todo_complete · Claude Flow MCP: Risk & Policy

WHAT IT DOES

What todo_complete does on Claude Flow

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

WHY IT NEEDS A POLICY

Why todo_complete needs a policy

This tool performs a reversible state change to a task object (marking complete). It does not delete data, execute arbitrary operations, or have financial impact. The scope is limited to a single task's status field. Severity is low because the blast radius of accidental misuse is minimal—tasks can be unmarked or corrected without loss of data or system integrity.

From the tool's definition Tool name and description: 'Mark a task as complete' — modifies task state by changing its completion status.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

todo_complete Rate-limited

todo_complete 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": {
    "todo_complete": {
      "limits": [
        {
          "counter": "todo_complete_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 Claude Flow, so you can run agents against it safely.

FAQ

Questions about todo_complete

What does the todo_complete tool do? +

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

How do I enforce a policy on todo_complete? +

Register the Claude Flow MCP server in PolicyLayer and add a rule for todo_complete: 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 Claude Flow. Nothing to install.

What risk level is todo_complete? +

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

Can I rate-limit todo_complete? +

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

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

todo_complete is provided by the Claude Flow MCP server (claude-flow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.