mcp-builder

Guides building and evaluating MCP servers in Python or TypeScript.

Updated Sep 1, 2026
One-click install
npx skills add https://github.com/sshekhar-04/SIH_PS_26151 --skill mcp-builder-sshekhar-04
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: mcp-builder
Source: https://github.com/sshekhar-04/SIH_PS_26151/tree/main/.agents/Skills/mcp-builder
Command: npx skills add https://github.com/sshekhar-04/SIH_PS_26151 --skill mcp-builder-sshekhar-04

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? Building MCP (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 - Guided MCP Server Development: Step-by-step process for designing tools with proper naming, input/output schemas, annotations, pagination, and error handling in Python (FastMCP) or TypeScript (MCP SDK). - Reference Documentation: Bundled guides covering MCP best practices, language-specific implementation patterns, and quality checklists. - Evaluation Harness: Scripts to create XML-based evaluation question sets and run automated tests measuring how well an LLM can use your MCP server via stdio, SSE, or HTTP transports. - Use Case: You need to expose your company's internal API to an LLM agent. Use this Skill to scaffold a TypeScript MCP server with Zod-validated tools, then generate 10 evaluation questions and run the evaluation script to verify agents can answer realistic questions. ## Quick Start Ask the AI to help you build an MCP server for your chosen API, specifying whether you want Python or TypeScript and which endpoints to cover.

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 or TypeScript?

Follow the four-phase workflow: research the MCP spec and target API, implement tools using FastMCP (Python) or the TypeScript SDK with registerTool, review code quality, then create evaluations. Use Zod schemas in TypeScript or Pydantic in Python for input validation.

What transport should I use for my MCP server?

Use streamable HTTP for remote servers serving multiple clients, and stdio for local integrations and command-line tools. SSE is deprecated in favor of streamable HTTP. Stdio servers must log to stderr, never stdout.

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

Create an XML evaluation file with 10 read-only, complex questions having single verifiable answers, then run scripts/evaluation.py with your transport type. The harness uses Claude to attempt each question and reports accuracy, tool calls, and agent feedback.

What makes a good MCP tool name and description?

Use snake_case with a service prefix like github_create_issue to avoid conflicts with other servers. Descriptions must precisely match functionality, document parameters and return schemas, and include annotations like readOnlyHint and destructiveHint.

Why do my MCP evaluation questions need stable answers?

Answers verified by direct string comparison must not change over time, so questions should target historical or closed data rather than current state like open issue counts. Base questions on completed projects, merged pull requests, or fixed time windows.