AI agents use rate_photos 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.
This tool modifies photo metadata (ratings) which is a Write operation—it creates or updates data reversibly. A star rating can be changed or removed without data loss. The severity is medium because misuse could alter the user's carefully organized photo ratings across their collection, requiring manual correction, but the operation is reversible and does not delete or destroy content.
From the tool's definition Tool applies a star rating to one or more photos, modifying metadata attributes in the user's photo collection. The description states 'Apply a star rating to one or more photos' which is a reversible modification operation.
Attacks that exploit this kind of access
Apply a star rating to one or more photos in the user. 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.
Register the Darktable MCP server in PolicyLayer and add a rule for rate_photos: 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.
rate_photos is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the rate_photos 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 rate_photos. 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.
rate_photos 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.
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 →