mcp-builder

Guides building and evaluating MCP servers in Python or TypeScript.

Updated Sep 11, 2026
One-click install
npx skills add https://github.com/CYRUS-pinto/pi-bot --skill mcp-builder-cyrus-pinto
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: mcp-builder
Source: https://github.com/CYRUS-pinto/pi-bot/tree/main/.agents/skills/mcp-builder
Command: npx skills add https://github.com/CYRUS-pinto/pi-bot --skill mcp-builder-cyrus-pinto

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? Building Model Context Protocol servers that LLMs can actually use effectively requires careful tool design, schema validation, transport selection, and evaluation—this Skill provides a structured four-phase workflow covering research, implementation, review, and evaluation. ## Core Features & Use Cases - End-to-End MCP Development Workflow: Guides you through research, planning, implementation, testing, and evaluation phases for MCP servers in Python (FastMCP) or TypeScript (MCP SDK). - Language-Specific Reference Guides: Includes detailed implementation patterns for Zod/Pydantic schemas, tool registration, pagination, error handling, and transport configuration (stdio vs streamable HTTP). - Evaluation Harness: Ships Python scripts to run automated evaluations that test whether LLMs can answer complex questions using only your MCP server's tools. - Use Case: You need to expose your company's internal API to an LLM assistant. Use this Skill to design well-named tools with proper annotations, implement the server in TypeScript, and generate 10 evaluation questions to verify quality. ## Quick Start Ask the agent to help you build an MCP server for your chosen API, specifying whether you want Python or TypeScript.

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 official MCP TypeScript SDK's McpServer class and registerTool method with Zod schemas for input validation. Initialize the server with a name following the {service}-mcp-server convention, then connect via StdioServerTransport for local use or StreamableHTTPServerTransport for remote deployment.

Should I use Python or TypeScript for an MCP server?

TypeScript is recommended due to high-quality SDK support, static typing, and strong linting tools, with FastMCP available as the Python alternative. Both SDKs support stdio and streamable HTTP transports, so choose based on your existing stack and deployment environment.

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

Use stdio for local integrations and command-line tools running as subprocesses, and streamable HTTP for remote servers serving multiple clients. SSE is deprecated in favor of streamable HTTP, and stdio servers must log to stderr rather than stdout.

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 the evaluation.py script with your transport configuration. The harness uses Claude to attempt each question and reports accuracy, tool call counts, and agent feedback on your tool design.

What makes a good MCP tool description?

Tool descriptions must narrowly and unambiguously describe functionality, document parameters with types and constraints, and specify return value schemas. Include annotations like readOnlyHint and destructiveHint, use snake_case names with service prefixes like github_create_issue, and provide actionable error messages.