| name | supervisely |
| description | A web-based computer vision platform that enables teams to annotate and manage datasets (images, video, 3D, medical), build and train neural networks, automate labeling with AI, and collaborate on model development and deployment at scale. Read and write Supervisely data through One: tasks, figures, filestorage, images, jobs, projects and more, 427 actions with real parameter documentation. Use whenever the user asks to look something up in Supervisely, create or update a record there, or build code against the Supervisely API. |
Supervisely through One
A web-based computer vision platform that enables teams to annotate and manage datasets (images, video, 3D, medical), build and train neural networks, automate labeling with AI, and collaborate on model development and deployment at scale.
One exposes Supervisely through four MCP tools. The table below carries real action ids from One's knowledge base, so for a common operation you can skip search and go straight to reading the action's parameters.
How to run an action
- Find the action in the table below, or call
search_one_platform_actions with platform supervisely if it is not listed.
- Call
get_one_action_knowledge with the action id. Do this every time, including for actions in this table. The table gives you the id, not the parameters.
- Call
execute_one_action with parameters copied from that knowledge.
Never guess a parameter name, a body field, or an enum value. The knowledge has the real schema, and a guessed field is either a 400 or a silent write of the wrong thing.
Before you start
Call list_one_integrations once and confirm Supervisely is connected. If it is missing, the user has not connected it: say so and point them at https://app.withone.ai rather than reaching for raw HTTP.
Each connection carries an access field. If it reports the agent is read-only here, so plan a read-only answer instead of attempting a write that will be refused.
