set_metadata
AI agents use set_metadata to create or update resources in Rawtherapee — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Rawtherapee environment.
Setting metadata on image files is a reversible write operation—it modifies file attributes without destructively deleting data or executing arbitrary code. Severity is medium because metadata changes can affect image organization, copyright info, or processing parameters, but they are not irreversible deletions and typically do not pose immediate security risk unless metadata is used for sensitive purposes (e.g.,…
From the tool's definition Tool name 'set_metadata' indicates modification of image metadata. Context of RawTherapee (RAW photo development tool) confirms this writes metadata to image files. Description is empty, limiting certainty.
Attacks that exploit this kind of access
set_metadata. It is categorised as a Write tool in the Rawtherapee MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Rawtherapee MCP server in PolicyLayer and add a rule for set_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.
set_metadata is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the set_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 set_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.
set_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 →