cvat_api_request · CVAT MCP: Risk & Policy

WHAT IT DOES

What cvat_api_request does on CVAT MCP

AI agents invoke cvat_api_request to trigger actions in CVAT MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why cvat_api_request needs a policy

This tool is a general-purpose API proxy that can invoke any CVAT REST endpoint, including destructive DELETE operations, data-modifying POST/PATCH/PUT operations, and arbitrary executions. Because it spans multiple categories (Read through Destructive), the most severe applicable category is chosen.

From the tool's definition 'Call any official CVAT REST endpoint under /api/. For POST, PATCH, PUT, or DELETE, confirmMutation must be true.'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

cvat_api_request Rate-limited

cvat_api_request stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "cvat_api_request": {
      "limits": [
        {
          "counter": "cvat_api_request_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches CVAT MCP, so you can run agents against it safely.

FAQ

Questions about cvat_api_request

What does the cvat_api_request tool do? +

Call any official CVAT REST endpoint under /api/. For POST, PATCH, PUT, or DELETE, confirmMutation must be true. It is categorised as a Execute tool in the CVAT MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on cvat_api_request? +

Register the CVAT MCP server in PolicyLayer and add a rule for cvat_api_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.

What risk level is cvat_api_request? +

cvat_api_request is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit cvat_api_request? +

Yes. Add a rate_limit block to the cvat_api_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.

How do I block cvat_api_request completely? +

Set action: deny in the PolicyLayer policy for cvat_api_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.

What MCP server provides cvat_api_request? +

cvat_api_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.