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

Mar 15, 2026

Find agent skills by outcome

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

* This server provides tools to interact with Example API

* project management

const truncatedData = data.slice(0

const data = await apiRequest(params.limit

- Return complete

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

- The `register*` methods provide better type safety

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

2. **Load each task instruction** and in parallel using the MCP server and tools

Remember to parallelize solving tasks to avoid running out of context

<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.

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

Prioritize comprehensive API coverage. List endpoints to implement

Review the service's API documentation to identify key endpoints

- **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

Agents benefit from concise tool descriptions and the ability to filter/paginate results. Design tools that return focused

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()`

2. Load each task instruction and in parallel using the MCP server and tools

- 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