Dual-Model MCP Server
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Dual-Model MCP ServerGenerate a secure JWT auth system in Python and review it for bugs."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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 Opus 4.6 | 生成代码和设计框架 |
| Codex 5.4 | 审查代码并修复 bug |
| - | 判断任务类型 |
| 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-5.4MCP 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)
This server cannot be installed
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/skewliness/claude-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server