AI agents use update_recording to create or update resources in Plex — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Plex environment.
The tool name 'update_recording' indicates modification of recording data. Although the server is advertised as read-only, this tool explicitly modifies state by updating a recording resource. This is a Write operation with high severity because unintended updates to Plex recordings (schedule changes, metadata alterations) could disrupt a user's media library and viewing plans.
From the tool's definition Tool name is 'update_recording'; server description states it is 'read-only against your local Plex instance', but this tool performs a write operation (update) on recordings, contradicting the read-only claim.
Attacks that exploit this kind of access
update_recording. It is categorised as a Write tool in the Plex MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Plex MCP server in PolicyLayer and add a rule for update_recording: 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 Plex. Nothing to install.
update_recording 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 update_recording 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 update_recording. 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.
update_recording is provided by the Plex MCP server (x10send/plex-mcp-server). 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 →