Clear the thought history.
AI agents call clear_history to permanently remove resources in COAIA Sequential Thinking — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly deletes data (thought history) and cannot be undone, which places it in the Destructive category rather than Write. While the blast radius is limited to session history rather than critical business data, the permanent loss of user work and analytical records represents a medium severity risk if triggered unintentionally by an AI agent.
From the tool's definition The tool name is 'clear_history' and the description states it will 'Clear the thought history.' This is an irreversible deletion operation that permanently removes previously stored thought records.
Attacks that exploit this kind of access
Clear the thought history. It is categorised as a Destructive tool in the COAIA Sequential Thinking MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the COAIA Sequential Thinking MCP server in PolicyLayer and add a rule for clear_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 COAIA Sequential Thinking. Nothing to install.
clear_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_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_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_history is provided by the COAIA Sequential Thinking MCP server (miadisabelle/mcp-coaia-sequential-thinking). 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 →