AI agents use set_delivery 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 is a reversible Write operation that modifies task properties (delivery method, deadline, or schedule parameters) rather than executing the task itself or destructively deleting it. The ability to change delivery settings is metadata-level modification. Given the limited blast radius (affecting only queued task properties, not external systems or financial transactions), severity is low.
From the tool's definition Tool allows to 'Set or change' configuration of a scheduled task, indicating modification of task metadata/parameters in the scheduler.
Attacks that exploit this kind of access
Set or change how a scheduled task. 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 set_delivery: 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.
set_delivery 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 set_delivery 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 set_delivery. 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.
set_delivery 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 →