Delete rows based on condition.
AI agents call delete to permanently remove resources in Tax Alert Chatbot MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The delete operation permanently removes data from the SQLite database without possibility of recovery through normal means. While the blast radius is limited to tax alert records (not financial transactions), unauthorized or mistaken deletion of tax alert data could cause compliance issues, loss of audit trails, or operational disruption.
From the tool's definition Tool name is 'delete' and description states 'Delete rows based on condition.' This explicitly performs irreversible deletion of data from the tax alerts database.
Attacks that exploit this kind of access
Delete rows based on condition. It is categorised as a Destructive tool in the Tax Alert Chatbot MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Tax Alert Chatbot MCP Server MCP server in PolicyLayer and add a rule for delete: 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 Tax Alert Chatbot MCP Server. Nothing to install.
delete 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 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. 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 is provided by the Tax Alert Chatbot MCP Server MCP server (soham-bakshi/mcp-server). 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 →