Ecosystem
Add a chat UI with ContextChat
ContextMCP serves retrieval; pair it with **ContextChat** to give your docs a drop-in, embeddable "Ask AI" widget. ContextChat is a single Cloudflare Worker that queries your ContextMCP /search endpoint and streams answers with inline citations — add it to any site or docs page with one tag.
Repository Structure
Packages
| Package | Description | Published |
| ------------------- | -------------------- | -------------------- |
| packages/cli | CLI scaffolding tool | ✅ npm: contextmcp |
| packages/template | Project template | (copied by CLI) |
| packages/website | Documentation site | (deployed to Vercel) |
Development
Prerequisites
- Node.js 18+
Setup
Documentation
Visit contextmcp.ai/docs for full documentation.
Contributing
We welcome contributions! Please see CONTRIBUTING.md for guidelines on how to contribute to this project.