AI agents call get_recently_added to retrieve information from PlexMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name indicates a retrieval operation ('get') on historical media additions. This is a non-destructive query operation that only fetches data about recently added items to the media library. No data modification, deletion, or external execution is implied. The low severity reflects minimal risk from misuse—returning library data poses no direct harm.
From the tool's definition Tool name 'get_recently_added' indicates retrieval of recently added media items from Plex library without modification. Empty description limits direct evidence but name strongly implies query/read operation.
Attacks that exploit this kind of access
get_recently_added. It is categorised as a Read tool in the PlexMCP MCP Server, which means it retrieves data without modifying state.
Register the Plex MCP server in PolicyLayer and add a rule for get_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 PlexMCP. Nothing to install.
get_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 get_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 get_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.
get_recently_added is provided by the Plex MCP server (sandraschi/plexmcp). 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 →