AI agents call bus as a supporting operation in iTerm MCP workflows.
The description is empty and the name 'bus' is ambiguous — it could refer to a message bus, event bus, or inter-process communication mechanism. Given the server context (iTerm2, orchestration, multi-agent), it might relay messages between agents/sessions, which could be Write or Execute.
From the tool's definition Tool name is 'bus' with an empty description. No information about what it does is available.
Attacks that exploit this kind of access
bus. It is categorised as a Other tool in the iTerm MCP MCP Server, which means it performs auxiliary operations.
Register the iTerm MCP server in PolicyLayer and add a rule for bus: 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 iTerm MCP. Nothing to install.
bus is a Other tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the bus 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 bus. 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.
bus is provided by the iTerm MCP server (research-developer/iterm-mcp-claude-agency). 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 →