Clear recorded sequential-thinking history for one session or all sessions.
AI agents call clear_thinking_history to permanently remove resources in Mcp Sequentialthinking Tools — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool permanently deletes thinking history records, which is an irreversible destructive action. It can affect a single session or all sessions, making the blast radius potentially broad. No indication of recovery or undo capability is present.
From the tool's definition 'Clear recorded sequential-thinking history for one session or all sessions' — irreversibly removes stored history data
Attacks that exploit this kind of access
Clear recorded sequential-thinking history for one session or all sessions. It is categorised as a Destructive tool in the Mcp Sequentialthinking Tools MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Mcp Sequentialthinking Tools MCP server in PolicyLayer and add a rule for clear_thinking_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 Mcp Sequentialthinking Tools. Nothing to install.
clear_thinking_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 clear_thinking_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 clear_thinking_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.
clear_thinking_history is provided by the Mcp Sequentialthinking Tools MCP server (mcp-sequentialthinking-tools). 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 →