List runs, optionally filtered by namespace, statuses, externalId, and updated-at range.
AI agents call list_runs 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 retrieves and queries existing run data with no side effects. It allows filtering but does not modify, execute code, or trigger external operations. It is a standard read operation typical of state/working memory systems.
From the tool's definition Tool is named 'list_runs' and the description indicates it retrieves/filters runs without any modification: 'List runs, optionally filtered by namespace, statuses, externalId, and updated-at range.' The action verb 'list' and the lack of any…
Attacks that exploit this kind of access
List runs, optionally filtered by namespace, statuses, externalId, and updated-at range. 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_runs: 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_runs 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_runs 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_runs. 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_runs 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 →