Manage Model Context Protocol (MCP) servers - discover, analyze, and execute tools/prompts/resources from configured MCP servers. Use when working with MCP integrations, need to discover available MCP capabilities, filter MCP tools for specific tasks, execute MCP tools programmatically, access MCP prompts/resources, or implement MCP client functionality. Supports intelligent tool selection, multi-server management, and context-efficient capability discovery.
Intelligent management and execution of Model Context Protocol (MCP) servers.
This skill enables Claude to discover, analyze, and execute MCP server capabilities without polluting the main context window. Perfect for context-efficient MCP integration using subagent-based architecture.
mcp-manager subagentcd .claude/skills/mcp-management/scripts
npm install
Create .claude/.mcp.json:
{
"mcpServers": {
"memory": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-memory"]
},
"filesystem": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-filesystem", "/allowed/path"]
}
}
}
See .claude/.mcp.json.example for more examples.
cd .claude/skills/mcp-management/scripts
npm run list-tools
# Or directly:
npx tsx cli.ts list-tools
Note: The CLI automatically looks for config at ~/.claude/.mcp.json. You can run it from any directory.
cd .claude/skills/mcp-management/scripts
npm run list-tools
npm run list-prompts
npm run list-resources
# Or directly:
npx tsx cli.ts list-tools
npx tsx cli.ts list-prompts
npx tsx cli.ts list-resources
The LLM reads assets/tools.json and intelligently selects tools. No separate analysis command needed - the LLM's understanding of context and intent is superior to keyword matching.
npx tsx cli.ts call-tool memory add '{"key":"name","value":"Alice"}'
In main Claude conversation:
User: "I need to search the web and save results"
Main Agent: [Spawns mcp-manager subagent]
mcp-manager: Discovers brave-search + memory tools, reports back
Main Agent: Uses recommended tools for implementation
Main Agent (Claude)
↓ (delegates MCP tasks)
mcp-manager Subagent
↓ (uses skill)
mcp-management Skill
↓ (connects via)
MCP Servers (memory, filesystem, etc.)
Benefits:
mcp-management/
├── SKILL.md # Skill definition
├── README.md # This file
├── scripts/
│ ├── mcp-client.ts # Core MCP client manager
│ ├── analyze-tools.ts # Intelligent tool selection
│ ├── cli.ts # Command-line interface
│ ├── package.json # Dependencies
│ ├── tsconfig.json # TypeScript config
│ └── .env.example # Environment template
└── references/
├── mcp-protocol.md # MCP protocol reference
└── configuration.md # Config guide
Core client manager class:
.claude/.mcp.jsonCommand-line interface:
list-tools - Show all tools and save to assets/tools.jsonlist-prompts - Show all promptslist-resources - Show all resourcescall-tool <server> <tool> <json> - Execute toolNote: Tool analysis is performed by the LLM reading assets/tools.json, which provides better context understanding than algorithmic matching.
Scripts check for variables in this order:
process.env (runtime).claude/skills/mcp-management/.env.claude/skills/.env.claude/.env{
"mcpServers": {
"server-name": {
"command": "executable", // Required
"args": ["arg1", "arg2"], // Required
"env": { // Optional
"VAR": "value",
"API_KEY": "${ENV_VAR}" // Reference env vars
}
}
}
}
Install with npx:
@modelcontextprotocol/server-memory - Key-value storage@modelcontextprotocol/server-filesystem - File operations@modelcontextprotocol/server-brave-search - Web search@modelcontextprotocol/server-puppeteer - Browser automation@modelcontextprotocol/server-fetch - HTTP requestsThe mcp-manager agent (.claude/agents/mcp-manager.md) uses this skill to:
This architecture keeps main context clean and enables efficient MCP integration.
Ensure .claude/.mcp.json exists and is valid JSON.
Check:
npx packages installed?)List available tools first:
cd .claude/skills/mcp-management/scripts
npm run list-tools
MIT
npx skills add kettleofketchup/mcp-management下载完整 Skill 目录，包含 SKILL.md 及所有相关文件
Search for places (restaurants, cafes, etc.) via Google Places API proxy on localhost.
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Start voice calls via the OpenClaw voice-call plugin.
Notion API for creating and managing pages, databases, and blocks.
Gemini CLI for one-shot Q&A, summaries, and generation.
Category:developer