AI agents call plex_recently_added to retrieve information from Homelab without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata about recently added content in Plex media server. It has no side effects, makes no changes to the system, and poses no risk of data loss or unauthorized execution. The only potential concern is information disclosure if the Plex library contents are sensitive, but this is a negligible risk in a personal homelab context and does not elevate the severity beyond low.
From the tool's definition Tool name 'plex_recently_added' and description 'Show recently added movies and episodes in Plex' indicate a query operation that retrieves and displays data without modifying, deleting, or executing any actions.
Attacks that exploit this kind of access
Show recently added movies and episodes in Plex. It is categorised as a Read tool in the Homelab MCP Server, which means it retrieves data without modifying state.
Register the Homelab MCP server in PolicyLayer and add a rule for plex_recently_added: 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.
plex_recently_added 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 plex_recently_added 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 plex_recently_added. 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.
plex_recently_added 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 →