AI agents call cvat_get_job 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 operation against the CVAT API. It retrieves information about a specific job using its ID via an HTTP GET request. There are no modifications to data, no code execution, and no destructive or financial implications. The severity is low because retrieving job metadata poses minimal risk even if misused by an agent.
From the tool's definition Tool description states 'Get one CVAT job by id from GET /api/jobs/{id}' — a GET request that retrieves job data without modification or side effects.
Attacks that exploit this kind of access
Get one CVAT job by id from GET /api/jobs/{id}. 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_job: 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_job 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_job 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_job. 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_job 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 →