MCP Boilerplate

MIT License
1
2

Integrations

  • Allows loading environment variables from a .env file for server configuration, including port, API key, and host settings.

  • Provides development mode with automatic server restarting for a smoother development experience.

  • Enables production deployment with process management capabilities for improved stability and monitoring.

MCP boilerplate: Model Context Protocol Server

This server implements the Model Context Protocol (MCP) for global use as a boilerplate. It provides a standardized way to connect AI models to different data sources and tools using the Model Context Protocol.

Features

  • Implements the MCP Server-Sent Events (SSE) transport
  • Provides a robust structure for building custom MCP servers
  • Includes example tools with proper type definitions
  • Secure authentication with API key
  • Logging capabilities with different severity levels
  • Session management for multiple client connections
  • Graceful shutdown handling for SIGINT and SIGTERM signals

Tools

The server currently includes the following example tool:

  • calculator: Performs basic arithmetic operations (add, subtract, multiply, divide)

For information on how to add your own custom tools, check out the Extending the Boilerplate section.

Configuration

The server configuration is centralized in src/config.ts. This makes it easy to adjust settings without modifying multiple files.

// Essential configuration options export const config = { server: { name: "mcp-boilerplate", version: "1.0.0", port: parseInt(process.env.PORT || "4005"), host: process.env.HOST || "localhost", apiKey: process.env.API_KEY || "dev_key", }, sse: { // How often to send keepalive messages (in milliseconds) keepaliveInterval: 30000, // Whether to send ping events in addition to comments usePingEvents: true, // Initial connection message sendConnectedEvent: true, }, tools: { // Number of retries for failed tool executions maxRetries: 3, // Delay between retries (in milliseconds) retryDelay: 1000, // Whether to send notifications about tool execution status sendNotifications: true, }, logging: { // Default log level defaultLevel: "debug", // How often to send log messages (in milliseconds) logMessageInterval: 10000, }, };

Troubleshooting SSE Timeouts

If you're experiencing "Body timeout error" with your MCP connection:

  1. Decrease keepaliveInterval to send more frequent keepalive messages (e.g., 15000ms)
  2. Ensure usePingEvents is enabled for additional connection stability
  3. Check for any proxy timeouts if you're using a proxy server

Setup

  1. Install dependencies:
npm install
  1. Create a .env file with the following variables:
PORT=4005 API_KEY=your_api_key
  1. Build the project:
npm run build
  1. Start the server:
npm run start:sse

Development

# Start in development mode with hot reloading npm run start # Start with PM2 for production npm run start:pm2 # Development mode with nodemon npm run dev

API Endpoints

  • /health: Health check endpoint that returns server status and version
  • /sse: SSE endpoint for establishing MCP connections (requires API key)
  • /messages: Message handling endpoint for client-server communication

MCP Configuration

To connect an MCP to this server, add the following configuration:

{ "mcpServers": { "mcp-server": { "url": "http://localhost:4005/sse?API_KEY={{your_api_key_here}}" } } }

Extending the boilerplate

Adding Custom Tools

Follow these steps to add a new tool to the MCP server:

  1. Create your tool handler:
    • Add your new tool handler in src/tools.ts file or create a new file in the src/tools directory
    • The tool should follow the ToolHandler interface
  2. Configure your tool:
    • Add your tool configuration to the toolConfigs array in src/tools.ts
    • Define the name, description, input schema, and handler for your tool
  3. Export and register your tool:
    • If you created a separate file, export your handler and import it in src/tools.ts
    • Make sure your tool is properly registered in the toolConfigs array

Example:

// In src/tools.ts (adding directly to the toolConfigs array) { name: "myTool", description: "My tool description", inputSchema: { type: "object" as const, properties: {}, required: [], }, handler: async () => { return createSuccessResult({ result: "Tool result" }); }, }

Error Handling

The server implements comprehensive error handling:

  • All operations are wrapped in try/catch blocks
  • Proper validation for parameters and inputs
  • Appropriate error messages for better debugging
  • Helper functions for creating standardized error and success responses

Security Considerations

  • API key authentication for all connections
  • Type validation for all parameters
  • No hard-coded sensitive information
  • Proper error handling to prevent information leakage
  • Session-based transport management

MCP Protocol Features

This boilerplate supports the core MCP features:

  • Tools: List and call tools with proper parameter validation
  • Logging: Various severity levels (debug, info, notice, warning, error, critical, alert, emergency)
  • Server configuration: Name, version, and capabilities

Session Management

The server manages client sessions through:

  • Unique session IDs for each client connection
  • Tracking of active transports by session ID
  • Automatic cleanup of disconnected sessions
  • Connection status tracking

Additional Resources

License

This project is licensed under the MIT License - see the LICENSE file for details.

-
security - not tested
A
license - permissive license
-
quality - not tested

A server that implements the Model Context Protocol, providing a standardized way to connect AI models to different data sources and tools.

  1. Features
    1. Tools
      1. Configuration
        1. Troubleshooting SSE Timeouts
      2. Setup
        1. Development
          1. API Endpoints
            1. MCP Configuration
              1. Extending the boilerplate
                1. Adding Custom Tools
              2. Error Handling
                1. Security Considerations
                  1. MCP Protocol Features
                    1. Session Management
                      1. Additional Resources
                        1. License

                          Related MCP Servers

                          • A
                            security
                            F
                            license
                            A
                            quality
                            A Model Context Protocol server that enables AI models to interact with SourceSync.ai's knowledge management platform for managing documents, ingesting content from various sources, and performing semantic searches.
                            Last updated -
                            25
                            14
                            • Apple
                            • Linux
                          • -
                            security
                            F
                            license
                            -
                            quality
                            A server that enables AI systems to browse, retrieve content from, and interact with web pages through the Model Context Protocol.
                            Last updated -
                          • A
                            security
                            F
                            license
                            A
                            quality
                            A Model Context Protocol server implementation that provides structured, AI-friendly access to eRegulations data, making it easier for AI models to answer user questions about administrative procedures.
                            Last updated -
                            4
                            28
                            TypeScript
                            • Linux
                            • Apple
                          • -
                            security
                            A
                            license
                            -
                            quality
                            A Model Context Protocol server that provides a standardized interface for AI models to access, query, and modify content in Notion workspaces.
                            Last updated -
                            275
                            2
                            TypeScript
                            MIT License
                            • Apple

                          View all related MCP servers

                          ID: hvby5vclw6