AI agents call list_tasks 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 queries task state from the message bus without side effects. It supports filtering but only changes what data is returned, not the underlying state. The operation is read-only and returns information about tasks managed by the local agent collaboration system. Low severity because data exposure is limited to local task metadata on a private message bus.
From the tool's definition Tool name 'list_tasks' and description 'List tasks' with filter options (include_terminal) indicates a retrieval/query operation. No modification, execution, deletion, or financial operations occur.
Attacks that exploit this kind of access
List tasks. By default excludes terminal states (completed/failed/canceled) but includes backlog; set include_terminal:true to show terminal tasks. 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_tasks: 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_tasks 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_tasks 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_tasks. 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_tasks 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 →