List the append-only event log for a run.
AI agents call list_run_events 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 only retrieves historical event data from an immutable log. It has no side effects, does not execute code, and cannot modify or delete data. The append-only nature ensures the underlying log cannot be altered through this interface. Classification as Read is appropriate.
From the tool's definition 'List the append-only event log for a run' — retrieves and queries event log data without modifying state. The 'list' prefix and 'append-only' description confirm this is a read-only operation.
Attacks that exploit this kind of access
List the append-only event log for a run. 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_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 State Trace. Nothing to install.
list_run_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_run_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_run_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_run_events 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.
list_run_events is one line of State Trace's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →