ultralytics-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Capabilities
Features and capabilities supported by this server
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| projects_listC | List computer-vision projects in your Ultralytics workspace. |
| projects_getA | Get details for one project by id, slug, username/slug, or project ul:// URI. |
| projects_createC | Create a project in your Ultralytics workspace. |
| datasets_listC | List datasets in your Ultralytics workspace. |
| datasets_getA | Get details for one dataset by id, slug, username/slug, or dataset ul:// URI. |
| models_listA | List models in a project by project id, slug, username/slug, or project ul:// URI. |
| models_getA | Get one model by id, or by slug plus project. |
| gpu_availabilityB | Get current cloud-GPU stock status by GPU type. |
| training_monitorC | Report a model's training status and progress (works for private and public projects). |
| model_predictB | Run inference with a trained model on an image URL or base64 source (no local file paths). |
| model_downloadC | Download one trained model weight file to an explicit local path. |
| exports_listC | List export jobs for a model. |
| export_statusA | Get status for one export job by 24-character export id. |
| export_createA | Create a model export job (state-changing, may cost credits). Requires confirm_cost=true. |
| training_startC | Start a cloud training job (state-changing, may cost credits). Requires confirm_cost=true. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/amanharshx/ultralytics-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server