Clear temporary scratch notes
AI agents call clear_scratch to permanently remove resources in MCP Contemplation — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Clearing scratch notes destroys temporary cognitive processing data that cannot be recovered. While the data is described as 'temporary', the action is irreversible deletion, making Destructive the appropriate category. Severity is medium because scratch notes are transient/working data rather than primary persistent storage, but misuse could disrupt the contemplation loop's in-progress reasoning.
From the tool's definition 'Clear temporary scratch notes' — clearing implies irreversible removal of stored data (scratch notes)
Attacks that exploit this kind of access
Clear temporary scratch notes. It is categorised as a Destructive tool in the MCP Contemplation MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP Contemplation MCP server in PolicyLayer and add a rule for clear_scratch: 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 Contemplation. Nothing to install.
clear_scratch 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_scratch 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_scratch. 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_scratch is provided by the MCP Contemplation MCP server (mikeybeez/mcp-contemplation). 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 →