DevDocs MCP server

This MCP server provides a comprehensive implementation of the Model Context Protocol for documentation management and integration, allowing efficient resource handling through URI-based access with type safety and parameter validation.

Installation

To install the DevDocs MCP Implementation, follow these steps:

1. Clone the repository:

   git clone https://github.com/your-username/devdocs-mcp.git
   cd devdocs-mcp
   

2. Install the required dependencies:

   pip install -r requirements.txt
   

3. Verify the installation by running the tests:

   pytest tests/property/test_templates.py
   

Core Components

Resource Template System

The resource template system is the foundation of the MCP implementation, providing URI-based access to documentation resources.

Key features:

• Type-safe parameter handling through Pydantic
• Flexible URI template matching
• Comprehensive error handling
• State management for resource lifecycle

Using Resource Templates

You can create and use resource templates as follows:

from src.resources.templates.base import ResourceTemplate

# Create a template with parameter typing
template = ResourceTemplate(
    uri_template='docs://api/{version}/endpoint',
    parameter_types={'version': str}
)

# Extract and validate parameters from a URI
params = template.extract_parameters('docs://api/v1/endpoint')
template.validate_parameters(params)

Working with Documentation Resources

Accessing Resources

To access documentation resources using the MCP implementation:

1. Create appropriate resource templates
2. Extract and validate parameters from URIs
3. Use the templates to access the desired resources

Example:

# Create a template for API documentation
api_docs_template = ResourceTemplate(
    uri_template='docs://api/{version}/{endpoint}',
    parameter_types={'version': str, 'endpoint': str}
)

# Access a specific API endpoint documentation
params = api_docs_template.extract_parameters('docs://api/v2/authentication')
if api_docs_template.validate_parameters(params):
    # Use params to fetch the documentation
    documentation = fetch_documentation(params['version'], params['endpoint'])

Error Handling

The MCP implementation provides structured error handling for various situations:

• Invalid URI formats
• Missing required parameters
• Type mismatches in parameters
• Resource not found scenarios

Example of error handling:

try:
    params = template.extract_parameters('docs://api/invalid-endpoint')
    template.validate_parameters(params)
except ValueError as e:
    print(f"Parameter validation error: {e}")
except ResourceNotFoundError as e:
    print(f"Resource not found: {e}")

Testing Your Implementation

The MCP implementation comes with a robust testing framework:

# Run all tests
pytest

# Run specific test categories
pytest tests/property/
pytest tests/integration/

Available Features

The current implementation includes:

• Resource template system with parameter validation
• URI validation and parameter extraction
• Error handling foundation

Features in development that will be available soon:

• Documentation processor integration
• Caching layer
• Task management system
• Search functionality

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "devdocs" '{"command":"npx","args":["-y","devdocs-mcp"]}'

See the official Claude Code MCP documentation for more details.

For 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 > Tools & Integrations and click "New MCP Server".

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

{
    "mcpServers": {
        "devdocs": {
            "command": "npx",
            "args": [
                "-y",
                "devdocs-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 explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

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

3. Restart Claude Desktop for the changes to take effect