AI agents call retrieve to retrieve information from Vectorize without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and fetches documents from an existing pipeline without modifying, deleting, or executing arbitrary operations. It is a straightforward read operation with minimal blast radius if misused by an AI agent.
From the tool's definition Tool name is 'retrieve' and description states 'Retrieve documents from the configured pipeline' — retrieves data with no side effects.
Attacks that exploit this kind of access
Retrieve documents from the configured pipeline. It is categorised as a Read tool in the Vectorize MCP Server, which means it retrieves data without modifying state.
Register the Vectorize MCP server in PolicyLayer and add a rule for retrieve: 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 Vectorize. Nothing to install.
retrieve 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 retrieve 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 retrieve. 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.
retrieve is provided by the Vectorize MCP server (@vectorize-io/vectorize-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.