AI agents use immich_assets_upload 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.
Upload operations are Write category—they create or add new data reversibly. Severity is high because uploading to a photo management system could introduce large volumes of data, consume storage, or potentially introduce malicious files if not validated server-side. However, this is not Destructive (reversible) or Financial.
From the tool's definition Tool name 'immich_assets_upload' indicates file upload functionality. Server context describes 'managing photo libraries' and the tool appears among asset and album management operations. Upload operations create or add new data to the photo library.
Attacks that exploit this kind of access
immich_assets_upload. 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_assets_upload: 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_assets_upload 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_assets_upload 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_assets_upload. 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_assets_upload 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 →