apply_ratings_batch · Darktable MCP: Risk & Policy

WHAT IT DOES

What apply_ratings_batch does on Darktable

AI agents use apply_ratings_batch to create or update resources in Darktable — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Darktable environment.

WHY IT NEEDS A POLICY

Why apply_ratings_batch needs a policy

The tool creates or modifies metadata files (XMP sidecars) associated with images, which is a reversible write operation. While it affects multiple files in batch, the changes are metadata-only and can be undone (ratings can be modified or removed). This is less severe than destructive operations but more impactful than simple reads due to batch scope and file modification.

From the tool's definition The tool writes XMP sidecars containing rating metadata (xmp:Rating) for a batch of photos. This is a create/modify operation that persists data to files.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

apply_ratings_batch Rate-limited

apply_ratings_batch stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "apply_ratings_batch": {
      "limits": [
        {
          "counter": "apply_ratings_batch_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about apply_ratings_batch

What does the apply_ratings_batch tool do? +

Write XMP sidecars (xmp:Rating) for a batch of. It is categorised as a Write tool in the Darktable MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on apply_ratings_batch? +

Register the Darktable MCP server in PolicyLayer and add a rule for apply_ratings_batch: 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 Darktable. Nothing to install.

What risk level is apply_ratings_batch? +

apply_ratings_batch is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit apply_ratings_batch? +

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

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

apply_ratings_batch is provided by the Darktable MCP server (w1ne/darktable-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.