AI agents use import_from_camera 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.
Importing creates new records in the photo library and persists them to disk. This is a Write operation because it creates new data structures (image metadata, thumbnails, library entries) in a reversible manner—the imported images can later be removed from the library or deleted. It is not Destructive because no existing data is irreversibly deleted or overwritten.
From the tool's definition Tool named 'import_from_camera' with description 'Use when a camera or memory card is physically connected' indicates it imports/ingests media files from an external source into darktable's managed collection.
Attacks that exploit this kind of access
Use when a camera or memory card is physically connected. 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 import_from_camera: 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.
import_from_camera 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 import_from_camera 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 import_from_camera. 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.
import_from_camera 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 →