AI agents call query_rag to retrieve information from RAGFlow MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The name 'query_rag' strongly implies a read/search operation against a RAG dataset. However, the description is empty, which lowers confidence. Given the sibling tools (create_rag, get_ragflow_datasets, upload_rag), this tool most likely queries/retrieves information from a RAG pipeline.
From the tool's definition Tool name 'query_rag' suggests a retrieval/query operation against a RAG (Retrieval-Augmented Generation) datastore.
Documented attack patterns abuse exactly the kind of access query_rag gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and RAGFlow MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for query_rag:
{
"version": "1",
"default": "deny",
"tools": {
"query_rag": {}
}
}query_rag 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_rag. It is categorised as a Read tool in the RAGFlow MCP MCP Server, which means it retrieves data without modifying state.
Register the RAGFlow MCP server in PolicyLayer and add a rule for query_rag: 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 RAGFlow MCP. Nothing to install.
query_rag 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_rag 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_rag. 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_rag is provided by the RAGFlow MCP server (oraichain/ragflow-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from RAGFlow MCP, 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 RAGFlow MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.