DevDocs-MCP: Documentation Authority for AI Agents
以下摘录自该仓库的 README(片段) · 在 GitHub 读完整 README →
> **Eliminate AI hallucinations with local, version-aware, and authoritative documentation.**
DevDocs-MCP is a Model Context Protocol (MCP) server that provides version-pinned, deterministic documentation sourced from DevDocs.io to AI assistants (Claude, RooCode, Cline, Copilot etc.). It acts as a local Documentation Intelligence Layer, ensuring your agent always has the correct API context without network latency or training data drift.
This server follows the proposed MCP server standard defined by the MCP , which is being adopted by AI tools and agents across the ecosystem, including those from providers such as Anthropic, OpenAI, and Google.
---
> ⚠️ **Project Status Notice** ⚠️
> This project is under active and heavy development. Still need to test existing features and implement more new features like optimal caching , update latest doc automatically and also on request basis , optimal querying and more... Design decisions, APIs, and structure are expected to evolve based on strong opinions, reviews, and feedback from the developer community. I warmly welcome discussions, critiques, and contributions to help shape this project in the right direction.
---
📑 Table of Contents
1. Overview
2. Key Capabilities
3. Quickstart
4. Installation & Setup
5. AI Agent Configuration
6. Further Reading
---
🎯 Overview
What This Project Is
- A **local MCP server** written in NestJS (TypeScript).
- A **deterministic authority** for documentation metadata and content.
- A **lazy-ingestion engine** that caches DevDocs offline.
- A **project-aware context manager** that pins docs to your package.json versions.
What This Project Is NOT
- ❌ An AI agent or code generator.
- ❌ A web scraper (it uses structured DevDocs datasets).
- ❌ A DevDocs UI replacement.
- ❌ A hosted SaaS (it runs 100% locally).
Why This Exists (The Problem)
Modern AI coding agents face three major hurdles:
1. **Hallucination**: Guessing API signatures or using deprecated methods.
2. **Latency**: Fetching live web docs for every query is slow.
3. **Version Drift**: Mixing up React 18 with React 19 features.
**The Solution**: DevDocs-MCP provides "Just-in-Time" documentation retrieved from local storage, filtered by your project's specific dependency versions.
Mental Model
DevDocs-MCP acts as a middleware between your IDE Agent and the documentation source.
---
🚀 Key Capabilities
- **Offline-First**: Documentation is cached locally; no internet is needed after ingestion.
- **Ranked Fuzzy Search**: Instantly find relevant entries (e.g., "intersection observer").
- **Version Awareness**: Automatically maps to specific library versions in your project.
- **Node-Only Architecture**: Uses sql.js for zero-native dependencies (no Python/C++ build steps).
- **Structured Outputs**: Returns clean, LLM-optimized content.
---
⚡ Quickstart
1. **Clone & Install**
2. **Configure Environment**
3. **Build & Run**
> **Note:** Strictly use pnpm for development and contributions.
---
🛠️ Installation & Setup
DevDocs-MCP is optimized for zero-fuss setup with pnpm. It is a **Node-only** project.
Prerequisites
- Node.js 18+ (tested on 18.x and 20.x).
🐳 Docker Usage
DevDocs-MCP is designed to be lightweight and persistent. Since it downloads and caches large documentation datasets, managing your data volumes correctly is essential.