mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Why use this skill?
Master Model Context Protocol (MCP) server development. Use mcp-builder to design high-impact, agent-centric tools for your AI integrations.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/seanphan/mcp-builderWhat This Skill Does
The mcp-builder skill is a specialized development assistant designed to help developers architect, implement, and optimize Model Context Protocol (MCP) servers. By adhering to agent-centric design principles, this skill bridges the gap between raw API functionality and the complex reasoning needs of LLM agents. It provides a structured workflow covering research, protocol adherence, and best-practice implementation for both Python (FastMCP) and TypeScript SDKs, ensuring your MCP servers are efficient, reliable, and highly usable for autonomous agents.
Installation
To integrate this skill into your environment, execute the following command in your terminal:
clawhub install openclaw/skills/skills/seanphan/mcp-builder
Ensure you have the latest version of the OpenClaw agent environment configured, as this skill relies on up-to-date protocol specifications.
Use Cases
- API Integration: Transform standard REST or GraphQL APIs into agent-native MCP tools that support complex decision-making workflows.
- Agentic Workflow Design: Consolidate multi-step API operations into single, high-level tools to preserve LLM context windows.
- Error Handling Optimization: Craft semantic error messages that teach the agent how to correct its own usage patterns during failed attempts.
- Production-Grade Infrastructure: Use this skill to structure robust MCP servers that adhere to the full protocol specification for production deployment.
Example Prompts
- "I am building an MCP server for a CRM API. How should I design the 'fetch_leads' tool so that it is optimized for an agent's limited context?"
- "Draft a Python FastMCP implementation for a calendar service that combines checking availability and booking a slot into a single agentic tool."
- "My agent is failing to interpret error messages from my custom MCP tool. How can I rewrite the error handling to be more instructional based on MCP best practices?"
Tips & Limitations
- Tip: Always prioritize human-readable identifiers over database IDs to reduce ambiguity for the agent.
- Tip: Utilize the provided WebFetch capabilities to cross-reference your code against the official MCP documentation frequently.
- Limitation: This skill provides architectural guidance and code patterns; it does not host the infrastructure for you. You remain responsible for secure hosting and environment variables required for your specific API integrations.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-seanphan-mcp-builder": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: external-api, code-execution
Related Skills
artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
template-skill
Replace with description of the skill and when Claude should use it.
canvas-design
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
algorithmic-art
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.