AI agents call session_brief 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.
session_brief reads and aggregates existing state from the agent bus (task statuses, decisions, messages, memories) to produce a summary report. There are no side effects—no data is created, modified, deleted, or executed. The tool is purely informational, making it a Read category risk with low severity since it only surfaces information already accessible to the system.
From the tool's definition Tool generates a brief by retrieving information ('from live agents, open/blocked/stale tasks, recent decisions, memories, and messages') with no modification or deletion of underlying data.
Attacks that exploit this kind of access
Generate a startup/handoff brief from live agents, open/blocked/stale tasks, recent decisions, memories, and messages. 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 session_brief: 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.
session_brief 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 session_brief 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 session_brief. 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.
session_brief 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 →