Query a document using RAG. Note: If the index does not exist, it will be created when you query, which may take some time.
AI agents call rag_query to retrieve information from MCP Docs RAG Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a retrieval-augmented generation query against indexed documents. It retrieves and returns contextual information without modifying, deleting, or executing code. The only side effect mentioned is automatic index creation on first query, which is a preparatory operation for the read action, not a destructive or execute operation.
From the tool's definition Tool name 'rag_query' and description 'Query a document using RAG' indicate data retrieval. The description explicitly states querying documents with no mention of modification, deletion, or execution capabilities.
Documented attack patterns abuse exactly the kind of access rag_query gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Docs RAG Server, and nothing reaches the server without passing your rules. This is the rule we recommend for rag_query:
{
"version": "1",
"default": "deny",
"tools": {
"rag_query": {}
}
}rag_query 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 a document using RAG. Note: If the index does not exist, it will be created when you query, which may take some time. It is categorised as a Read tool in the MCP Docs RAG Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Docs 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 Docs RAG Server. Nothing to install.
rag_query 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 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.
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.
rag_query is provided by the MCP Docs RAG Server MCP server (kazuph/mcp-docs-rag). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Docs RAG Server, 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.
4 MCP Docs RAG Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.