AI agents call review_gate 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 tool retrieves and reports gate status (merge/push eligibility) from existing project data. It has no side effects—it reads state to inform decisions but does not execute merges, push operations, or modify any data. The information returned (ok=true/false with blockers/warnings) is purely advisory for the calling agent.
From the tool's definition Tool description states 'Return a deterministic merge/push gate from the project board and final report.' The verb 'Return' indicates retrieval/querying of status data. No modification, execution, deletion, or financial action is described.
Attacks that exploit this kind of access
Return a deterministic merge/push gate from the project board and final report. ok=false includes blockers and warnings. 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 review_gate: 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.
review_gate 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 review_gate 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 review_gate. 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.
review_gate 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 →