Search collection with filter
AI agents call filter_search to retrieve information from Qdrant MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Search operations retrieve and query data without modifying state. Even with filtering capabilities, the tool does not create, modify, delete, or execute arbitrary code—it only queries the vector database. Low severity because misuse would at worst retrieve unintended data, but cannot cause data loss or execute external operations.
From the tool's definition Tool is named 'filter_search' and described as 'Search collection with filter'. It performs a search operation on a vector database collection, which is a retrieval operation with no side effects.
Attacks that exploit this kind of access
Search collection with filter. It is categorised as a Read tool in the Qdrant MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Qdrant MCP Server MCP server in PolicyLayer and add a rule for filter_search: 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 MCP Server. Nothing to install.
filter_search 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 filter_search 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 filter_search. 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.
filter_search is provided by the Qdrant MCP Server MCP server (jimmy974/qdrant-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 →