create_manual_checkpoint · Todos MCP: Risk & Policy

WHAT IT DOES

What create_manual_checkpoint does on Todos

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

WHY IT NEEDS A POLICY

Why create_manual_checkpoint needs a policy

This tool creates new checkpoint records, which is a Write operation (creates data reversibly). It's not Read (doesn't just query), not Execute (doesn't run external code or shell commands), not Destructive (checkpoints can be removed/superseded), and not Financial.

From the tool's definition Tool name 'create_manual_checkpoint' and description 'Create a manual checkpoint on a task' indicates creating/persisting new checkpoint data on an existing task. The mention of 'optionally requiring approval' suggests this modifies task state.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

create_manual_checkpoint Rate-limited

create_manual_checkpoint 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": {
    "create_manual_checkpoint": {
      "limits": [
        {
          "counter": "create_manual_checkpoint_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 Todos, so you can run agents against it safely.

FAQ

Questions about create_manual_checkpoint

What does the create_manual_checkpoint tool do? +

Create a manual checkpoint on a task, optionally requiring approval. It is categorised as a Write tool in the Todos MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on create_manual_checkpoint? +

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

What risk level is create_manual_checkpoint? +

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

Can I rate-limit create_manual_checkpoint? +

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

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

create_manual_checkpoint is provided by the Todos MCP server (@hasna/todos). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.