Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OLLAMA_HOST | No | Custom Ollama API endpoint | http://127.0.0.1:11434 |
Schema
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list | List all models in Ollama |
| show | Show information for a model |
| create | Create a model from a base model (remote only, no Modelfile support) |
| pull | Pull a model from a registry |
| push | Push a model to a registry |
| cp | Copy a model |
| rm | Remove a model |
| run | Run a model with a prompt. Optionally accepts an image file path for vision/multimodal models and a temperature parameter. |
| chat_completion | OpenAI-compatible chat completion API. Supports optional images per message for vision/multimodal models. |