ragflow_delete_chat_tool
AI agents call ragflow_delete_chat_tool to permanently remove resources in RAGFlow MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool name clearly indicates a deletion operation (delete_chat). In the context of a knowledge base and dataset management system, deleting a chat session is irreversible and represents destructive capability.
From the tool's definition Tool name 'ragflow_delete_chat_tool' combined with server context showing deletion operations ('ragflow_delete_chunk_tool', 'ragflow_delete_dataset_tool', 'ragflow_delete_document_tool'). The 'delete' prefix indicates irreversible data removal.
Attacks that exploit this kind of access
ragflow_delete_chat_tool. It is categorised as a Destructive tool in the RAGFlow MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the RAGFlow MCP Server MCP server in PolicyLayer and add a rule for ragflow_delete_chat_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_delete_chat_tool is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the ragflow_delete_chat_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_delete_chat_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_delete_chat_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 →