AI agents call ask_team to retrieve information from Agent Bus without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
ask_team retrieves information or a response from a team member without causing side effects or triggering external operations. The 'ask' semantics indicate a query-like interaction within the local agent bus. Since it is scoped to a team and filtered by attributes, it is a constrained read operation.
From the tool's definition Tool performs a request/response query to an active team member, optionally filtered by capability and role. No modification, deletion, execution, or financial action is implied by the description.
Attacks that exploit this kind of access
Ask the best active member of a team. Optionally filter by capability and role. Use for team-scoped request/response. It is categorised as a Read tool in the Agent Bus MCP Server, which means it retrieves data without modifying state.
Register the Agent Bus MCP server in PolicyLayer and add a rule for ask_team: 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_team is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the ask_team 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_team. 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_team 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 →