label_images · SensorMCP Server MCP: Risk & Policy

WHAT IT DOES

What label_images does on SensorMCP Server

AI agents invoke label_images to trigger actions in SensorMCP 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 label_images needs a policy

This tool executes an ML model pipeline over images and saves the resulting label files. It involves both running external model inference (Execute) and writing output files (Write). Since it triggers an external computation process whose effects depend on the base model and image inputs, Execute is the most appropriate category, ranked above Write.

From the tool's definition 'Run the base model over RAW_IMAGES_DIR and save labels' — triggers execution of a foundation model (GroundedSAM) over a directory of images and writes output label files

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

label_images Rate-limited

label_images 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": {
    "label_images": {
      "limits": [
        {
          "counter": "label_images_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 SensorMCP Server, so you can run agents against it safely.

FAQ

Questions about label_images

What does the label_images tool do? +

Run the base model over RAW_IMAGES_DIR and save labels. It is categorised as a Execute tool in the SensorMCP 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 label_images? +

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

What risk level is label_images? +

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

Can I rate-limit label_images? +

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

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

label_images is provided by the SensorMCP Server MCP server (sensormcp/sensor-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.