AI agents use immich_people_merge to create or update resources in Immich — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Immich environment.
The tool modifies existing data (merging person clusters) in a reversible manner—the merge operation could be undone by splitting clusters again or through other administrative actions. This is not a Read operation (it changes state), not Execute (no arbitrary code or external operations), not Destructive (the data is preserved, just reorganized), and not Financial. Therefore it is Write.
From the tool's definition Tool description states 'Merge two person clusters into one. The source person will be merged into the target.' This is a data modification operation that combines two entities.
Attacks that exploit this kind of access
Merge two person clusters into one. The source person will be merged into the target. It is categorised as a Write tool in the Immich MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Immich MCP server in PolicyLayer and add a rule for immich_people_merge: 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 Immich. Nothing to install.
immich_people_merge 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 immich_people_merge 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 immich_people_merge. 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.
immich_people_merge is provided by the Immich MCP server (whitehara/immich-mcp). 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 →