run_inference · Roboflow MCP Server MCP: Risk & Policy

WHAT IT DOES

What run_inference does on Roboflow MCP Server

AI agents invoke run_inference to trigger actions in Roboflow MCP Server. 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 run_inference needs a policy

This tool executes inference operations on computer vision models, which is a computational action with effects determined by the model and input data. While inference itself is typically read-only from the user's perspective, it triggers external ML model execution and could consume computational resources or return sensitive predictions depending on the model's purpose.

From the tool's definition Tool name 'run_inference' combined with server description stating it 'perform[s] inference directly from the CLI' indicates execution of model inference operations.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_inference Rate-limited

run_inference 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": {
    "run_inference": {
      "limits": [
        {
          "counter": "run_inference_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 Roboflow MCP Server, so you can run agents against it safely.

FAQ

Questions about run_inference

What does the run_inference tool do? +

run_inference. It is categorised as a Execute tool in the Roboflow MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_inference? +

Register the Roboflow MCP Server MCP server in PolicyLayer and add a rule for run_inference: 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 Roboflow MCP Server. Nothing to install.

What risk level is run_inference? +

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

Can I rate-limit run_inference? +

Yes. Add a rate_limit block to the run_inference 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 run_inference completely? +

Set action: deny in the PolicyLayer policy for run_inference. 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 run_inference? +

run_inference is provided by the Roboflow MCP Server MCP server (nickedridge-wq/roboflow-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.