Delete rows from a KDB+ table
AI agents call kdb_delete to permanently remove resources in KDB MCP Service — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deletion is inherently destructive and irreversible. In a financial database context (as indicated by the server description), deleting rows could result in loss of critical transaction history, audit trails, or market data. An AI agent with unchecked access could maliciously or erroneously delete large datasets.
From the tool's definition Tool name 'kdb_delete' and description 'Delete rows from a KDB+ table' explicitly indicate irreversible deletion of data.
Attacks that exploit this kind of access
Delete rows from a KDB+ table. It is categorised as a Destructive tool in the KDB MCP Service MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the KDB MCP Service MCP server in PolicyLayer and add a rule for kdb_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 KDB MCP Service. Nothing to install.
kdb_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 kdb_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 kdb_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.
kdb_delete is provided by the KDB MCP Service MCP server (riteshsonawala/kdb-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 →