AI agents invoke ask to trigger actions in Agent Bus. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool triggers an inter-agent communication operation that blocks execution until a response is received or a timeout occurs. It initiates an external operation (message dispatch to another agent on the bus) and waits for its result, making it Execute rather than a simple Read. Misuse could cause blocking delays or trigger unintended agent actions depending on the content of the question sent.
From the tool's definition Send a question and BLOCK until a reply arrives (or timeout). Capped at 110s.
Attacks that exploit this kind of access
Send a question and BLOCK until a reply arrives (or timeout). Capped at 110s. It is categorised as a Execute tool in the Agent Bus MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Agent Bus MCP server in PolicyLayer and add a rule for ask: 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.
ask is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the ask 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 ask. 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.
ask 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 →