AI agents use immich_activities_create 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.
This tool creates new metadata (comments and likes) on photos/albums. While it modifies state, these additions are reversible through deletion or editing. This is a classic Write operation—non-destructive data creation with no financial impact or code execution.
From the tool's definition Tool performs 'Add a comment or like' which creates new data (comments/likes) that are reversible and can be edited or deleted.
Attacks that exploit this kind of access
Add a comment or like to an album or specific asset within an album. 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_activities_create: 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_activities_create 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_activities_create 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_activities_create. 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_activities_create 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 →