ragflow_retrieval_tool
AI agents call ragflow_retrieval_tool to retrieve information from RAGFlow MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite the empty description lowering confidence slightly, the tool name 'ragflow_retrieval_tool' in the context of a RAG (Retrieval-Augmented Generation) system strongly suggests this performs semantic search or document retrieval without modifying data. RAG systems primarily retrieve relevant chunks/documents to augment LLM prompts.
From the tool's definition Tool name contains 'retrieval' which typically indicates data fetching/querying operations. The server description mentions 'semantic retrieval' as a core capability, and this tool name aligns with that retrieve-only functionality.
Attacks that exploit this kind of access
ragflow_retrieval_tool. It is categorised as a Read tool in the RAGFlow MCP Server MCP Server, which means it retrieves data without modifying state.
Register the RAGFlow MCP Server MCP server in PolicyLayer and add a rule for ragflow_retrieval_tool: 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 Server. Nothing to install.
ragflow_retrieval_tool 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_tool 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_tool. 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_tool is provided by the RAGFlow MCP Server MCP server (migoxv/ragflow-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →