Zen
- javascript
1
GitHub Stars
javascript
Language
4 months ago
First Indexed
2 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
Installation
Add the following to your MCP client configuration file.
Configuration
View docs{
"mcpServers": {
"mcp-mirror-199-biotechnologies_mcp-zen-plus": {
"command": "npx",
"args": [
"zen-mcp-server-199bio"
],
"env": {
"GEMINI_API_KEY": "YOUR_GEMINI_API_KEY",
"OPENAI_API_KEY": "YOUR_OPENAI_API_KEY",
"OPENROUTER_API_KEY": "YOUR_OPENROUTER_API_KEY"
}
}
}
}You can run Zen MCP Server as an NPX wrapper to expose Claude Desktop to multiple AI models for enhanced development tasks. It provides quick access to Gemini, OpenAI, and OpenRouter models, enabling extended reasoning, code reviews, debugging, and collaborative development across AI perspectives without Docker or complex setup.
How to use
Use the server with your MCP client to access multiple AI models through a single entry point. The default tool set includes quick consultations, collaborative discussions, in-depth reasoning, code reviews, pre-commit checks, debugging assistance, and smart codebase analysis. The server maintains context across calls for smoother multi-turn conversations.
How to install
Prerequisites you need before starting include Node.js and npm (or npx), and at least one API key for Gemini, OpenAI, or OpenRouter. You will run an NPX command to start the MCP server, which automatically handles dependencies.
Step-by-step commands to get started:
# Ensure you have Node.js and npm installed
node -v
npm -v
# Start the Zen MCP Server via NPX
npx zen-mcp-server-199bio
Additional setup and configuration
On first run, you will configure API keys and environment settings. You will create an environment file and provide keys for the supported models. You can also integrate the MCP server with Claude Desktop by adding a configuration entry that points to the NPX command.
Example configuration for Claude Desktop integration is shown below. This config launches the NPX-based server and provides API keys for Gemini, OpenAI, and OpenRouter.
{
"mcpServers": {
"zen": {
"command": "npx",
"args": ["zen-mcp-server-199bio"],
"env": {
"GEMINI_API_KEY": "your_gemini_key_here",
"OPENAI_API_KEY": "your_openai_key_here",
"OPENROUTER_API_KEY": "your_openrouter_key_here"
}
}
}
}
Troubleshooting
If Python or other runtime issues arise, verify you have the required runtimes installed and that your API keys are valid. Common issues include missing API keys or invalid credentials for the supported models.
If a problem occurs with starting the server via NPX, ensure your environment variables are set correctly in your shell or in the Claude Desktop config snippet and try restarting the client.
Notes
This setup does not require Docker. It runs directly with Node.js and your API keys, minimizing container overhead while preserving rapid startup and flexible model access.
Available tools
zen
Default tool for quick AI consultation and chat with integrated MCP capabilities.
chat
Facilitates collaborative development discussions with the MCP-enabled AI.
thinkdeep
Extended reasoning mode powered by Gemini 2.0 Pro for deeper analysis.
codereview
Professional code review assistance with architectural insights.
precommit
Pre-commit validation helper to catch issues early.
debug
Advanced debugging assistance with specialized models.
analyze
Smart analysis of files and codebases to identify patterns and improvements.