Dual-Model MCP Server
An MCP server that orchestrates a dual-model workflow using Claude Opus for high-level code generation and Codex for automated code review and bug fixing. It provides tools for framework design, task classification, and quality assurance to optimize software development.
README
Dual-Model MCP Server
代码生成与质量保障系统:Claude Opus 4.6 生成代码,Codex 5.4 审查修复
工作流程
┌─────────────────────┐
│ Claude Opus 4.6 │
│ 写复杂代码 + 设计框架 │
└──────────┬──────────┘
│
│ 生成代码
▼
┌──────────┐
│ 完成代码 │
└──────┬───┘
│
│ 审查代码
▼
┌─────────────────────┐
│ Codex 5.4 │
│ 代码审查 + 修复 bug │
└─────────────────────┘
MCP 工具
| 工具 | 模型 | 说明 |
|---|---|---|
claude_codegen |
Claude Opus 4.6 | 生成代码和设计框架 |
codex_review |
Codex 5.4 | 审查代码并修复 bug |
classify_task |
- | 判断任务类型 |
claude_chat |
Claude Opus 4.6 | 与 Claude 对话 |
工具详情
1. claude_codegen - Claude Opus 4.6 生成代码
用途:复杂代码生成和框架设计
输入:
task(string): 任务描述context(string): 上下文信息language(string): 编程语言(默认 python)requirements(array): 额外需求列表
输出:生成的代码和说明
2. codex_review - Codex 5.4 审查代码
用途:代码审查和 bug 修复
输入:
code(string): 要审查的代码language(string): 编程语言(默认 python)focus(string): 审查重点(security/performance/bugs/all)
输出:审查结果和修复后的代码
3. classify_task - 判断任务类型
输出:
{
"type": "simple" | "complex",
"model": "glm-4.7" | "claude-opus-4-6",
"action": "use_local" | "use_claude",
"reason": "判断原因",
"confidence": "high" | "medium"
}
4. claude_chat - 与 Claude 对话
输入:
message(string): 用户消息system_prompt(string): 系统提示词(可选)
配置
环境变量 (.env)
# Claude API 配置
ANTHROPIC_API_KEY=sk-xxxxx
ANTHROPIC_BASE_URL=https://subrouter.ai
CLAUDE_MODEL=claude-opus-4-6
# Codex API 配置
CODEX_API_KEY=sk-xxxxx
CODEX_BASE_URL=https://subrouter.ai
CODEX_MODEL=codex-5.4
MCP 配置 (.mcp.json)
{
"mcpServers": {
"dual-model": {
"command": "python",
"args": ["-u", "C:/skewliness/claude-mcp/server.py"],
"cwd": "C:/skewliness/claude-mcp",
"env": {
"ANTHROPIC_API_KEY": "sk-xxxxx",
"CLAUDE_MODEL": "claude-opus-4-6",
"CODEX_API_KEY": "sk-xxxxx",
"CODEX_MODEL": "codex-5.4"
}
}
}
}
使用示例
完整工作流程
1. 用户请求:"实现一个用户认证系统"
↓
2. 调用 claude_codegen (Claude Opus 4.6)
↓
3. 生成代码:
- FastAPI 框架
- JWT 认证
- 密码加密
↓
4. 调用 codex_review (Codex 5.4)
↓
5. 审查并修复:
- 检查安全漏洞
- 修复 bug
- 性能优化
↓
6. 输出最终代码
安装
cd C:/skewliness/claude-mcp
pip install -r requirements.txt
启动
python server.py
依赖
anthropic
python-dotenv
mcp
注意事项
- API Key 安全:不要把
.env文件提交到 Git - 成本控制:Claude Opus 4.6 和 Codex 5.4 按使用量计费
- 网络要求:需要能访问 API 代理 (https://subrouter.ai/register?aff=dRgW)
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.