Delete a chat summary file.
AI agents call delete_summary to permanently remove resources in IDE Chat Summarizer — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool performs irreversible deletion of user files (chat summaries). While the blast radius is somewhat contained to summary files rather than critical system data, the destructive nature and inability to undo the action classify it as Destructive.
From the tool's definition Tool name includes 'delete' and description explicitly states 'Delete a chat summary file', indicating irreversible removal of data.
Attacks that exploit this kind of access
Delete a chat summary file. It is categorised as a Destructive tool in the IDE Chat Summarizer MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the IDE Chat Summarizer MCP server in PolicyLayer and add a rule for delete_summary: 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 IDE Chat Summarizer. Nothing to install.
delete_summary 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 delete_summary 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 delete_summary. 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.
delete_summary is provided by the IDE Chat Summarizer MCP server (ralphli213/ide-chat-summarizer-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 →