retrieve · Rag MCP: Risk & Policy

WHAT IT DOES

What retrieve does on Rag

AI agents call retrieve to retrieve information from Rag without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

WHY IT NEEDS A POLICY

Why retrieve needs a policy

This tool queries stored knowledge and returns results without side effects. It matches the Read category definition: retrieves or queries data with no side effects. The low severity reflects that misuse would only expose information already ingested into the system, with no destructive or financial impact.

From the tool's definition Tool performs 'semantic search across ingested knowledge' — a retrieval operation with no modification, creation, or deletion of data.

Attacks that exploit this kind of access

Questions about retrieve

What does the retrieve tool do? +

Semantic search across ingested knowledge. It is categorised as a Read tool in the Rag MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on retrieve? +

Register the Rag 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 Rag. Nothing to install.

What risk level is retrieve? +

retrieve is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit retrieve? +

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.

How do I block retrieve completely? +

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.

What MCP server provides retrieve? +

retrieve is provided by the Rag MCP server (mrankitvish/rag-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.