AI agents call search_documents 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.
This tool retrieves or queries document metadata without creating, modifying, or deleting any data. It is a passive read operation that fits the Read category. Severity is low because metadata queries have minimal blast radius—the worst case is information disclosure of existing metadata, which is non-destructive and reversible.
From the tool's definition Tool name 'search_documents' combined with description 'Search document metadata' indicates a query operation that retrieves information without modification.
Attacks that exploit this kind of access
Search document metadata. It is categorised as a Read tool in the Rag MCP Server, which means it retrieves data without modifying state.
Register the Rag 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 Rag. 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 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.
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 →