Zen MCP server

µ-MCP Server is a minimalist implementation of the Model Context Protocol (MCP) that enables chat with AI models via OpenRouter. It follows UNIX principles, doing one thing well by providing clean access to AI models while maintaining persistent conversations and supporting model switching.

Installation

Quick Install (with uv)

1. Get an OpenRouter API key

   First, obtain your API key from OpenRouter.

2. Run the setup script

   ./setup.sh
   

   This script:

   • Installs uv if it's not already present
   • Installs the required dependencies
   • Shows instructions for Claude Desktop configuration

3. Configure Claude Desktop

   Add the following to your Claude Desktop config file (~/.config/claude/claude_desktop_config.json):

   {
     "mcpServers": {
       "mu-mcp": {
         "command": "uv",
         "args": ["--directory", "/path/to/mu-mcp", "run", "python", "/path/to/mu-mcp/server.py"],
         "env": {
           "OPENROUTER_API_KEY": "your-key-here"
         }
       }
     }
   }
   

   Replace /path/to/mu-mcp with the actual path to your μ-MCP installation directory and your-key-here with your OpenRouter API key.

4. Restart Claude Desktop

Manual Install (traditional)

If you prefer using pip and virtual environments:

python3 -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate
pip install -r requirements.txt

Then use this Claude Desktop config:

{
  "mcpServers": {
    "mu-mcp": {
      "command": "/path/to/mu-mcp/venv/bin/python",
      "args": ["/path/to/mu-mcp/server.py"],
      "env": {
        "OPENROUTER_API_KEY": "your-key-here"
      }
    }
  }
}

Usage

Basic Chat

To start a basic chat with a specific model:

/mu:chat
Then specify model and prompt: "Use gpt-5 to explain quantum computing"

Continue Conversations

To continue previous conversations across sessions:

/mu:continue

This preserves full context even after Claude's memory is compacted. When Claude's context gets compacted or you need to switch between tasks, this command allows Claude to see all your recent conversations (with titles, timestamps, and models used) and seamlessly resume where you left off.

Challenge Mode

To encourage critical thinking:

/mu:challenge

This mode avoids reflexive agreement from the AI.

Multi-AI Discussion

To orchestrate discussions between different AI models:

/mu:discuss

Model Selection

You can specify different models for different tasks:

Chat with GPT-5 about code optimization
Chat with O3 Mini High for complex reasoning
Chat with DeepSeek R1 for systematic analysis  
Chat with Claude about API design

Reasoning Effort Control

Control the reasoning effort for different tasks:

Chat with o3-mini using high reasoning effort for complex problems
Chat with gpt-5 using low reasoning effort for quick responses
Chat with o4-mini-high using medium reasoning effort for balanced analysis

Note: Reasoning effort is automatically ignored by models that don't support it.

Working with Files and Images

You can include files and images in your conversations:

Review this code: /path/to/file.py
Analyze this diagram: /path/to/image.png

Automatic Model Selection

The calling LLM agent (Claude) can intelligently select from available models based on:

• Task requirements and complexity
• Performance vs cost trade-offs
• Specific model strengths
• Context window needs
• Image support requirements

Configuration

Environment Variables

Configure μ-MCP using the following environment variables:

• OPENROUTER_API_KEY - Your OpenRouter API key (required)
• OPENROUTER_ALLOWED_MODELS - Comma-separated list of allowed models (optional)
• LOG_LEVEL - Logging verbosity (DEBUG, INFO, WARNING, ERROR)

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "zen" '{"command":"bash","args":["-c","for p in $(which uvx 2>/dev/null) $HOME/.local/bin/uvx /opt/homebrew/bin/uvx /usr/local/bin/uvx uvx; do [ -x \"$p\" ] && exec \"$p\" --from git+https://github.com/BeehiveInnovations/zen-mcp-server.git zen-mcp-server; done; echo 'uvx not found' >&2; exit 1"],"env":{"PATH":"/usr/local/bin:/usr/bin:/bin:/opt/homebrew/bin:~/.local/bin","GEMINI_API_KEY":"your-key-here","DISABLED_TOOLS":"analyze,refactor,testgen,secaudit,docgen,tracer","DEFAULT_MODEL":"auto"}}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "zen": {
            "command": "bash",
            "args": [
                "-c",
                "for p in $(which uvx 2>/dev/null) $HOME/.local/bin/uvx /opt/homebrew/bin/uvx /usr/local/bin/uvx uvx; do [ -x \"$p\" ] && exec \"$p\" --from git+https://github.com/BeehiveInnovations/zen-mcp-server.git zen-mcp-server; done; echo 'uvx not found' >&2; exit 1"
            ],
            "env": {
                "PATH": "/usr/local/bin:/usr/bin:/bin:/opt/homebrew/bin:~/.local/bin",
                "GEMINI_API_KEY": "your-key-here",
                "DISABLED_TOOLS": "analyze,refactor,testgen,secaudit,docgen,tracer",
                "DEFAULT_MODEL": "auto"
            }
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "zen": {
            "command": "bash",
            "args": [
                "-c",
                "for p in $(which uvx 2>/dev/null) $HOME/.local/bin/uvx /opt/homebrew/bin/uvx /usr/local/bin/uvx uvx; do [ -x \"$p\" ] && exec \"$p\" --from git+https://github.com/BeehiveInnovations/zen-mcp-server.git zen-mcp-server; done; echo 'uvx not found' >&2; exit 1"
            ],
            "env": {
                "PATH": "/usr/local/bin:/usr/bin:/bin:/opt/homebrew/bin:~/.local/bin",
                "GEMINI_API_KEY": "your-key-here",
                "DISABLED_TOOLS": "analyze,refactor,testgen,secaudit,docgen,tracer",
                "DEFAULT_MODEL": "auto"
            }
        }
    }
}

3. Restart Claude Desktop for the changes to take effect