Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GEMINI_API_KEY | Yes | Gemini API Key required for model discovery and agent interaction. |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| read_code | Reads the content of a file. Supported extensions: .py, .ts, .tsx, .js, .json, .md. |
| write_code | Writes or overwrites content to a file. |
| run_terminal | Executes a shell command and returns stdout and stderr. Example: npm run dev, pytest, etc. |
| list_models_with_limits | Lists available Gemini models sorted by input token limit (context window). Provides a proxy for 'capacity' since exact quota is not available via API. |
| notify_dev | Sends a desktop notification. Supports Linux (notify-send). |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |