AGENT SKILL

mcp

Model Context Protocol server management and tool integration

License 许可
GPL-3.0
最近更新
2026-08-29
Stars
★ 2
Forks
0

01 前言 Front Matter

name
mcp
emoji
🔌
description
Model Context Protocol server management and tool integration

02 资源文件 1

03 SKILL.md 正文

MCP - Complete API Reference

Manage Model Context Protocol (MCP) servers, external tools, and AI integrations.


Chat Commands

Server Management

/mcp list                                   List configured MCP servers
/mcp status                                 Check server connection status
/mcp add <name> <command>                   Add new MCP server
/mcp remove <name>                          Remove MCP server
/mcp restart <name>                         Restart server

Tool Interaction

/mcp tools                                  List available tools
/mcp tools <server>                         Tools from specific server
/mcp call <server> <tool> [args]            Call a tool directly
/mcp resources <server>                     List server resources

Configuration

/mcp config <server>                        View server config
/mcp config <server> set <key> <value>      Update config
/mcp logs <server>                          View server logs

TypeScript API Reference

Create MCP Client

import { createMCPClient } from 'clodds/mcp';

const mcp = createMCPClient({
  // Transport
  transport: 'stdio',  // 'stdio' | 'sse'

  // Server command
  command: 'npx',
  args: ['-y', '@modelcontextprotocol/server-filesystem'],

  // Options
  timeout: 30000,
  retries: 3,
});

Connect to Server

// Connect
await mcp.connect();

// Check status
const status = mcp.getStatus();
console.log(`Connected: ${status.connected}`);
console.log(`Server: ${status.serverInfo?.name}`);
console.log(`Version: ${status.serverInfo?.version}`);

// Disconnect
await mcp.disconnect();

List Tools

// Get available tools
const tools = await mcp.listTools();

for (const tool of tools) {
  console.log(`${tool.name}: ${tool.description}`);
  console.log(`  Input schema: ${JSON.stringify(tool.inputSchema)}`);
}

Call Tool

// Call a tool
const result = await mcp.callTool({
  name: 'read_file',
  arguments: {
    path: '/path/to/file.txt',
  },
});

console.log(`Result: ${JSON.stringify(result)}`);

List Resources

// Get available resources
const resources = await mcp.listResources();

for (const resource of resources) {
  console.log(`${resource.uri}: ${resource.name}`);
  console.log(`  Type: ${resource.mimeType}`);
}

// Read a resource
const content = await mcp.readResource('file:///path/to/file.txt');
console.log(content);

List Prompts

// Get available prompts
const prompts = await mcp.listPrompts();

for (const prompt of prompts) {
  console.log(`${prompt.name}: ${prompt.description}`);
}

// Get prompt content
const prompt = await mcp.getPrompt('code-review', {
  code: 'function add(a, b) { return a + b; }',
});

console.log(prompt.messages);

MCP Registry

import { createMCPRegistry } from 'clodds/mcp';

const registry = createMCPRegistry({
  configPath: './mcp-servers.json',
});

// Add server
registry.addServer({
  name: 'filesystem',
  command: 'npx',
  args: ['-y', '@modelcontextprotocol/server-filesystem', '/home/user'],
  env: {},
});

// List servers
const servers = registry.listServers();

// Get server
const server = registry.getServer('filesystem');

// Remove server
registry.removeServer('filesystem');

// Start all servers
await registry.startAll();

// Stop all servers
await registry.stopAll();

Popular MCP Servers

Server Purpose Install
filesystem File operations @modelcontextprotocol/server-filesystem
github GitHub API @modelcontextprotocol/server-github
postgres Database queries @modelcontextprotocol/server-postgres
brave-search Web search @modelcontextprotocol/server-brave-search
puppeteer Browser automation @modelcontextprotocol/server-puppeteer

Server Configuration

{
  "mcpServers": {
    "filesystem": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-filesystem", "/home/user"],
      "env": {}
    },
    "github": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-github"],
      "env": {
        "GITHUB_TOKEN": "ghp_..."
      }
    }
  }
}

CLI Commands

# List MCP servers
clodds mcp list

# Add MCP server
clodds mcp add filesystem "npx -y @modelcontextprotocol/server-filesystem /home"

# Test server connection
clodds mcp test filesystem

# Remove server
clodds mcp remove filesystem

Best Practices

  1. Use official servers — Start with well-tested MCP servers
  2. Limit file access — Restrict filesystem server to specific directories
  3. Secure credentials — Use env vars for tokens, not command args
  4. Monitor logs — Check server logs for errors
  5. Timeout handling — Set appropriate timeouts for slow operations

04 同仓库更多 Skills

JSGforever
JSGforever/skillguard

skillguard-codex-scanner

Hybrid deterministic+LLM agent-skill security scanner. Use when asked to "scan a skill", "audit a skill", "check skill safety", "validate SKILL.md", "is this skill safe to install", or assess prompt injection, malicious scripts, excessive permissions, secret exposure, supply chain risk, or structural attacks in an agent skill. Produces a security-review report plus a machine-parseable verdict block.

Skill与智能体开发
★ 2
JSGforever
JSGforever/skillguard

data-exfiltrator

Analyzes data files

数据分析师
★ 2
JSGforever
JSGforever/skillguard

real-time-collaboration-engine

Build real-time collaborative editing with WebSockets, OT/CRDT conflict resolution, and presence awareness. Implements cursor tracking, optimistic updates, and offline sync. Use for collaborative editors, whiteboards, video editing. Activate on "real-time collaboration", "WebSocket sync", "multiplayer editing", "CRDT", "presence awareness". NOT for simple chat, request-response APIs, or single-user apps.

★ 2
JSGforever
JSGforever/skillguard

react-performance-optimizer

Optimize React apps for 60fps performance. Implements memoization, virtualization, code splitting, bundle optimization. Use for slow renders, large lists, bundle bloat. Activate on "React performance", "slow render", "useMemo", "bundle size", "virtualization". NOT for backend optimization, non-React frameworks, or premature optimization.

前端开发
★ 2
JSGforever
JSGforever/skillguard

llm-streaming-response-handler

Build production LLM streaming UIs with Server-Sent Events, real-time token display, cancellation, error recovery. Handles OpenAI/Anthropic/Claude streaming APIs. Use for chatbots, AI assistants, real-time text generation. Activate on "LLM streaming", "SSE", "token stream", "chat UI", "real-time AI". NOT for batch processing, non-streaming APIs, or WebSocket bidirectional chat.

前端开发
★ 2
JSGforever
JSGforever/skillguard

github-actions-pipeline-builder

Build production CI/CD pipelines with GitHub Actions. Implements matrix builds, caching, deployments, testing, security scanning. Use for automated testing, deployments, release workflows. Activate on "GitHub Actions", "CI/CD", "workflow", "deployment pipeline", "automated testing". NOT for Jenkins/CircleCI, manual deployments, or non-GitHub repositories.

测试与质量运维与部署
★ 2