mcp-builder

Guides building MCP servers in TypeScript or Python with evaluation tooling.

Updated Mar 31, 2026
One-click install
npx skills add https://github.com/SESELOVSKYDarian/Vase --skill mcp-builder-seselovskydarian
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: mcp-builder
Source: https://github.com/SESELOVSKYDarian/Vase/tree/main/.agents/skills/mcp-builder
Command: npx skills add https://github.com/SESELOVSKYDarian/Vase --skill mcp-builder-seselovskydarian

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 testing, which is easy to get wrong without structured guidance. ## Core Features & Use Cases - Four-Phase Workflow: Covers research and planning, implementation, review and testing, and evaluation creation for MCP servers. - Language-Specific Guides: Provides reference documentation for TypeScript (MCP SDK with Zod) and Python (FastMCP with Pydantic) implementations. - Evaluation Harness: Includes Python scripts to run XML-based QA evaluations against MCP servers over stdio, SSE, or streamable HTTP transports. - Use Case: You want to expose the GitHub API to an LLM agent. Follow the guide to design tools like github_create_issue, implement them with the TypeScript SDK, then generate 10 evaluation questions and run the harness to measure accuracy. ## Quick Start Ask the assistant to help you build an MCP server for your chosen API using the mcp-builder guide, starting with research and tool 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 guide covers project structure, package.json setup, error handling, and a complete working example with stdio or streamable HTTP transport.

How do I test an MCP server with evaluations?

Create an XML file with 10 read-only question-answer pairs, then run scripts/evaluation.py with your transport type (stdio, sse, or http). The harness uses Claude to attempt each question and reports accuracy, tool calls, and agent feedback.

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

Use stdio for local integrations and single-client command-line tools. Use streamable HTTP for remote servers, web services, and multi-client scenarios. SSE is deprecated in favor of streamable HTTP.

What makes a good MCP tool name?

Use snake_case with a service prefix and action verb, like github_create_issue or slack_send_message. Prefixes prevent naming conflicts when multiple MCP servers are used together, and action-oriented names improve discoverability.

What are the requirements for MCP evaluation questions?

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 whose answers change over time, like counts of current open issues.