preview_lut
AI agents call preview_lut 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 'preview' prefix and LUT context indicate this tool displays a visual representation of a color lookup table's effect, which is a read-only operation. No modification, deletion, or execution of arbitrary commands occurs. The empty description lowers confidence slightly, but the naming convention and sibling tools (apply_lut, which is Write) strongly suggest preview_lut is the non-destructive Read variant.
From the tool's definition Tool name 'preview_lut' with empty description suggests a preview/visualization function. LUT (Look-Up Table) preview would retrieve or display color grading data without modifying the underlying image file.
Attacks that exploit this kind of access
preview_lut. 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: 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 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 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. 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 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 →