Clear the context for a user
AI agents call clear_context to permanently remove resources in Memory Context Provider Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes user context data without possibility of recovery. While not directly threatening production systems or financial data, it destructively wipes user-specific stored state that cannot be easily reconstructed, fitting the Destructive category.
From the tool's definition Tool name 'clear_context' and description 'Clear the context for a user' indicate irreversible deletion of stored conversation context data.
Attacks that exploit this kind of access
Clear the context for a user. It is categorised as a Destructive tool in the Memory Context Provider Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Memory Context Provider Server MCP server in PolicyLayer and add a rule for clear_context: 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 Memory Context Provider Server. Nothing to install.
clear_context 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_context 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_context. 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_context is provided by the Memory Context Provider Server MCP server (srish-ty/mcp-testing-interface-for-llms). 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 →