rag_query

Query the knowledge base using hybrid search (vector similarity + keyword matching). Returns relevant chunks with a formatted context string suitable for LLM prompts.

SERVERMCP RAG Server SOURCE0xrdan/mcp-rag-server

Low RISK CLASS

Category Read

Parameters 00 required

Recommended Allowedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/0xrdan-mcp-rag-server/rag-query.md

WHAT IT DOES

What rag_query does on MCP RAG Server

AI agents call rag_query to retrieve information from MCP RAG Server without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

RISK

Why rag_query is rated Low

This tool retrieves and searches existing data from a knowledge base without any side effects. It performs a read-only query operation combining vector similarity and keyword matching to return information. No data is created, modified, deleted, or executed.

From the tool's definition Tool name is 'rag_query' and description states it 'Query the knowledge base' and 'Returns relevant chunks' — purely a retrieval operation with no modification, deletion, or execution capability.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs rag_query safely

PolicyLayer is an MCP gateway: it sits between your AI agents and MCP RAG Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For rag_query, this is the rule to start with:

rag_query Allowed

rag_query is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "rag_query": {}
  }
}

ALLOW ONLY THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect MCP RAG Server, apply this rule, and every rag_query call is checked against it from then on.

FAQ

Questions about rag_query

What does the rag_query tool do? +

Query the knowledge base using hybrid search (vector similarity + keyword matching). Returns relevant chunks with a formatted context string suitable for LLM prompts. It is categorised as a Read tool in the MCP RAG Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on rag_query? +

Register the MCP RAG Server MCP server in PolicyLayer and add a rule for rag_query: 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 Server. Nothing to install.

What risk level is rag_query? +

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

Can I rate-limit rag_query? +

Yes. Add a rate_limit block to the rag_query 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 rag_query completely? +

Set action: deny in the PolicyLayer policy for rag_query. 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 rag_query? +

rag_query is provided by the MCP RAG Server MCP server (0xrdan/mcp-rag-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on MCP RAG Server, and thousands of servers like it.

This server

All 7 MCP RAG Server tools →

Across the catalogue

claude_query on Claude Bridge → The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →