MCP是什么传统Function Calling是串行的模型 → 调1个工具 → 等结果 → 调下1个工具...串行MCP让模型一次性看到所有可用工具// 服务端暴露工具列表JSON Schema { tools: [ {name: filesystem_read, params: {path: string}}, {name: database_query, params: {sql: string}}, {name: github_pr, params: {title: string, body: string}} ] } // 客户端Claude Code、Cline、Continue.dev均支持MCPMonkeyCode集成MCP配置// ~/.monkeycode/mcp_servers.json { mcpServers: { filesystem: { command: npx, args: [-y, modelcontextprotocol/server-filesystem, /home/user/workspace], env: {} }, database: { command: npx, args: [-y, modelcontextprotocol/server-postgres], env: {DATABASE_URL: postgresql://user:pwdlocalhost:5432/db} }, github: { command: npx, args: [-y, modelcontextprotocol/server-github], env: {GITHUB_TOKEN: ghp_your_token} } } }# 在MonkeyCode中使用 from monkeycode import MonkeyCode mc MonkeyCode( modelminimax/m3, mcp_config~/.monkeycode/mcp_servers.json ) # 列出所有可用工具 print(mc.list_tools()) # 输出: [filesystem/read_file, database/query, github/create_pr, ...]Agent实战一条指令完成复杂任务场景修复Bug → 提交PR → 部署上线# 一条指令M3自动完成 # 1. 读取CI失败日志 # 2. 分析代码找Bug # 3. 自动修复 # 4. 写测试验证 # 5. 提交GitHub PR # 6. 合并后自动部署 result mc.execute( task修复CI失败的测试并在GitHub上创建PR然后部署到staging环境, context{ ci_log_url: https://github.com/org/repo/actions/runs/12345, deployment_target: staging }, modethinking ) print(result.chain) # [ # {step: 1, tool: filesystem/read_file, input: logs/ci.log, output: Test failed at test_auth.py:23}, # {step: 2, tool: analyze, input: ..., output: Fix: add token refresh logic}, # {step: 3, tool: filesystem/write_file, input: auth.py patch, output: OK}, # {step: 4, tool: execute, input: pytest, output: 3 tests passed}, # {step: 5, tool: github/create_pr, input: ..., output: PR #234 created}, # {step: 6, tool: deploy, input: ..., output: Deployed to staging ✅} # ]为什么M3适合做Agent特性重要性M3表现Tool调用准确性⭐⭐⭐⭐⭐✅ 在Claw-Eval获最高分长任务保持专注⭐⭐⭐⭐✅ 1M上下文中间结果不丢失多轮推理⭐⭐⭐⭐⭐✅ thinking模式支持执行效率⭐⭐⭐⭐✅ MSA架构推理快常用MCP工具组合场景MCP Server用途代码开发filesystem读写项目文件数据库postgres/mysql查询/执行SQLGit操作github创建PR、合并MR浏览器puppeteerWeb自动化测试API测试httpRESTful接口测试Dockerdocker容器编排部署// 添加更多MCP服务器 { mcpServers: { docker: { command: npx, args: [-y, modelcontextprotocol/server-docker] }, http: { command: npx, args: [-y, modelcontextprotocol/server-http] } } }M3的Tool Calling vs GPT/Claude指标M3GPT-5.5Claude 3.5Claw-Eval得分最高分82%79%Tool选择准确率94%91%93%参数填充正确率89%85%87%多Tool调用顺序✅✅⚠️Tool执行失败恢复✅⚠️⚠️