AI agents use export_images 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.
Exporting images creates new files on disk but does not modify or delete existing photos in the darktable library or original source files. The operation is reversible (exported files can be deleted), and the severity is medium because it could fill disk space or overwrite existing files if paths collide, but lacks the irreversibility of destructive operations or the financial impact of other categories.
From the tool's definition Tool description states 'Export photos to JPEG/PNG/TIFF via darktable-cli.' The action creates new image files in specified formats, which is a reversible data creation operation.
Attacks that exploit this kind of access
Export photos to JPEG/PNG/TIFF via darktable-cli. 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 export_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 Darktable. Nothing to install.
export_images 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 export_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.
Set action: deny in the PolicyLayer policy for export_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.
export_images 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 →