Query indexed documents using RAG
AI agents call query_documents to retrieve information from Mcp Rag without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs document retrieval and context fetching via RAG without modifying, deleting, or executing operations. It is a read-only operation that queries indexed data to return relevant results. The sibling tools (embedding_documents=Write, remove_document=Destructive, remove_all_documents=Destructive, list_documents=Read) confirm this server handles both read and destructive operations separately.
From the tool's definition Tool name 'query_documents' and description 'Query indexed documents using RAG' indicate a retrieval operation that searches and retrieves relevant context from previously indexed documents.
Documented attack patterns abuse exactly the kind of access query_documents gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Rag, and nothing reaches the server without passing your rules. This is the rule we recommend for query_documents:
{
"version": "1",
"default": "deny",
"tools": {
"query_documents": {}
}
}query_documents is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Query indexed documents using RAG. It is categorised as a Read tool in the Mcp Rag MCP Server, which means it retrieves data without modifying state.
Register the Mcp Rag MCP server in PolicyLayer and add a rule for query_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 Mcp Rag. Nothing to install.
query_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 query_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 query_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.
query_documents is provided by the Mcp Rag MCP server (kwanleefrmvi/mcp-rag-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mcp Rag, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
5 Mcp Rag tools catalogued and risk-classified — across an index of 43,000+ MCP servers.