Create and persist a custom device/format preset for cropping and resizing.
AI agents use add_device_preset_tool to create or update resources in Rawtherapee — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Rawtherapee environment.
This tool creates new presets (reversible writes) and stores them persistently. It does not delete data (Destructive), execute code (Execute), handle money (Financial), or merely read data (Read).
From the tool's definition Tool creates and persists a custom device/format preset. The words 'Create and persist' indicate data is being written and stored. This modifies configuration state rather than performing destructive operations or executing arbitrary commands.
Attacks that exploit this kind of access
Create and persist a custom device/format preset for cropping and resizing. It is categorised as a Write tool in the Rawtherapee MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Rawtherapee MCP server in PolicyLayer and add a rule for add_device_preset_tool: 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 Rawtherapee. Nothing to install.
add_device_preset_tool 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 add_device_preset_tool 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 add_device_preset_tool. 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.
add_device_preset_tool is provided by the Rawtherapee MCP server (lucamarien/rawtherapee-mcp-server). 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 →