Click on "Deploy 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 Server Generate 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.
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
┌─────────────────────┐
│ 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 │
└─────────────────────┘Related MCP server: Multi-MCP
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 |
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
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
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"
}claude_chat - 与 Claude 对话输入：
message (string): 用户消息
system_prompt (string): 系统提示词（可选）
# 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{
"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"
}
}
}
}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cd C:/skewliness/claude-mcp
pip install -r requirements.txtpython server.pyanthropic
python-dotenv
mcpAPI 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 deployed
Augments MCP Server - A comprehensive framework documentation provider for Claude Code
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
MCP server for building and testing AI agents with multi-model experimentation and insights.
MCP server for progressive tool usage at any scale (see https://klavis.ai)
