Clear the conversation memory/history.
AI agents call reset_history to permanently remove resources in Senior Consult MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool permanently clears conversation history/memory. This is a destructive operation because once the history is cleared it cannot be recovered. However, the blast radius is limited to session memory within this MCP server rather than affecting external systems or financial data, so severity is medium.
From the tool's definition "Clear the conversation memory/history" — clearing/purging stored data is irreversible
Attacks that exploit this kind of access
Clear the conversation memory/history. It is categorised as a Destructive tool in the Senior Consult MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Senior Consult MCP server in PolicyLayer and add a rule for reset_history: 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 Senior Consult MCP. Nothing to install.
reset_history 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 reset_history 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 reset_history. 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.
reset_history is provided by the Senior Consult MCP server (silkyland/senior-consult-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 →