AI agents call list_task_events 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 tool retrieves and displays existing task event data with optional filters. It has no side effects—it does not create, modify, delete, or execute operations. It is a read-only query of task event logs. Given the local MCP server context (private machine collaboration), the blast radius of misuse is minimal: an agent could enumerate task history but cannot harm systems or data.
From the tool's definition Tool name is 'list_task_events' and description states it 'List[s] task event/progress rows, optionally filtered by task, agent, type, project, or area.' This is purely a query/retrieval operation with filtering capabilities.
Attacks that exploit this kind of access
List task event/progress rows, optionally filtered by task, agent, type, project, or area. 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 list_task_events: 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.
list_task_events 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 list_task_events 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 list_task_events. 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.
list_task_events 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 →