while comprehensive coverage gives agents flexibility to compose operations. Performance varies by client—some clients benefit from code execution that combines basic tools

Mar 20, 2026

Find agent skills by outcome

data = await api_request(limit=params.limit

- Return complete

- Omit verbose metadata (e.g.

The official MCP Python SDK provides FastMCP

This document provides Python-specific best practices and examples for implementing MCP servers using the MCP Python SDK. It covers server setup

- [ ] Tools enable complete workflows

Expose data as resources for efficient

* project management

* This server provides tools to interact with Example API

const truncatedData = data.slice(0

- Return complete

const data = await apiRequest(params.limit

│ └── constants.ts # Shared constants (API_URL

- **DO NOT use**: Old deprecated APIs such as `server.tool()`

<question>Look for pull requests that modified files in the /api directory and were merged between January 1 and January 31

After understanding the API and tools

- Store API keys in environment variables

- **Return pagination metadata**: Include `has_more`

- **Python**: `{service}_mcp` (e.g.

Prioritize comprehensive API coverage. List endpoints to implement

- [🐍 Python Guide](./reference/python_mcp_server.md) - Module organization

- **Language**: TypeScript (high-quality SDK support and good compatibility in many execution environments e.g. MCPB. Plus AI models are good at generating TypeScript code

Review the service's API documentation to identify key endpoints

Balance comprehensive API endpoint coverage with specialized workflow tools. Workflow tools can be more convenient for specific tasks

- DO NOT use: Old deprecated APIs such as `server.tool()`

- Return pagination metadata: Include `has_more`

- Python: `{service}_mcp` (e.g.

- Language: TypeScript (high-quality SDK support and good compatibility in many execution environments e.g. MCPB. Plus AI models are good at generating TypeScript code