Scan a directory for supported RAW image files.
AI agents call list_raw_files 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 performs a non-destructive read operation—it scans and lists files in a directory. There are no side effects, no data modification, no command execution, and no financial impact. It is purely informational retrieval of file system metadata. The low severity reflects minimal risk even if an agent misuses it, as the worst outcome is listing files the user owns.
From the tool's definition Tool name 'list_raw_files' and description 'Scan a directory for supported RAW image files' indicate a directory query operation that retrieves file metadata without modification or deletion.
Attacks that exploit this kind of access
Scan a directory for supported RAW image files. 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 list_raw_files: 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.
list_raw_files 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 list_raw_files 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 list_raw_files. 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.
list_raw_files 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 →