AI agents call get_collection_items to retrieve information from Mcp Plex without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves collection metadata and membership without side effects. It is purely informational, similar to other Read operations on this server like get_libraries, get_episodes, and get_library_contents. No data is created, modified, deleted, or executed. Severity is low because misuse would only expose existing media information the user has access to.
From the tool's definition Tool name and description indicate retrieval operation: 'Get the items in a Plex collection with full collection details' — a query/fetch action with no modification or deletion.
Attacks that exploit this kind of access
Get the items in a Plex collection with full collection details. It is categorised as a Read tool in the Mcp Plex MCP Server, which means it retrieves data without modifying state.
Register the Mcp Plex MCP server in PolicyLayer and add a rule for get_collection_items: 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 Mcp Plex. Nothing to install.
get_collection_items 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_collection_items 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_collection_items. 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_collection_items is provided by the Mcp Plex MCP server (obrien-matthew/mcp-plex). 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 →