服务器协调器

运维部署 社区

技能解读

当前原文的自动摘译,尚未人工审校。

MCP 架构概述

关键概念: 服务器:通过 MCP 协议提供工具、资源和提示 客户端:使用服务器功能(Claude Desktop、Claude Code 等) 传输:通信层(stdio、SSE、WebSocket)

配置位置

客户端 · 配置文件 · 平台 Claude Desktop · claude_desktop_config.json · macOS:~/Library/Application Support/Claude/ Windows:%APPDATA%\Claude\ Claude Code · settings.json 或 MCP 配置 · 项目级别或用户设置 Cline · cline_mcp_settings.json · VS Code 扩展设置

常见服务器类型

Python 服务器 (uvx): 节点服务器 (npx): 本地开发服务器:

连接问题

验证服务器独立启动:检查日志:Claude Desktop:~/Library/Logs/Claude/mcp*.log 查找 JSON-RPC 错误、连接超时验证 JSON 配置:

身份验证问题

OAuth 流程:确保重定向 URI 配置正确 API 密钥:验证服务器进程可访问的环境变量 令牌刷新:检查令牌存储位置和权限

流狐档案 运行与权限由流狐静态检查推断,不代表作者声明或实际测试结果。
领域
运维部署
作者声明的智能体
未找到明确声明;不据此推断已兼容或已测试
静态检查
88 / 100 · 启发式扫描,不代表运行安全
运行环境证据
未执行;当前没有隔离运行测试证据
作者 / 版本 / 许可证
@tomevault-io · 未声明许可证
上下文用量评级
低消耗
接入复杂程度
需手动接入
是否需要外部接口密钥
需要 · Vendor-specific
兼容的系统
macOS · Windows
运行环境要求
Node.js · Python
检测到的文件与系统行为
  • 只读
  • 命令执行
  • 读取环境变量
网络行为
允许外网请求
安装命令数
无(仅作为资料)

需要注意: 未声明工具权限范围;实际权限由运行环境决定。

作者说明文件(原文) SKILL.md

# MCP Server Orchestrator

Manage MCP server infrastructure for AI-powered development workflows.

## MCP Architecture Overview

```
┌─────────────────┐     ┌──────────────────┐     ┌─────────────────┐
│   MCP Client    │────▶│   MCP Server     │────▶│  External APIs  │
│ (Claude, etc.)  │◀────│  (Tool Provider) │◀────│  (Services)     │
└─────────────────┘     └──────────────────┘     └─────────────────┘
         │                       │
         └───── JSON-RPC ────────┘
```

**Key concepts:**
- **Server**: Provides tools, resources, and prompts via MCP protocol
- **Client**: Consumes server capabilities (Claude Desktop, Claude Code, etc.)
- **Transport**: Communication layer (stdio, SSE, WebSocket)

## Configuration Locations

| Client | Config File | Platform |
|--------|------------|----------|
| Claude Desktop | `claude_desktop_config.json` | macOS: `~/Library/Application Support/Claude/` |
| | | Windows: `%APPDATA%\Claude\` |
| Claude Code | `settings.json` or MCP config | Project-level or user settings |
| Cline | `cline_mcp_settings.json` | VS Code extension settings |

## Server Configuration Schema

```json
{
  "mcpServers": {
    "server-name": {
      "command": "executable",
      "args": ["arg1", "arg2"],
      "env": {
        "API_KEY": "value"
      },
      "disabled": false
    }
  }
}
```

### Common Server Types

**Python Server (uvx)**:
```json
{
  "my-python-server": {
    "command": "uvx",
    "args": ["--from", "package-name", "server-command"]
  }
}
```

**Node Server (npx)**:
```json
{
  "my-node-server": {
    "command": "npx",
    "args": ["-y", "@scope/package-name"]
  }
}
```

**Local Development Server**:
```json
{
  "dev-server": {
    "command": "python",
    "args": ["-m", "my_server"],
    "env": {
      "DEBUG": "true"
    }
  }
}
```

## Troubleshooting Workflow

### Connection Issues

1. **Verify server starts independently**:
   ```bash
   # Test Python server
   python -m my_server
   
   # Test Node server
   npx -y @scope/package-name
   ```

2. **Check logs**:
   - Claude Desktop: `~/Library/Logs/Claude/mcp*.log`
   - Look for JSON-RPC errors, connection timeouts

3. **Validate JSON config**:
   ```bash
   python -c "import json; json.load(open('config.json'))"
   ```

4. **Common fixes**:
   - Use absolute paths for commands
   - Ensure dependencies installed in correct environment
   - Check API keys/env vars are set
   - Restart client after config changes

### Authentication Issues

1. **OAuth flows**: Ensure redirect URIs configured correctly
2. **API keys**: Verify env vars accessible to server process
3. **Token refresh**: Check token storage location and permissions

## Building Custom Servers

### Python Server (FastMCP)

```python
from fastmcp import FastMCP

mcp = FastMCP("my-server")

@mcp.tool()
def my_tool(param: str) -> str:
    """Tool description for the AI."""
    return f"Result: {param}"

@mcp.resource("resource://my-data")
def get_data() -> str:
    """Provide data as a resource."""
    return "Resource content"

if __name__ == "__main__":
    mcp.run()
```

### Node Server (MCP SDK)

```typescript
import { Server } from "@modelcontextprotocol/sdk/server/index.js";
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";

const server = new Server({ name: "my-server", version: "1.0.0" }, {
  capabilities: { tools: {} }
});

server.setRequestHandler(ListToolsRequestSchema, async () => ({
  tools: [{
    name: "my_tool",
    description: "Tool description",
    inputSchema: { type: "object", properties: { param: { type: "string" } } }
  }]
}));

const transport = new StdioServerTransport();
await server.connect(transport);
```

## Multi-Server Orchestration

### Modular Architecture

Organize servers by domain:

```json
{
  "mcpServers": {
    "filesystem": { "command": "...", "args": ["--allowed-dirs", "/projects"] },
    "database": { "command": "...", "env": { "DB_URL": "..." } },
    "api-integrations": { "command": "...", "env": { "API_KEYS": "..." } },
    "custom-tools": { "command": "python", "args": ["-m", "my_tools"] }
  }
}
```

### Server Selection Strategy

Think of servers as modules in a synthesizer—patch them together based on workflow needs:

- **Development workflow**: filesystem + git + code-analysis servers
- **Research workflow**: web-search + document + note-taking servers
- **Data workflow**: database + visualization + export servers

## Performance Optimization

- **Lazy loading**: Only enable servers needed for current task
- **Caching**: Implement response caching for expensive operations
- **Timeout tuning**: Adjust timeouts for slow external APIs
- **Connection pooling**: Reuse connections in database servers

## References

- `references/server-templates.md` - Boilerplate for common server types
- `references/debugging-guide.md` - Detailed troubleshooting procedures

---
> Source: [a-organvm/a-i--skills](https://github.com/a-organvm/a-i--skills) — distributed by [TomeVault](https://tomevault.io).
<!-- tomevault:4.0:skill_md:2026-05-23 -->

讨论

基于 GitHub Discussions。登录 GitHub 即可参与讨论、点赞、订阅更新。