AI agents call search_documents 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 tool retrieves and returns data from a vector database without modifying, deleting, or executing code. It performs a search/query operation identical in risk profile to a SELECT query. The metadata filtering capability does not elevate risk as it only constrains retrieval scope. Blast radius of misuse is minimal — worst case returns unintended documents, with no destructive or financial consequence.
From the tool's definition Tool description states it 'Embed query text and return top-k chunk matches from Qdrant' — a retrieval operation with no side effects.
Attacks that exploit this kind of access
Embed query text and return top-k chunk matches from Qdrant. 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 search_documents: 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.
search_documents 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 search_documents 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 search_documents. 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.
search_documents 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 →