AI agents call cvat_get_request 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 performs a read-only query of background request status via a GET API endpoint. It retrieves information about previously initiated operations without creating, modifying, or deleting any data. The use case of checking import/export/upload status confirms it is purely informational. No side effects or modifications are possible.
From the tool's definition The tool description states it 'Get[s] a CVAT background request by id' using a GET endpoint, which is a retrieval operation.
Attacks that exploit this kind of access
Get a CVAT background request by id from GET /api/requests/{id}; useful after imports, exports, or data upload. 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_get_request: 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_get_request 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_get_request 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_get_request. 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_get_request 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 →