AI agents call cvat_list_labels to retrieve information from CVAT MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves label metadata from CVAT using filters (task_id, project_id, job_id, name, search, page_size). It has no side effects—it only queries and returns existing data. This is a classic Read operation with minimal risk; misuse would only expose label information the user might already have access to.
From the tool's definition Tool name 'cvat_list_labels' and description 'List labels with /api/labels filters' indicate a query/retrieval operation. No modification, deletion, or execution is described.
Attacks that exploit this kind of access
List labels with /api/labels filters such as task_id, project_id, job_id, name, search, and page_size. It is categorised as a Read tool in the CVAT MCP MCP Server, which means it retrieves data without modifying state.
Register the CVAT MCP server in PolicyLayer and add a rule for cvat_list_labels: 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_list_labels is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the cvat_list_labels 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_list_labels. 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_list_labels 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 →