面向CLI智能代理的统一MCP（模型上下文协议）服务器。提供单一界面调用Codex、Gemini、Claude、OpenCode CLI工具和Nano Banana Pro图像生成。
概览
面向CLI智能代理的统一MCP（模型上下文协议）服务器。提供单一界面调用Codex、Gemini、Claude、OpenCode CLI工具和Nano Banana Pro图像生成。 这不仅仅是一个CLI封装器——它是多模型协作的工具。 让克洛德来安排。描述你想要什么，它会把你模糊的想法分解成适合合适的代理人的具体任务。委托的行为迫使你清晰。 每个模型都带来了独特的视角：- ：批评者。它的分析眼光捕捉你忽略的部分，挑战假设，发现边缘案例。- ：创造力。发散思维，意想不到的联系，你未曾意识到需要的火花。- ：书写员。忠实执行，清晰的文档，将想法转化为可操作的代码。- ：艺术家。为UI模型、产品视觉和创意资产提供高保真图像生成。 利用handoff_file捕捉代理输出，然后让Claude综合多项分析的洞察。
概述（AI 翻译）
中文文档
面向CLI智能代理的统一MCP（模型上下文协议）服务器。提供单一界面调用Codex、Gemini、Claude、OpenCode CLI工具和Nano Banana Pro图像生成。
为什么是cli-agent-mcp？
这不仅仅是一个CLI封装器——它是一种多模型协作的编排模式。
**无法清晰表达你的需求？**让克劳德来安排。描述你想要什么，它会把你模糊的想法分解成具体任务，交给合适的代理人。委托的行为迫使你清晰。
规划宏大的产品愿景？ 每个模型都带来了独特的视角：
- Codex：批评家。它的分析眼光捕捉你忽略的部分，挑战假设，发现边缘案例。
- 双子座：创造力。发散思维，意想不到的联系，你未曾意识到需要的火花。
- Claude：抄写员。忠实执行，清晰的文档，将想法转化为可行代码。
- 香蕉：艺术家。为用户界面模型、产品视觉和创意素材提供高保真图像生成。
想要持久结果？ 使用 handoff_file 捕捉代理输出，然后让 Claude 综合多项分析的洞见。
本页由 AI 翻译，技术细节请以原文为准。
README
以下为原文 README 节选，完整内容请查看原文。
cli-agent-mcp
Unified MCP (Model Context Protocol) server for CLI AI agents. Provides a single interface to invoke Codex, Gemini, Claude, OpenCode CLI tools, and Nano Banana Pro image generation.
Why cli-agent-mcp?
This is more than a CLI wrapper — it’s an orchestration pattern for multi-model collaboration.
Can’t articulate your requirements clearly? Let Claude orchestrate. Describe what you want, and it will decompose your vague idea into concrete tasks for the right agent. The act of delegation forces clarity.
Planning a grand product vision? Each model brings a unique lens:
- Codex: The critic. Its analytical eye catches what you missed, challenges assumptions, finds edge cases.
- Gemini: The creative. Divergent thinking, unexpected connections, the spark you didn’t know you needed.
- Claude: The scribe. Faithful execution, clear documentation, turning ideas into working code.
- Banana: The artist. High-fidelity image generation for UI mockups, product visuals, and creative assets.
Want persistent results? Use handoff_file to capture agent outputs, then let Claude synthesize insights across multiple analyses.
We don’t just wrap CLIs — we provide a thinking framework for human-AI collaboration.
Features
- Unified Interface: Single MCP server exposing multiple CLI agents
- GUI Dashboard: Real-time task monitoring with pywebview
- Request Isolation: Per-request execution context for safe concurrent usage
- Signal Handling: Graceful cancellation via SIGINT without killing the server
- Debug Logging: Comprehensive subprocess output capture for debugging
Screenshot
Installation
# Install from PyPI (when published)
uvx cli-agent-mcp
# Install from GitHub
uvx --from git+https://github.com/shiharuharu/cli-agent-mcp.git cli-agent-mcp
# Install from source (editable mode for development)
uvx --from /path/to/cli-agent-mcp cli-agent-mcp
# Or use pip
pip install -e .
Configuration
Configure via environment variables:
| Variable | Description | Default |
|---|---|---|
CAM_ENABLE |
Comma-separated list of enabled tools (empty = all) | "" (all) |
CAM_DISABLE |
Comma-separated list of disabled tools (subtracted from enable) | "" |
CAM_GUI |
Enable GUI dashboard | true |
CAM_GUI_DETAIL |
GUI detail mode | false |
CAM_GUI_KEEP |
Keep GUI on exit | false |
CAM_GUI_HOST |
GUI bind host | 127.0.0.1 |
CAM_GUI_PORT |
GUI bind port (set a fixed port to keep URL stable across restarts) | 0 (random) |
CAM_DEBUG |
Include debug info in MCP responses | false |
CAM_LOG_DEBUG |
Write debug logs to temp file | false |
CAM_SIGINT_MODE |
SIGINT handling (cancel/exit/cancel_then_exit) |
cancel |
CAM_SIGINT_DOUBLE_TAP_WINDOW |
Double-tap exit window (seconds) | 1.0 |
Tools
codex
安装
uvx cli-agent-mcp配置
{
"mcpServers": {
"cli-agent-mcp": {
"command": "uvx",
"args": ["cli-agent-mcp"]
}
}
}