AI agents use radarr_manual_import 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.
The tool scans a local folder and imports video files into Radarr's library—a modification operation that adds or updates records in the system. This is a Write-class action as it creates new entries in Radarr's database/collection. Severity is medium because misuse could clutter or pollute the media library with unwanted content, but the action is reversible (imports can typically be removed).
From the tool's definition Tool description states it will 'import' video files into Radarr, which creates or modifies state in the media management system. The action is reversible (files can be removed from the collection), distinguishing it from destructive operations.
Attacks that exploit this kind of access
Scan a local folder for video files and import them into Radarr. 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 radarr_manual_import: 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.
radarr_manual_import 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 radarr_manual_import 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 radarr_manual_import. 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.
radarr_manual_import 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 →