MCP Builder

Featured markdown Development

mcpserverspythontypescripttools

Summary

Guidance for building high-quality MCP servers that expose external APIs to LLMs through well-designed tools, in Python (FastMCP) or Node/TypeScript.

Features

Design clear, LLM-friendly tools
Python (FastMCP) and Node/TypeScript (MCP SDK) patterns
Robust schema and error handling
Testing and validation guidance
Best practices for tool naming and descriptions

Install This Skill

Add this skill to your favorite AI agent in a few steps.

Any AI agent

This skill is plain instructions — it works with any assistant that accepts custom instructions or system prompts.

Copy the skill content with the button below.
Paste it into your agent's instruction file or system prompt (for example AGENTS.md, .cursorrules, or a custom instructions field).
Ask the agent to apply the skill whenever the task matches.

Claude Code & Claude apps

Claude loads skills automatically from its skills directory.

Claude Code

Create a skill folder — personal: ~/.claude/skills/mcp-builder/, or per-project: .claude/skills/mcp-builder/
Save the skill content as SKILL.md inside that folder.
Claude Code picks it up automatically and invokes it when relevant.

mkdir -p ~/.claude/skills/mcp-builder

Claude.ai / Claude Desktop

Enable Skills under Settings → Capabilities, then upload the skill (a folder or zip containing SKILL.md).

One-prompt install

Paste this prompt into any agent with web access and it will install the skill for you.

Install the "MCP Builder" skill from Onei AI. Fetch https://onei.ai/skills/mcp-builder, extract the full skill content from the page, and save it where you load skills from (for Claude Code: .claude/skills/mcp-builder/SKILL.md). From now on, apply this skill whenever it is relevant to my request.

Skill Content

Markdown Content

Copy this content and use it with your preferred AI agent

# MCP Builder

Use this skill when building an MCP server to integrate an external API or service.

## What it teaches
- How to model an external API as a small set of well-named, well-scoped tools
- Writing input schemas and tool descriptions an LLM can use reliably
- Error handling that gives the model something actionable
- Python (FastMCP) and Node/TypeScript (MCP SDK) implementations
- Testing the server before shipping

## Principle
A good MCP server is judged by how easily an agent succeeds with its tools — not by how many endpoints it wraps.

Description

A skill for creating well-designed Model Context Protocol servers. It guides tool design, schema definition, error handling, and testing for servers that let LLMs interact with external services — whether written in Python with FastMCP or in Node/TypeScript with the MCP SDK. Use it when integrating an external API or service as an MCP server.