AI agents call delete_row to permanently remove resources in Coda — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes data from a table and cannot be undone without external recovery mechanisms. It matches the Destructive category definition: 'irreversibly deletes or overwrites data, or actions that cannot be undone.' The high severity reflects that an AI agent given this tool could accidentally or maliciously delete important rows from user documents in Coda, with potential for broad data loss…
From the tool's definition Tool name 'delete_row' combined with description 'Delete a specific row from a table' explicitly performs irreversible deletion of data.
Documented attack patterns abuse exactly the kind of access delete_row gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Coda, and nothing reaches the server without passing your rules. This is the rule we recommend for delete_row:
{
"version": "1",
"default": "deny",
"hide": [
"delete_row"
]
}delete_row disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Delete a specific row from a table by its ID or name. It is categorised as a Destructive tool in the Coda MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Coda MCP server in PolicyLayer and add a rule for delete_row: 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 Coda. Nothing to install.
delete_row 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_row 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_row. 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_row is provided by the Coda MCP server (tjc-lp/coda-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Coda, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
24 Coda tools catalogued and risk-classified — across an index of 43,000+ MCP servers.