AI agents call cockpit 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.
The cockpit tool is a coordinator dashboard that retrieves and displays status information about tasks and project state. It performs no writes, executions, deletions, or financial transactions. The blast radius of misuse is minimal — an AI agent could only view operational status, not change it. Categorized as Read with low severity and high confidence.
From the tool's definition Tool provides dashboard/monitoring functionality showing 'waiting items, ready items, blockers, suggested next actions, and underlying project board' — all read-only display of status and state information with no modification, execution, or destructive…
Attacks that exploit this kind of access
Coordinator dashboard: waiting items, ready items, blockers, suggested next actions, and the underlying project board. 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 cockpit: 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.
cockpit 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 cockpit 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 cockpit. 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.
cockpit 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 →