Configuration Schema

servers[ ]

• id (string, required) — unique identifier used in scenario server lists.
• transport (string, required) — connection type. Use "http" for HTTP/SSE.
• url (string, required) — full URL of the MCP endpoint.
• token (string, optional) — bearer token for authentication. Use a literal string or $ENV_VAR to read from the environment.

agents[ ]

• id (string, required) — unique identifier referenced by scenarios.
• provider (string, required) — LLM provider. One of: anthropic, openai, azure.
• model (string, required) — model identifier as used by the provider API.
• temperature (number, optional) — sampling temperature. Defaults to 0.

scenarios[ ]

• Inline scenario: `id`, `prompt`, optional `name`, optional `mcp_servers`, optional `eval` and `extract`.
• Referenced scenario: `ref` with optional `mcp_servers` override.
• `mcp_servers` entries can be `{ ref: <server-id> }` or inline server objects.
• Legacy top-level `servers` pool is deprecated; prefer scenario-owned `mcp_servers`.

eval.tool_constraints and eval.response_assertions

• tool_constraints.required_tools (string[], optional) — tool names the agent must call.
• tool_constraints.forbidden_tools (string[], optional) — tool names the agent must not call.
• response_assertions supports: contains, not_contains, starts_with, ends_with, equals, regex, jsonpath, jsonpath_exists, jsonpath_not_exists.
• For detailed examples of each assertion, see Reference / Tool and Response Assertions.

Reference Syntax

Use `ref` inside `agents` and `scenarios` list items to pull from library ids.

agents:
  - ref: claude-sonnet-46

scenarios:
  - ref: add-calculations
    mcp_servers:
      - ref: kpi-api-prod