AI agents use update_deadline to create or update resources in Ebb Ai — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ebb Ai environment.
This tool modifies task metadata (deadline and scheduling) but does not delete, execute arbitrary code, move money, or irreversibly destroy data. The change can be undone by rescheduling again. While it affects task behavior, the impact is limited to scheduling parameters within the carbon-aware queuing system.
From the tool's definition Tool description states it 're-score[s] and reschedule[s] a queued/scheduled task', which modifies the state of an existing task's deadline and scheduling parameters.
Attacks that exploit this kind of access
Re-score and reschedule a queued/scheduled task against a new deadline. Throws if the task is already running or terminal, or if the new deadline is invalid/in the past. It is categorised as a Write tool in the Ebb Ai MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ebb Ai MCP server in PolicyLayer and add a rule for update_deadline: 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 Ebb Ai. Nothing to install.
update_deadline 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_deadline 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_deadline. 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_deadline is provided by the Ebb Ai MCP server (vitalini/ebb-ai). 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 →