AI agents use materialize_plan_steps 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.
This tool creates new task objects by decomposing a plan into constituent steps. While reversible (tasks can be deleted), it modifies the task management system by introducing new entities. It does not execute arbitrary code or have destructive/financial implications, making Write the most appropriate category.
From the tool's definition Tool description states it "Split plan into ordered step tasks" which involves creating new task entities. The verbs "split" and the action of generating "step tasks" indicate data creation/modification operations.
Attacks that exploit this kind of access
Split plan into ordered step tasks with sequential or parallel execution. 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 materialize_plan_steps: 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.
materialize_plan_steps 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 materialize_plan_steps 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 materialize_plan_steps. 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.
materialize_plan_steps 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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →