replace_in_column · DataBeak MCP: Risk & Policy

WHAT IT DOES

What replace_in_column does on DataBeak

AI agents use replace_in_column to create or update resources in DataBeak — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your DataBeak environment.

WHY IT NEEDS A POLICY

Why replace_in_column needs a policy

The tool appears designed to replace values within a CSV column, which is a reversible modification operation characteristic of Write-category tools. Severity is high because bulk replacements across columns could affect many data records and downstream analyses, though the operation remains reversible unlike Destructive actions.

From the tool's definition Tool name 'replace_in_column' indicates modification of data within a column. Sibling tools on the server include 'add_column', 'change_column_type', 'delete_row', and 'fill_missing_values', all of which are Write operations that modify data reversibly.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

replace_in_column Rate-limited

replace_in_column stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "replace_in_column": {
      "limits": [
        {
          "counter": "replace_in_column_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches DataBeak, so you can run agents against it safely.

FAQ

Questions about replace_in_column

What does the replace_in_column tool do? +

replace_in_column. It is categorised as a Write tool in the DataBeak MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on replace_in_column? +

Register the DataBeak MCP server in PolicyLayer and add a rule for replace_in_column: 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 DataBeak. Nothing to install.

What risk level is replace_in_column? +

replace_in_column is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit replace_in_column? +

Yes. Add a rate_limit block to the replace_in_column 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.

How do I block replace_in_column completely? +

Set action: deny in the PolicyLayer policy for replace_in_column. 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.

What MCP server provides replace_in_column? +

replace_in_column is provided by the DataBeak MCP server (jonpspri/databeak). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.