AI agents use seerr_approve_request to create or update resources in Homelab — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Homelab environment.
This tool modifies data by approving (transitioning state of) a pending request, which is a reversible change. It does not execute arbitrary commands, delete data irreversibly, or move money. While it could trigger downstream media downloads/processing, the tool itself performs a state-change write operation on a request object.
From the tool's definition Tool name 'seerr_approve_request' and description 'Approve a pending media request in Seerr' indicate a modification action that creates or changes state in the Seerr media request system.
Attacks that exploit this kind of access
Approve a pending media request in Seerr. It is categorised as a Write tool in the Homelab MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Homelab MCP server in PolicyLayer and add a rule for seerr_approve_request: 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 Homelab. Nothing to install.
seerr_approve_request 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 seerr_approve_request 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 seerr_approve_request. 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.
seerr_approve_request is provided by the Homelab MCP server (nainounen/homelab-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 →