AI agents use apply_preset 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 is a Write operation because it modifies data (applies edits/presets to photos) in a reversible manner. Users can undo the preset application or apply a different preset. It does not delete data (not Destructive), execute arbitrary code (not Execute), involve financial transactions (not Financial), or merely retrieve data (not Read).
From the tool's definition The tool 'apply_preset' applies a darktable style (preset) to one or more photos. This modifies photo metadata and editing state within darktable, creating reversible changes to the photos' processing parameters.
Attacks that exploit this kind of access
Apply a darktable style (preset) to one or more photos. The. 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 apply_preset: 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.
apply_preset 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 apply_preset 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 apply_preset. 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.
apply_preset 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 →