inspect_metadata
AI agents call inspect_metadata 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.
Metadata inspection is a retrieval operation with no side effects on the image or filesystem. Within the context of a RAW photo development tool, this retrieves information about photos without modifying them. Confidence is slightly reduced due to empty description, but the name is clear enough to classify with reasonable confidence.
From the tool's definition Tool name 'inspect_metadata' indicates querying/retrieving metadata from images; no description provided, but the name strongly suggests read-only introspection of photo metadata
Attacks that exploit this kind of access
inspect_metadata. 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 inspect_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.
inspect_metadata 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 inspect_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 inspect_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.
inspect_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 →