mcp-builder

Guides building and evaluating MCP servers in Python or TypeScript.

Updated Aug 28, 2026
One-click install
npx skills add https://github.com/AnderHonorato/Mem-rias-IA---Infinity --skill mcp-builder-anderhonorato
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: mcp-builder
Source: https://github.com/AnderHonorato/Mem-rias-IA---Infinity/tree/main/Manus/Skills/snapshots/anthropic-mcp-builder
Command: npx skills add https://github.com/AnderHonorato/Mem-rias-IA---Infinity --skill mcp-builder-anderhonorato

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires anthropic, mcp, and includes scripts (resource) and references (resource) components.

What problem does it solve? Building a Model Context Protocol server that LLMs can actually use effectively requires careful tool design, schema validation, transport selection, and testing—this Skill provides a structured four-phase workflow covering research, implementation, review, and evaluation. ## Core Features & Use Cases - Four-Phase Development Workflow: Deep research and planning, implementation with FastMCP (Python) or the MCP TypeScript SDK, code review and testing with MCP Inspector, and evaluation creation. - Language-Specific References: Detailed guides for Python and Node/TypeScript covering project structure, Zod/Pydantic schemas, tool annotations, pagination, and error handling. - Evaluation Harness: Scripts to create 10-question XML evaluations and run them against your server via stdio, SSE, or streamable HTTP, producing accuracy reports with per-task feedback. - Use Case: You need to expose your company's internal API to Claude. Follow the workflow to design well-named tools with clear schemas, implement the server in TypeScript, then run the evaluation harness to verify an LLM can answer realistic questions using only your tools. ## Quick Start Ask the AI to help you build an MCP server for your chosen API, specifying whether you want Python with FastMCP or TypeScript with the MCP SDK.

Frequently Asked Questions about mcp-builder

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build an MCP server in Python?

Use the FastMCP framework from the official MCP Python SDK, defining tools with the @mcp.tool decorator and Pydantic models for input validation. The reference guide covers server initialization, tool registration, and a complete working example with a quality checklist.

How do I build an MCP server in TypeScript?

Use the MCP TypeScript SDK's McpServer class and registerTool method with Zod schemas for runtime input validation. Name your server with the {service}-mcp-server convention, build with tsc, and test using the MCP Inspector via npx @modelcontextprotocol/inspector.

Should I use stdio or streamable HTTP for my MCP server?

Use stdio for local integrations and command-line tools running as a subprocess of the client. Use streamable HTTP for remote servers serving multiple clients, preferably with stateless JSON responses for simpler scaling.

How do I test whether my MCP server works well with LLMs?

Create an XML evaluation file with 10 complex, read-only questions having single verifiable answers, then run scripts/evaluation.py against your server. The harness reports accuracy, tool call counts, and per-task feedback on tool design quality.

What makes a good MCP tool description?

Tool descriptions should concisely state functionality, document each parameter, describe the return schema, and include usage examples. Use snake_case names with a service prefix like github_create_issue, and set annotations such as readOnlyHint and destructiveHint.

What dependencies are needed to run the MCP evaluation harness?

The evaluation scripts require the anthropic and mcp Python packages, plus an ANTHROPIC_API_KEY environment variable. The harness connects via stdio, SSE, or streamable HTTP and uses a Claude model to attempt each evaluation question.