AI agents use cvat_create_task to create or update resources in CVAT MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your CVAT MCP environment.
This tool creates a new annotation task resource in CVAT via a POST API call. Creating a task is a Write operation—it modifies the system state by adding a new entity, but the action is reversible (tasks can be deleted or updated).
From the tool's definition Tool description states "Create a CVAT task using POST /api/tasks". POST operation creates new data (a task) that is reversible through deletion or modification. The tool does not execute arbitrary code, delete data irreversibly, or move money.
Attacks that exploit this kind of access
Create a CVAT task using POST /api/tasks. Use cvat_attach_task_data afterward to upload images or videos. It is categorised as a Write tool in the CVAT MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the CVAT MCP server in PolicyLayer and add a rule for cvat_create_task: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches CVAT MCP. Nothing to install.
cvat_create_task is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the cvat_create_task rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for cvat_create_task. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
cvat_create_task is provided by the CVAT MCP server (jangjs1216/cvat-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →