AI agents use supersede_decision_record 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 is a Write operation: it creates new decision records and updates the status of existing ones, both of which are reversible changes. The blast radius is medium because incorrect decision record supersessions could create confusion or require manual cleanup, but the data itself remains recoverable.
From the tool's definition Tool performs 'Create a replacement decision and mark the prior record superseded' — creates new data (replacement decision) and modifies existing data (marks prior record as superseded).
Attacks that exploit this kind of access
Create a replacement decision and mark the prior record superseded. 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 supersede_decision_record: 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.
supersede_decision_record 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 supersede_decision_record 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 supersede_decision_record. 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.
supersede_decision_record 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 →