AI agents call immich_search_explore to retrieve information from Immich without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves aggregated discovery information (places, people, things) from the photo library. It performs no writes, deletions, code execution, or financial operations. The verb 'Get' and the phrase 'discovery data' indicate a read-only operation with no side effects on the underlying photo library.
From the tool's definition Tool description states 'Get discovery data: popular places, recognized people, and notable things in your library' — purely retrieves and queries existing metadata without modification or deletion.
Attacks that exploit this kind of access
Get discovery data: popular places, recognized people, and notable things in your library. It is categorised as a Read tool in the Immich MCP Server, which means it retrieves data without modifying state.
Register the Immich MCP server in PolicyLayer and add a rule for immich_search_explore: 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_search_explore 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 immich_search_explore 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_search_explore. 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_search_explore 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 →