AI agents use set_agent_status to create or update resources in Agent Bus — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Agent Bus environment.
This tool creates or modifies data (agent status) in a reversible manner. Setting an agent's status is a state change that can be undone by setting it to a different status, making it Write rather than Destructive.
From the tool's definition Tool description explicitly states it 'Set[s] an agent work state' to one of several predefined statuses (idle, working, blocked, waiting_review, or sleeping). This modifies the internal state of an agent.
Attacks that exploit this kind of access
Set an agent work state: idle, working, blocked, waiting_review, or sleeping. It is categorised as a Write tool in the Agent Bus MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Agent Bus MCP server in PolicyLayer and add a rule for set_agent_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 Agent Bus. Nothing to install.
set_agent_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 set_agent_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 set_agent_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.
set_agent_status is provided by the Agent Bus MCP server (mustaphasteph/agent-bus). 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 →