Update the completion status of a todo item
AI agents use update_todo_status to create or update resources in Software Planning Tool — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Software Planning Tool environment.
This tool creates or modifies data reversibly by changing a todo item's status. It does not execute arbitrary code, delete data permanently, or trigger financial transactions. The 'medium' severity reflects that an AI agent misusing this tool could mark unfinished tasks as complete or vice versa, potentially disrupting project planning accuracy, but the change is reversible (status can be updated again).
From the tool's definition Tool updates the completion status of a todo item, which modifies existing data (the todo item's status field) in a reversible manner.
Attacks that exploit this kind of access
Update the completion status of a todo item. It is categorised as a Write tool in the Software Planning Tool MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Software Planning Tool MCP server in PolicyLayer and add a rule for update_todo_status: 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 Software Planning Tool. Nothing to install.
update_todo_status 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 update_todo_status 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 update_todo_status. 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.
update_todo_status is provided by the Software Planning Tool MCP server (philippmt/software-planning-mcp). 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 →