AI agents call team_board 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.
This is a dashboard or status board tool that presents team management information. It queries and displays state without modifying data or triggering external actions. No side effects, no data mutation, no execution of commands. The low severity reflects that misuse (e.g., reading sensitive task information) has minimal blast radius in a local private agent bus context.
From the tool's definition Tool name 'team_board' and description indicate it provides a 'Manager board' that displays and retrieves information: 'agents, tasks, review queue, acknowledgements, conflicts, pinned risks/handoffs, and next actions.' The verb is 'for' (informational…
Attacks that exploit this kind of access
Manager board for one team: agents, tasks, review queue, acknowledgements, conflicts, pinned risks/handoffs, and next actions. 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 team_board: 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.
team_board 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 team_board 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 team_board. 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.
team_board 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 →