preview_before_after
AI agents call preview_before_after 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.
This tool appears to query or retrieve image data for comparison purposes without making changes. The primary function is to show visual feedback, which is consistent with the Read category (retrieves data; no side effects). Confidence is slightly reduced due to empty description, but the name and server context are clear. Severity is low since previewing images has minimal blast radius if misused by an AI agent.
From the tool's definition Tool name 'preview_before_after' indicates it displays or compares images before and after edits. The server context describes 'a visual feedback loop that allows the LLM to see and iteratively edit images,' which suggests this tool retrieves/visualizes image…
Attacks that exploit this kind of access
preview_before_after. 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_before_after: 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_before_after 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_before_after 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_before_after. 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_before_after 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 →