Reset/clear the chat session for a specific dataset
AI agents call ragflow_reset_session to permanently remove resources in RAGFlow Claude MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Resetting/clearing a chat session is an irreversible destructive action — the session history and context are wiped. While not catastrophic in terms of data loss (no documents or datasets are deleted), the session state cannot be recovered after clearing, making it Destructive rather than Write. Severity is medium because only session/conversation data is lost, not underlying knowledge base content.
From the tool's definition Reset/clear the chat session for a specific dataset
Documented attack patterns abuse exactly the kind of access ragflow_reset_session 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_reset_session:
{
"version": "1",
"default": "deny",
"hide": [
"ragflow_reset_session"
]
} ragflow_reset_session disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Reset/clear the chat session for a specific dataset. It is categorised as a Destructive tool in the RAGFlow Claude MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the RAGFlow Claude MCP Server MCP server in PolicyLayer and add a rule for ragflow_reset_session: 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_reset_session 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_reset_session 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_reset_session. 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_reset_session 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.