claim_goal_step · Todos MCP: Risk & Policy

WHAT IT DOES

What claim_goal_step does on Todos

AI agents use claim_goal_step 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 claim_goal_step needs a policy

Claiming a goal step is a write/state-change operation that assigns or reserves a task step to an agent. While 'execute' is mentioned as equivalent, the action itself is about claiming/assigning ownership of a step (a reversible state change), not running arbitrary code or commands. The blast radius is moderate since misuse could disrupt task coordination for AI agents.

From the tool's definition Claim the next ready /goal step for an agent (equivalent to /goal execute)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

claim_goal_step Rate-limited

claim_goal_step 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": {
    "claim_goal_step": {
      "limits": [
        {
          "counter": "claim_goal_step_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 claim_goal_step

What does the claim_goal_step tool do? +

Claim the next ready /goal step for an agent (equivalent to /goal execute). 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 claim_goal_step? +

Register the Todos MCP server in PolicyLayer and add a rule for claim_goal_step: 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 claim_goal_step? +

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

Can I rate-limit claim_goal_step? +

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

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

claim_goal_step 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.

// THE FULL RECORD

claim_goal_step is one line of Todos's registry record.

The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →