Create a durable run that groups tasks. Optionally seeds an initial context snapshot.
AI agents use create_run to create or update resources in State Trace — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your State Trace environment.
This tool creates new data structures in the state-trace system but does not delete, overwrite irreversibly, move money, or execute external code. It is reversible (runs can be cancelled via cancel_run and deleted via other cleanup mechanisms), making it a Write rather than Destructive operation.
From the tool's definition Tool description states 'Create a durable run' — the verb 'create' indicates data creation, which is a write operation. The tool constructs a new persistent object (a run) that groups tasks and may initialize context snapshots.
Attacks that exploit this kind of access
Create a durable run that groups tasks. Optionally seeds an initial context snapshot. It is categorised as a Write tool in the State Trace MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the State Trace MCP server in PolicyLayer and add a rule for create_run: 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.
create_run is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_run 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 create_run. 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.
create_run 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 →