AI agents use reject_gate 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 changes task workflow state (rejecting an approval gate) rather than executing arbitrary operations or permanently deleting data. The rejection can typically be reversed by re-approving or resubmitting. It falls under Write (reversible modification) rather than Execute (which would imply running external code/commands) or Destructive (which would mean irreversible deletion).
From the tool's definition 'Reject a pending approval gate request' - modifies the state of an approval gate from pending to rejected, reversibly changing task workflow state without deletion
Attacks that exploit this kind of access
Reject a pending approval gate request. 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 reject_gate: 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.
reject_gate 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 reject_gate 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 reject_gate. 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.
reject_gate 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 →