Summary
This is a context management layer for working with MCP servers. It keeps your main Claude session clean by delegating tool discovery and execution to subagents or the Gemini CLI. The workflow is practical: it saves discovered tools to a JSON catalog, lets an LLM analyze which ones you actually need for a task, then executes them without loading dozens of irrelevant tool definitions into your context. Supports multiple servers from a single config file. The three-tier execution strategy (Gemini CLI first, direct scripts second, subagent fallback) is smart. Most useful when you have several MCP servers configured and don't want every single tool cluttering your available actions list.
Install to Claude Code
npx -y skills add mrgoonie/claudekit-skills --skill mcp-management --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 →
