Zen MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PATH | No | System PATH for locating executables | /usr/local/bin:/usr/bin:/bin:/opt/homebrew/bin:~/.local/bin |
| LOG_LEVEL | No | Logging level for the server | INFO |
| XAI_API_KEY | No | API key for X.AI Grok models | |
| DIAL_API_KEY | No | API key for DIAL vendor-agnostic model access | |
| DEFAULT_MODEL | No | Default model to use (e.g., 'auto', 'pro') | auto |
| DISABLED_TOOLS | No | Comma-separated list of tools to disable to optimize context window usage | analyze,refactor,testgen,secaudit,docgen,tracer |
| GEMINI_API_KEY | No | API key for Google's Gemini models | |
| OPENAI_API_KEY | No | API key for OpenAI models (O3, GPT-5 series) | |
| OPENROUTER_API_KEY | No | API key for OpenRouter to access multiple models with one API | |
| AZURE_OPENAI_API_KEY | No | API key for Azure OpenAI enterprise deployments | |
| MAX_CONVERSATION_TURNS | No | Maximum number of conversation turns | 50 |
| CONVERSATION_TIMEOUT_HOURS | No | Timeout for conversations in hours | 6 |
| DEFAULT_THINKING_MODE_THINKDEEP | No | Default thinking mode for thinkdeep tool (e.g., 'high') |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |