AI agents call remove_columns to permanently remove resources in CSV Editor — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing columns from a dataframe permanently destroys that data. While the server mentions undo/redo features which could mitigate this, the operation itself is inherently destructive as it deletes data. The blast radius is high because an AI agent could accidentally remove critical columns from large datasets, causing significant data loss.
From the tool's definition 'Remove columns from the dataframe' — removing columns is an irreversible deletion of data structure and content
Documented attack patterns abuse exactly the kind of access remove_columns gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and CSV Editor, and nothing reaches the server without passing your rules. This is the rule we recommend for remove_columns:
{
"version": "1",
"default": "deny",
"hide": [
"remove_columns"
]
}remove_columns 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.
Remove columns from the dataframe. It is categorised as a Destructive tool in the CSV Editor MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the CSV Editor MCP server in PolicyLayer and add a rule for remove_columns: 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 CSV Editor. Nothing to install.
remove_columns 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 remove_columns 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 remove_columns. 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.
remove_columns is provided by the CSV Editor MCP server (santoshray02/csv-editor). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from CSV Editor, 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.
39 CSV Editor tools catalogued and risk-classified — across an index of 43,000+ MCP servers.