Summary
This is a comprehensive reference for building MCP servers, covering everything from basic architecture to tool design patterns and security practices. Use it when you're implementing MCP tools or resources and need quick answers on schemas, error handling, or transport types. It's dense with tables and checklists, so it works best as a lookup guide rather than a tutorial. The practical bits on tool naming, input validation, and the current spec features (tool annotations, outputSchema) are immediately actionable. If you're wiring up Claude to external systems via MCP, keep this one loaded.
Install to Claude Code
npx -y skills add vudovn/antigravity-kit --skill mcp-builder --agent claude-codeInstalls into .claude/skills of the current project.
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Files
SKILL.md
Select a file.
Featured
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
