multi_edit · LocalAnt MCP: Risk & Policy

WHAT IT DOES

What multi_edit does on LocalAnt

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

WHY IT NEEDS A POLICY

Why multi_edit needs a policy

multi_edit creates or modifies file data through string replacements. This is a Write operation—the changes are reversible (the user can re-edit the file, and a backup is kept). It does not delete files (Destructive), execute arbitrary code (Execute), or cause financial harm (Financial).

From the tool's definition "Apply a sequence of string-replace edits to one file atomically" and "any write" indicate this tool modifies file contents reversibly through search-and-replace operations.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

multi_edit Rate-limited

multi_edit 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": {
    "multi_edit": {
      "limits": [
        {
          "counter": "multi_edit_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 LocalAnt, so you can run agents against it safely.

FAQ

Questions about multi_edit

What does the multi_edit tool do? +

Apply a sequence of string-replace edits to one file atomically (all validated before any write). Keeps a single backup. It is categorised as a Write tool in the LocalAnt MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on multi_edit? +

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

What risk level is multi_edit? +

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

Can I rate-limit multi_edit? +

Yes. Add a rate_limit block to the multi_edit 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 multi_edit completely? +

Set action: deny in the PolicyLayer policy for multi_edit. 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 multi_edit? +

multi_edit is provided by the LocalAnt MCP server (yuga-hashimoto/localant). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.