Documentation Scraper MCP server

The Docs MCP Server is an AI-powered documentation manager that solves the problem of outdated information and hallucinations in AI coding assistants. It indexes third-party documentation from websites, GitHub, npm, PyPI, and local files, making the latest official documentation available to your AI through the Model Context Protocol (MCP).

Installation Options

Using Docker Desktop (Recommended)

1. Install Docker and Docker Compose

2. Clone the repository

   git clone https://github.com/arabold/docs-mcp-server.git
   cd docs-mcp-server
   

3. Set up environment

   cp .env.example .env
   # Edit .env and add your OpenAI API key
   

4. Start the services

   docker compose up -d
   

5. Configure your MCP client Add this configuration to your MCP settings:

   {
     "mcpServers": {
       "docs-mcp-server": {
         "url": "http://localhost:6280/sse",
         "disabled": false,
         "autoApprove": []
       }
     }
   }
   

6. Access the web interface Open http://localhost:6281 in your browser

Using Docker Directly

1. Install and start Docker

2. Configure your MCP client Add this to your MCP settings:

   {
     "mcpServers": {
       "docs-mcp-server": {
         "command": "docker",
         "args": [
           "run",
           "-i",
           "--rm",
           "-e",
           "OPENAI_API_KEY",
           "-v",
           "docs-mcp-data:/data",
           "ghcr.io/arabold/docs-mcp-server:latest"
         ],
         "env": {
           "OPENAI_API_KEY": "sk-proj-..." // Your OpenAI API key
         },
         "disabled": false,
         "autoApprove": []
       }
     }
   }
   

Using npx

Run the server without installation:

OPENAI_API_KEY="sk-proj-..." npx @arabold/docs-mcp-server@latest

Adding Documentation Sources

Through the Web Interface

1. Open the web interface at http://localhost:6281
2. Use the "Queue New Scrape Job" form
3. Enter:
   • Documentation URL
   • Library name
   • Version (optional)
4. Click "Queue Job" and monitor progress

Indexing Local Files

You can index documentation from your local filesystem using file:// URLs:

• Local file: file:///Users/me/docs/index.html
• Local folder: file:///Users/me/docs/my-library

When using Docker, you must mount your local folders:

docker run --rm \
  -e OPENAI_API_KEY="your-key" \
  -v /absolute/path/to/docs:/docs:ro \
  -v docs-mcp-data:/data \
  ghcr.io/arabold/docs-mcp-server:latest \
  scrape mylib file:///docs/my-library

Using the CLI

With Docker

docker run --rm \
  -e OPENAI_API_KEY="your-openai-api-key" \
  -v docs-mcp-data:/data \
  ghcr.io/arabold/docs-mcp-server:latest \
  <command> [options]

Example to list indexed libraries:

docker run --rm \
  -e OPENAI_API_KEY="your-openai-api-key" \
  -v docs-mcp-data:/data \
  ghcr.io/arabold/docs-mcp-server:latest \
  list

With npx

npx @arabold/docs-mcp-server@latest <command> [options]

Example:

npx @arabold/docs-mcp-server@latest list

Configuration Options

Configure the server using these environment variables:

Embedding Model Options

• text-embedding-3-small (default, OpenAI)
• openai:llama2 (OpenAI-compatible, Ollama)
• vertex:text-embedding-004 (Google Vertex AI)
• gemini:embedding-001 (Google Gemini)
• aws:amazon.titan-embed-text-v1 (AWS Bedrock)
• microsoft:text-embedding-ada-002 (Azure OpenAI)

Example Docker Configurations

OpenAI Embeddings (Default)

docker run -i --rm \
  -e OPENAI_API_KEY="your-key" \
  -e DOCS_MCP_EMBEDDING_MODEL="text-embedding-3-small" \
  -v docs-mcp-data:/data \
  ghcr.io/arabold/docs-mcp-server:latest

Google Vertex AI

docker run -i --rm \
  -e DOCS_MCP_EMBEDDING_MODEL="vertex:text-embedding-004" \
  -e GOOGLE_APPLICATION_CREDENTIALS="/app/gcp-key.json" \
  -v docs-mcp-data:/data \
  -v /path/to/gcp-key.json:/app/gcp-key.json:ro \
  ghcr.io/arabold/docs-mcp-server:latest

AWS Bedrock

docker run -i --rm \
  -e AWS_ACCESS_KEY_ID="your-aws-key" \
  -e AWS_SECRET_ACCESS_KEY="your-aws-secret" \
  -e AWS_REGION="us-east-1" \
  -e DOCS_MCP_EMBEDDING_MODEL="aws:amazon.titan-embed-text-v1" \
  -v docs-mcp-data:/data \
  ghcr.io/arabold/docs-mcp-server:latest

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.