How do I install the MCP Builder skill?

Run npx skillmds@latest add tomevault-io/mcp-builder-41 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. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. 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, and the skill stays under its author's original license.

Who published MCP Builder?

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

MCP Builder by tomevault-io — Agent Skill

Name: MCP Builder
Author: tomevault-io

MCP Builder

MCP server development for AI agents. Designs tool schemas, implements Python/TypeScript servers, creates evaluation tests. Use when user asks to build MCP server, create tool integration, or develop Claude plugins. Supports GitHub/Notion/Slack integrations. Use when this capability is needed.

tomevault-io Updated Sep 17, 2026

File contents

MCP Server Development Tool

Build high-quality Model Context Protocol servers to provide external tool capabilities for AI agents.

Core Capabilities

MCP protocol understanding and server architecture design
Python/TypeScript SDK implementation
Tool schema design for AI agents
Evaluation test creation and validation

Tech Stack

Language	SDK	Validation	Runtime
Python	MCP Python SDK	Pydantic v2	asyncio
TypeScript	MCP TypeScript SDK	Zod	Node.js 18+

Executable Tools

The following scripts can be run directly without reading source code:

scripts/evaluation.py - Run MCP server evaluation tests
scripts/connections.py - Test server connection status

Design Principles

Workflow-Oriented: Build complete task tools, not simple API wrappers
Optimize Context: Return high-signal information, avoid data dumping
Actionable Errors: Error messages guide agents to correct usage
Evaluation-Driven: Create evaluation scenarios early, iterate based on agent feedback

Boundaries

Focus on MCP server development and tool design, not third-party API development or client integration.

When NOT to Use

Writing general business logic code → use developer
Frontend UI development → use frontend-design
API design → use api-designer
Database schema design → use database-engineer
Product planning or requirements → use product-manager

Detailed References

./workflows/mcp-development.md - Complete development workflow
./guides/mcp_best_practices.md - MCP best practices
./guides/python_mcp_server.md - Python implementation guide
./guides/node_mcp_server.md - TypeScript implementation guide
./guides/evaluation.md - Evaluation creation guide

Escalation Rules

Pause and ask the owner before:

exposing tools that have overly broad permissions or weak schema boundaries
expanding server scope into generic third-party API integration work
shipping an MCP interface without at least a basic evaluation or validation path

Final Output Contract (MANDATORY)

Every use of this skill should end with:

Skill Fit - why an MCP server or tool design solution is needed
Primary Deliverable - server design, tool schema, or implementation plan
Execution Evidence - guides used, files changed, and evaluation steps prepared
Risks / Open Questions - permission, schema, or agent-usage concerns
Next Action - the next build, test, or review step

Source: JochenYang/Jochen-ai-rules — distributed by TomeVault.

---name: mcp-builder-41description: MCP server development for AI agents. Designs tool schemas, implements Python/TypeScript servers, creates evaluation tests. Use when user asks to build MCP server, create tool integration, or develop Claude plugins. Supports GitHub/Notion/Slack integrations. Use when this capability is needed.---# MCP Server Development ToolBuild high-quality Model Context Protocol servers to provide external tool capabilities for AI agents.## Core Capabilities- MCP protocol understanding and server architecture design- Python/TypeScript SDK implementation- Tool schema design for AI agents- Evaluation test creation and validation## Tech Stack| Language | SDK | Validation | Runtime ||------------|--------------------|-------------|-------------|| Python | MCP Python SDK | Pydantic v2 | asyncio || TypeScript | MCP TypeScript SDK | Zod | Node.js 18+ |## Executable ToolsThe following scripts can be run directly without reading source code:- `scripts/evaluation.py` - Run MCP server evaluation tests- `scripts/connections.py` - Test server connection status## Design Principles1. **Workflow-Oriented**: Build complete task tools, not simple API wrappers2. **Optimize Context**: Return high-signal information, avoid data dumping3. **Actionable Errors**: Error messages guide agents to correct usage4. **Evaluation-Driven**: Create evaluation scenarios early, iterate based on agent feedback## BoundariesFocus on MCP server development and tool design, not third-party API development or client integration.## When NOT to Use- Writing general business logic code → use `developer`- Frontend UI development → use `frontend-design`- API design → use `api-designer`- Database schema design → use `database-engineer`- Product planning or requirements → use `product-manager`## Detailed References- `./workflows/mcp-development.md` - Complete development workflow- `./guides/mcp_best_practices.md` - MCP best practices- `./guides/python_mcp_server.md` - Python implementation guide- `./guides/node_mcp_server.md` - TypeScript implementation guide- `./guides/evaluation.md` - Evaluation creation guide## Escalation RulesPause and ask the owner before:- exposing tools that have overly broad permissions or weak schema boundaries- expanding server scope into generic third-party API integration work- shipping an MCP interface without at least a basic evaluation or validation path## Final Output Contract (MANDATORY)Every use of this skill should end with:1. `Skill Fit` - why an MCP server or tool design solution is needed2. `Primary Deliverable` - server design, tool schema, or implementation plan3. `Execution Evidence` - guides used, files changed, and evaluation steps prepared4. `Risks / Open Questions` - permission, schema, or agent-usage concerns5. `Next Action` - the next build, test, or review step---> Source: [JochenYang/Jochen-ai-rules](https://github.com/JochenYang/Jochen-ai-rules) — distributed by [TomeVault](https://tomevault.io).

Frequently asked questions