mcp-builder

Guides building and evaluating MCP servers in Python or TypeScript.

Updated Aug 5, 2026
One-click install
npx skills add https://github.com/amirbiron/claude-skills --skill mcp-builder-amirbiron
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: mcp-builder
Source: https://github.com/amirbiron/claude-skills/tree/main/skills/mcp-builder
Command: npx skills add https://github.com/amirbiron/claude-skills --skill mcp-builder-amirbiron

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 many design decisions—tool naming, schemas, pagination, transports, error handling—and most developers lack a structured process, resulting in servers that technically work but fail real agent tasks. ## Core Features & Use Cases - Four-Phase Development Workflow: Structured process covering research and planning, implementation, review and testing, and evaluation creation for MCP servers. - Language-Specific Guides: Detailed implementation references for TypeScript (MCP SDK with Zod) and Python (FastMCP with Pydantic), including project structure, tool registration, and quality checklists. - Evaluation Harness: Scripts to create 10-question XML evaluations and run them against your server via stdio, SSE, or HTTP transports, producing accuracy reports with agent feedback. - Use Case: You need to expose your company's internal API to Claude. Use this Skill to design well-named tools with proper schemas, implement the server in TypeScript, then generate and run an evaluation to verify LLMs can answer realistic questions using only your tools. ## Quick Start Help me build an MCP server for the GitHub API following the mcp-builder workflow, starting with research and planning.

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 TypeScript?

Use the MCP TypeScript SDK's McpServer class and registerTool method with Zod schemas for input validation. The Skill's node_mcp_server.md reference covers project structure, package.json setup, tool registration patterns, and a complete working example with stdio or streamable HTTP transport.

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

Create an XML evaluation file with 10 complex, read-only questions that have single verifiable answers, then run scripts/evaluation.py against your server. The harness connects via stdio, SSE, or HTTP, runs each question through Claude with your tools, and reports accuracy plus agent feedback.

Should I use Python FastMCP or the TypeScript SDK for MCP servers?

The Skill recommends TypeScript for its high-quality SDK support, static typing, and strong AI code generation, though Python with FastMCP is fully supported. Both have dedicated implementation guides with tool registration patterns and quality checklists.

What transport should my MCP server use, stdio or HTTP?

Use stdio for local integrations and command-line tools where the server runs as a subprocess. Use streamable HTTP for remote servers serving multiple clients; SSE is deprecated in favor of streamable HTTP.

What makes a good MCP evaluation question?

Questions must be independent, read-only, complex enough to require multiple tool calls, and have a single stable answer verifiable by string comparison. Avoid questions about current state like open issue counts, since answers change over time.