AI agents call immich_capabilities 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 is a read-only information discovery tool. It queries the server to return available features and capabilities—similar to a 'get features' or 'list capabilities' endpoint. There are no side effects, no data modification, no code execution beyond information retrieval, and no destructive operations. The blast radius of misuse is minimal; an agent could only learn what the server supports.
From the tool's definition Tool name 'immich_capabilities' and description 'Discover Immich server features and supported API capabilities' indicate this retrieves or queries information about server features and capabilities without modifying any data.
Attacks that exploit this kind of access
Discover Immich server features and supported API capabilities. 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_capabilities: 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_capabilities 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_capabilities 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_capabilities. 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_capabilities 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 →