Delete multiple records in a single request
AI agents call batch_delete_records to permanently remove resources in Airtable MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes records from an Airtable base with no undo capability. The batch nature amplifies risk—a single malformed request or prompt injection could destroy large datasets. This is the most severe category of operation in a data management context.
From the tool's definition Tool name 'batch_delete_records' and description 'Delete multiple records in a single request' explicitly indicate irreversible deletion of data at scale.
Attacks that exploit this kind of access
Delete multiple records in a single request. It is categorised as a Destructive tool in the Airtable MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Airtable MCP Server MCP server in PolicyLayer and add a rule for batch_delete_records: 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 Airtable MCP Server. Nothing to install.
batch_delete_records 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 batch_delete_records 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 batch_delete_records. 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.
batch_delete_records is provided by the Airtable MCP Server MCP server (loticdigital/airtable-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 →