start_execution

Start a campaign execution without waiting for results.

Start a campaign execution without waiting for results.

Destructive · Writes data · Calls external systems. This tool can modify or delete data. Review the arguments before letting an agent call it.

Parameters

FieldTypeRequiredDescription
campaign_jsonstringYesCampaign JSON template (from build_campaign)
ignore_errorsbooleanNoIgnore failures across all action types (options.ignore_failed = <all action codes>).
overridesstringNoJSON object mapping test IDs to their variable values and owner assignments. Same format as run_campaign overrides.
parallelbooleanNoRun campaign tests in parallel (options.parallel_test_execution=-1). Superadmin-only; the platform rejects test lists that use SIM or SMARTPHONE actions, or sleep on unlocked resources.

Example arguments

Illustrative arguments an agent supplies when calling this tool:

{
  "campaign_json": "string"
}

Description

Returns a result_id for polling. Use this for campaigns that may take longer than 10 minutes, then poll with poll_execution. For shorter campaigns you want to block on, use run_campaign instead.

What's next?

All MCP tools

Browse the full tool reference by category.

Connect a client

Point Claude, Cursor, or Claude Code at the server.

Last updated on