AI agents use add_to_collection to create or update resources in Mcp Plex — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Plex environment.
This tool modifies existing collections by adding items to them. It creates a relationship between items and collections but does not delete data, execute code, or cause financial impact. The operation is reversible (items can be removed later). This is a straightforward Write category action with low blast radius—accidental misuse would simply add unwanted items to a collection, which can be undone.
From the tool's definition Tool name 'add_to_collection' and description 'Add items to a regular (non-smart) collection' indicate modification of collection membership, which is a reversible write operation.
Attacks that exploit this kind of access
Add items to a regular (non-smart) collection. It is categorised as a Write tool in the Mcp Plex MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Plex MCP server in PolicyLayer and add a rule for add_to_collection: 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.
add_to_collection 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 add_to_collection 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 add_to_collection. 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.
add_to_collection 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 →