AI agents call tautulli_get_activity 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 queries and displays real-time activity data (who is watching, what content, player info, stream quality, progress) from Tautulli (a Plex monitoring service). It is a passive read operation with no side effects, no data modification, no execution of external commands, and no destructive capabilities. The blast radius of misuse is minimal — an AI could only expose information about current viewing activity.
From the tool's definition Tool name includes 'get_activity' and description states 'Show current Plex streams' — retrieves monitoring/status information about active streams without modifying any data.
Attacks that exploit this kind of access
Show current Plex streams via Tautulli: who is watching what, player, stream decision, and progress. 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 tautulli_get_activity: 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.
tautulli_get_activity 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 tautulli_get_activity 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 tautulli_get_activity. 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.
tautulli_get_activity 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 →