Retrieve document chunks directly from RAGFlow datasets using the retrieval API. Returns raw chunks with similarity scores.
AI agents call ragflow_retrieval to retrieve information from RAGFlow Claude MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves data from a knowledge base without creating, modifying, deleting, or executing operations. It is a straightforward document retrieval function with no side effects, fitting the Read category. The low severity reflects minimal risk even in misuse—an agent retrieving wrong documents causes informational errors, not system compromise or data loss.
From the tool's definition Tool description states it 'Retrieve[s] document chunks directly from RAGFlow datasets' and 'Returns raw chunks with similarity scores.' The verb 'retrieve' and the read-only nature of returning existing data with no modifications indicated.
Documented attack patterns abuse exactly the kind of access ragflow_retrieval gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and RAGFlow Claude MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for ragflow_retrieval:
{
"version": "1",
"default": "deny",
"tools": {
"ragflow_retrieval": {}
}
}ragflow_retrieval 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.
Retrieve document chunks directly from RAGFlow datasets using the retrieval API. Returns raw chunks with similarity scores. It is categorised as a Read tool in the RAGFlow Claude MCP Server MCP Server, which means it retrieves data without modifying state.
Register the RAGFlow Claude MCP Server MCP server in PolicyLayer and add a rule for ragflow_retrieval: 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 Claude MCP Server. Nothing to install.
ragflow_retrieval 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 ragflow_retrieval 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 ragflow_retrieval. 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.
ragflow_retrieval is provided by the RAGFlow Claude MCP Server MCP server (norandom/ragflow-claude-desktop-local-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from RAGFlow Claude MCP 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.
8 RAGFlow Claude MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.