claim_plan_step
Claim and start the next ready plan step for an agent.
This record as markdown: /tools/todos/claim-plan-step.md
What claim_plan_step does on Todos
AI agents use claim_plan_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 claim_plan_step is rated Medium
The tool modifies task/plan state by claiming and starting a step, which changes data (ownership, status flags). This is Write rather than Execute because it doesn't directly run arbitrary code—it transitions workflow state. Severity is medium because misclaiming steps could block other agents or create workflow conflicts, but the impact is limited to task coordination and reversible.
From the tool's definition Tool name 'claim_plan_step' and description 'Claim and start the next ready plan step' indicate state modification—claiming a plan step changes its ownership/status from unclaimed to claimed, and 'start' implies initiating execution state.
Attacks that exploit this kind of access
The rule that runs claim_plan_step safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Todos, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For claim_plan_step, this is the rule to start with:
claim_plan_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.
The button opens the PolicyLayer dashboard: create your workspace, connect Todos, apply this rule, and every claim_plan_step call is checked against it from then on.
Questions about claim_plan_step
Claim and start the next ready plan step for an agent. 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.
Register the Todos MCP server in PolicyLayer and add a rule for claim_plan_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.
claim_plan_step is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the claim_plan_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.
Set action: deny in the PolicyLayer policy for claim_plan_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.
claim_plan_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.
More on Todos, and thousands of servers like it.
This server
Across the catalogue