List all tasks in a run, ordered by priority and creation time.
AI agents call list_run_tasks to retrieve information from State Trace without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns task information without modifying, deleting, or executing anything. It is a passive data retrieval operation typical of read-category tools. The ordering by priority and creation time is metadata presentation, not a mutation. Low severity because listing tasks poses minimal risk even if misused by an agent.
From the tool's definition Tool name 'list_run_tasks' and description 'List all tasks in a run' indicate data retrieval with no side effects. The verb 'list' is a quintessential read operation.
Attacks that exploit this kind of access
List all tasks in a run, ordered by priority and creation time. It is categorised as a Read tool in the State Trace MCP Server, which means it retrieves data without modifying state.
Register the State Trace MCP server in PolicyLayer and add a rule for list_run_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 State Trace. Nothing to install.
list_run_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_run_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_run_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_run_tasks is provided by the State Trace MCP server (agent-pattern-labs/state-trace). 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 →