analyze_image
AI agents call analyze_image 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 analyzes image data and returns information for visual feedback in the editing loop, with no modification of the underlying image or irreversible operations. This is a retrieval/inspection operation typical of Read category. Confidence is slightly reduced due to missing description, but the naming pattern and server architecture strongly indicate read-only behavior.
From the tool's definition Tool name 'analyze_image' and server context indicate image inspection/analysis. Description is empty, but the function name and sibling tools (e.g., 'adjust_*', 'apply_*') that modify state suggest this tool performs querying without side effects.
Attacks that exploit this kind of access
analyze_image. 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 analyze_image: 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.
analyze_image 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 analyze_image 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 analyze_image. 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.
analyze_image 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 →