DevDocs

v1.0.0Developer Toolsstable

Provides AI models with direct access to documentation for over 600 technologies from DevDocs.io, including popular languages, frameworks, and tools. It enables comprehensive searching, content retrieval, and offline access via an intelligent local c

clinecrawl4aicursordocumentationllm
Share:
2,076
Stars
0
Downloads
0
Weekly
0/5

What is DevDocs?

DevDocs is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to provides ai models with direct access to documentation for over 600 technologies from devdocs.io, including popular languages, frameworks, and tools. it enables comprehensive searching, content retrie...

Provides AI models with direct access to documentation for over 600 technologies from DevDocs.io, including popular languages, frameworks, and tools. It enables comprehensive searching, content retrieval, and offline access via an intelligent local c

This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Provides AI models with direct access to documentation for o

Use Cases

Access documentation for 600+ technologies offline
Comprehensive search across frameworks and tools
cyberagiinc

Maintainer

LicenseApache 2.0
Languagetypescript
Versionv1.0.0
UpdatedMay 21, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx devdocs-mcp-server

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use DevDocs

DevDocs MCP Server gives AI assistants direct, searchable access to offline documentation for over 600 technologies — including languages, frameworks, databases, and developer tools — sourced from DevDocs.io. It runs a local Docker stack with a frontend UI, backend API, and Crawl4AI scraping service that builds and caches documentation locally so queries are fast and work without an internet connection. Developers integrate it with Claude, Cline, Cursor, or Roo Code so the AI can look up precise API references and framework guides rather than relying on potentially outdated training data.

Prerequisites

  • Docker and Docker Compose installed on your system
  • Git to clone the repository
  • At least 4 GB of free disk space for documentation caches
  • A compatible MCP client: Claude Desktop, Cline, Cursor, or Roo Code
  • Optional: Playwright dependencies if running outside Docker
1

Clone the repository

Clone the DevDocs repository from GitHub to get the Docker configuration and startup scripts.

git clone https://github.com/cyberagiinc/DevDocs.git
cd DevDocs
2

Start the Docker stack

Run the provided startup script for your platform. It creates required directories, sets permissions, builds the Docker images, and starts all three services: the frontend UI, backend API, and Crawl4AI scraping service.

# macOS / Linux
./docker-start.sh

# Windows
docker-start.bat
3

Verify services are running

Confirm all three services started successfully by checking their ports. The frontend at port 3001 lets you browse and manage cached documentation.

# Frontend UI
curl http://localhost:3001

# Backend API
curl http://localhost:24125

# Crawl4AI service
curl http://localhost:11235
4

Add documentation sets via the UI

Open http://localhost:3001 in your browser and select the technologies whose documentation you want to index. The backend will crawl and cache the relevant DevDocs.io pages locally using the Crawl4AI service.

5

Configure your MCP client

Register the DevDocs MCP server in your client's config file. The MCP server runs as part of the Docker stack and is accessible over the backend API port.

{
  "mcpServers": {
    "devdocs": {
      "type": "http",
      "url": "http://localhost:24125/mcp"
    }
  }
}

DevDocs Examples

Client configuration

HTTP MCP client configuration connecting to the local DevDocs backend API. Make sure the Docker stack is running before connecting.

{
  "mcpServers": {
    "devdocs": {
      "type": "http",
      "url": "http://localhost:24125/mcp"
    }
  }
}

Prompts to try

Once connected, ask the AI to look up precise documentation rather than relying on memory. The recommended workflow is to request the table of contents first, then targeted section retrieval.

- "Look up the DevDocs table of contents for React and list available sections."
- "Retrieve the React useEffect hook documentation and explain its dependency array."
- "Find the PostgreSQL documentation section on window functions and show the syntax."
- "Search the Python 3.12 docs for the asyncio.TaskGroup API."
- "Get the Rust std::collections::HashMap documentation and show common methods."

Troubleshooting DevDocs

docker-start.sh fails with permission denied errors

Make the script executable with 'chmod +x docker-start.sh' before running it. If directories cannot be created, check that you have write permission to the DevDocs working directory.

Documentation crawling is very slow or times out

The Crawl4AI service at port 11235 handles scraping and can be slow on first run for large documentation sets. Ensure Docker has at least 2 GB of memory allocated. Check Crawl4AI logs with 'docker compose logs crawl4ai' to identify bottlenecks.

MCP client cannot reach the DevDocs server

Verify all three containers are running with 'docker compose ps'. The MCP interface is served by the backend container on port 24125. If running Docker Desktop on macOS or Windows, confirm port forwarding is active and no firewall rules are blocking localhost connections.

Frequently Asked Questions about DevDocs

What is DevDocs?

DevDocs is a Model Context Protocol (MCP) server that provides ai models with direct access to documentation for over 600 technologies from devdocs.io, including popular languages, frameworks, and tools. it enables comprehensive searching, content retrieval, and offline access via an intelligent local c It connects AI assistants to external tools and data sources through a standardized interface.

How do I install DevDocs?

Follow the installation instructions on the DevDocs GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with DevDocs?

DevDocs works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is DevDocs free to use?

Yes, DevDocs is open source and available under the Apache 2.0 license. You can use it freely in both personal and commercial projects.

Browse More Developer Tools MCP Servers

Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "devdocs-mcp-server": { "command": "npx", "args": ["-y", "devdocs-mcp-server"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use DevDocs?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides