compare_profiles
AI agents call compare_profiles 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 tool appears to perform a comparative analysis of RawTherapee color profiles, which would retrieve and display profile data without side effects. The low confidence reflects the uninformative empty description, but the naming convention and sibling tools (analyze_image, apply_profile) suggest this is a read-only query or display operation.
From the tool's definition Tool name 'compare_profiles' suggests it retrieves and compares data without modification. The empty description limits confidence, but the name and context within a photo development server (alongside analysis and viewing tools) indicate a read/comparison…
Attacks that exploit this kind of access
compare_profiles. 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 compare_profiles: 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.
compare_profiles 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 compare_profiles 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 compare_profiles. 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.
compare_profiles 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 →