strip_metadata
AI agents call strip_metadata to permanently remove resources in Rawtherapee — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The name strongly implies permanently removing metadata (EXIF, IPTC, XMP, etc.) from photo files, which is an irreversible destructive operation. However, the description is empty, lowering confidence. It is possible this only modifies a processing profile rather than the actual file, but the most severe plausible interpretation is chosen.
From the tool's definition Tool name 'strip_metadata' — 'strip' implies irreversible removal of metadata from image files.
Attacks that exploit this kind of access
strip_metadata. It is categorised as a Destructive tool in the Rawtherapee MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Rawtherapee MCP server in PolicyLayer and add a rule for strip_metadata: 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.
strip_metadata is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the strip_metadata 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 strip_metadata. 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.
strip_metadata 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 →