How do I install the MCP Builder skill?

Run npx skillmds@latest add gabrielmoreira/mcp-builder-7 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is MCP Builder safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with MCP Builder?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is MCP Builder free to use?

Yes. Installing skills from SkillMD is free. This skill is licensed under Complete terms in LICENSE.

Who published MCP Builder?

gabrielmoreira (@gabrielmoreira) published this skill. Their other Agent Skills are listed on their SkillMD profile.

MCP Builder by gabrielmoreira — Agent Skill

Name: MCP Builder
Rating: 4.2 (5 reviews)
Author: gabrielmoreira

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).

gabrielmoreira Updated Sep 22, 2026 17 repo stars

File contents

MCP Server Development

Guide for creating high-quality MCP (Model Context Protocol) servers.

Development Workflow

Phase 1: Research and Planning

Modern MCP Design: Balance comprehensive API coverage with specialized workflow tools. Prioritize clear, action-oriented tool names (e.g., github_create_issue).
Protocol Study: Review the specification overview and transport mechanisms.
Framework Selection:
- TypeScript (Recommended): Best SDK support and type safety.
- Python: Good for specific library integrations.
API Planning: Identify endpoints, auth requirements, and data models for the target service.

Phase 2: Implementation

Setup Project: Use language-specific templates.
Core Infrastructure: Implement API client, auth, and error handling helpers.
Implement Tools:
- Input Schema: Use Zod (TS) or Pydantic (Python) with clear descriptions.
- Output Schema: Define outputSchema for structured results.
- Annotations: Set readOnlyHint, destructiveHint, etc.

Phase 3: Review and Test

Code Quality: Ensure DRY principles and consistent error handling.
Testing:
- Verify compilation/syntax.
- Use the [MCP Inspector](https://npx @modelcontextprotocol/inspector).

Phase 4: Evaluation

Create evaluations to test LLM effectiveness using the provided guide.

Generate Questions: Create 10 realistic, complex, verifiable questions.
Verify Answers: Manually solve and document correct answers.
Format: Use the evaluation XML structure.

Resources

Best Practices: 📋 Core Guidelines
TypeScript SDK: ⚡ TS Patterns
Python SDK: 🐍 Python Patterns
Evaluations: ✅ Evaluation Guide

---name: mcp-builder-7description: 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).license: Complete terms in LICENSE.txt---# MCP Server DevelopmentGuide for creating high-quality MCP (Model Context Protocol) servers.## Development Workflow### Phase 1: Research and Planning1. **Modern MCP Design**: Balance comprehensive API coverage with specialized workflow tools. Prioritize clear, action-oriented tool names (e.g., `github_create_issue`).2. **Protocol Study**: Review the [specification overview](https://modelcontextprotocol.io/specification/draft.md) and transport mechanisms.3. **Framework Selection**: - **TypeScript (Recommended)**: Best SDK support and type safety. - **Python**: Good for specific library integrations.4. **API Planning**: Identify endpoints, auth requirements, and data models for the target service.### Phase 2: Implementation1. **Setup Project**: Use language-specific templates.2. **Core Infrastructure**: Implement API client, auth, and error handling helpers.3. **Implement Tools**: - **Input Schema**: Use Zod (TS) or Pydantic (Python) with clear descriptions. - **Output Schema**: Define `outputSchema` for structured results. - **Annotations**: Set `readOnlyHint`, `destructiveHint`, etc.### Phase 3: Review and Test1. **Code Quality**: Ensure DRY principles and consistent error handling.2. **Testing**: - Verify compilation/syntax. - Use the [MCP Inspector](https://npx @modelcontextprotocol/inspector).### Phase 4: EvaluationCreate evaluations to test LLM effectiveness using the provided guide.1. **Generate Questions**: Create 10 realistic, complex, verifiable questions.2. **Verify Answers**: Manually solve and document correct answers.3. **Format**: Use the [evaluation XML structure](reference/evaluation.md).## Resources- **Best Practices**: [📋 Core Guidelines](./reference/mcp_best_practices.md)- **TypeScript SDK**: [⚡ TS Patterns](./reference/node_mcp_server.md)- **Python SDK**: [🐍 Python Patterns](./reference/python_mcp_server.md)- **Evaluations**: [✅ Evaluation Guide](./reference/evaluation.md)

Frequently asked questions