preview_lut_comparison
AI agents call preview_lut_comparison to retrieve information from Rawtherapee without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The name suggests a preview/comparison operation, which is typically a read-only action for visual feedback. However, the empty description lowers confidence significantly. In the context of this RAW photo development server, previewing a LUT comparison likely renders or displays a comparison image without modifying the source files.
From the tool's definition Tool name 'preview_lut_comparison' suggests viewing/comparing LUT (Look-Up Table) effects, which is a read/display operation. Description is empty.
Attacks that exploit this kind of access
preview_lut_comparison. It is categorised as a Read tool in the Rawtherapee MCP Server, which means it retrieves data without modifying state.
Register the Rawtherapee MCP server in PolicyLayer and add a rule for preview_lut_comparison: 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.
preview_lut_comparison is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the preview_lut_comparison 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 preview_lut_comparison. 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.
preview_lut_comparison 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 →