AI agents call list_category to retrieve information from Qdrant without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a pure read operation that retrieves information about existing categories without modifying, deleting, or executing any code. The blast radius of misuse is minimal—an agent could learn what categories exist but cannot alter data or trigger external operations.
From the tool's definition Tool description states 'List existing categories in the configured collection' — a retrieval operation with no side effects that queries and returns metadata about categories.
Attacks that exploit this kind of access
List existing categories in the configured collection. It is categorised as a Read tool in the Qdrant MCP Server, which means it retrieves data without modifying state.
Register the Qdrant MCP server in PolicyLayer and add a rule for list_category: 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 Qdrant. Nothing to install.
list_category 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 list_category 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 list_category. 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.
list_category is provided by the Qdrant MCP server (msstnk/qdrant-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 →