深度长文｜MCP 协议 2026：从 0 到事实标准，开发者完全指南

MCP（Model Context Protocol）是 Anthropic 在 2024 年底提出、2025 年被 OpenAI / Google / 开源社区接受的 AI 工具调用协议。2026 年 6 月，它已经事实上成为标准。

本文 5000 字：协议原理、生态现状、Server 开发、最佳实践。

一、协议原理

MCP 是一个JSON-RPC 风格的协议，定义了 Agent 与工具之间的通信方式。

三类角色：

通信方式：

二、生态现状（2026 年 6 月）

三、写一个 MCP Server

from mcp.server import Server
from mcp.types import Tool, TextContent

app = Server("my-mcp-server")

@app.list_tools()
async def list_tools():
    return [
        Tool(
            name="get_weather",
            description="Get current weather for a city",
            inputSchema={
                "type": "object",
                "properties": {
                    "city": {"type": "string"}
                },
                "required": ["city"]
            }
        )
    ]

@app.call_tool()
async def call_tool(name: str, arguments: dict):
    if name == "get_weather":
        city = arguments["city"]
        # 调用天气 API
        result = await fetch_weather(city)
        return [TextContent(type="text", text=result)]

if __name__ == "__main__":
    app.run("stdio")

import { Server } from "@modelcontextprotocol/sdk/server/index.js";
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
import { CallToolRequestSchema, ListToolsRequestSchema } from "@modelcontextprotocol/sdk/types.js";

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

server.setRequestHandler(ListToolsRequestSchema, async () => ({
  tools: [{
    name: "get_weather",
    description: "Get current weather",
    inputSchema: { type: "object", properties: { city: { type: "string" } }, required: ["city"] }
  }]
}));

server.setRequestHandler(CallToolRequestSchema, async (request) => {
  if (request.params.name === "get_weather") {
    const result = await fetchWeather(request.params.arguments.city);
    return { content: [{ type: "text", text: result }] };
  }
  throw new Error("Unknown tool");
});

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

{
  "mcpServers": {
    "weather": {
      "command": "python",
      "args": ["/path/to/weather_server.py"],
      "env": {"WEATHER_API_KEY": "xxx"}
    },
    "github": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-github"],
      "env": {"GITHUB_TOKEN": "ghp_xxx"}
    }
  }
}

五、最佳实践

六、未来方向