Skip to main content
A single EngineConfig controls every aspect of your agent service. Define it as a YAML file or fetch it from the manager API. The structure is identical in both cases.

​
Complete config example

server:
  api:
    port: 8001

agent:
  type: "LANGGRAPH"
  config:
    name: "Support Agent"
    graph_definition: "./agent.py:graph"
    checkpointer:
      type: "sqlite"
      db_url: "sqlite:///checkpoints.db"

observability:
  - provider: "LANGFUSE"
    enabled: true
    config:
      host: "https://cloud.langfuse.com"
      public_key: "${LANGFUSE_PUBLIC_KEY}"
      secret_key: "${LANGFUSE_SECRET_KEY}"

guardrails:
  input:
    - config_id: "DETECT_PII"
      on_fail: "reject"
      reject_message: "Request contains personal information."
  output:
    - config_id: "TOXIC_LANGUAGE"
      on_fail: "reject"

mcp_servers:
  - name: "time"
    transport: "stdio"
    command: "docker"
    args: ["run", "-i", "--rm", "mcp/time"]

prompts:
  - prompt_id: "system-prompt"
    version: 1
    content: "You are a support agent for {{ company_name }}."
    tags: ["latest"]

sso:
  enabled: true
  issuer: "https://accounts.google.com"
  client_id: "123456789.apps.googleusercontent.com"
  allowed_domains: ["yourcompany.com"]

integrations:
  - provider: "WHATSAPP"
    enabled: true
    config:
      access_token: "${WHATSAPP_ACCESS_TOKEN}"
      phone_number_id: "${WHATSAPP_PHONE_ID}"
      verify_token: "${WHATSAPP_VERIFY_TOKEN}"
Values support ${ENV_VAR} syntax for referencing environment variables at load time.

​
Config sections

server — HTTP server binding. Exposes api.port (default: 8000). CORS allows all origins. The engine adds Access-Control-Allow-Private-Network: true so hosted UIs can reach local agents. agent — Framework type and framework-specific settings. The config fields change based on the type value. Supported types: LANGGRAPH, ADK. See the frameworks overview for per-framework config details. For LangGraph, provide an uncompiled StateGraph via graph_definition (path/to/file.py:variable_name). The engine compiles it with the configured checkpointer. observability — A list of providers, each with provider, enabled, and config. Multiple providers can be active simultaneously. Supported: LANGFUSE, PHOENIX, GCP_TRACE, GCP_LOGGING, LANGSMITH. See observability guides. guardrails — Split into input (validated before invocation) and output (validated after). Uses Guardrails AI Hub guards, downloaded and run locally. Available guards: BAN_LIST, DETECT_PII, NSFW_TEXT, COMPETITION_CHECK, BIAS_CHECK, CORRECT_LANGUAGE, GIBBERISH_TEXT, TOXIC_LANGUAGE, RESTRICT_TO_TOPIC. See guardrails reference. mcp_servers — Model Context Protocol servers that provide tools to your agent. Supports stdio, sse, streamable_http, and websocket transports. See tool governance. prompts — Versioned prompt templates with Jinja2 variable support ({{ variable }}). Each entry has prompt_id, version, content, and tags. sso — OIDC JWT validation on agent endpoints. When enabled, requests to /agent/run must include a valid token. Supports allowed_domains and allowed_emails filtering. See authentication overview. integrations — Messaging platform connections. Each integration adds webhook endpoints to the engine. Supported: WHATSAPP, DISCORD. checkpointer (inside agent.config for LangGraph) — Conversation memory. Types: memory (in-process), sqlite, postgres. For ADK, use session_service and memory_service instead. See memory guides.

​
Config sources

Open an agent and go to the Configuration tab. This shows the full materialized engine config that the agent receives from the platform when it connects.Toggle between JSON and YAML views. Use the Copy button to grab the config for local testing or debugging. Note that ${ENV_VAR} references aren’t resolved here; the engine resolves them at load time.Agent detail Configuration tab

​
Environment variables

VariablePurpose
IDUN_AGENT_API_KEYAPI key for fetching config from the manager
IDUN_MANAGER_HOSTManager API base URL
IDUN_CONFIG_PATHPath to config.yaml (alternative to --path flag)
IDUN_TELEMETRY_ENABLEDSet to false to disable anonymous usage telemetry
The engine resolves ${VAR_NAME} references in YAML values at config load time, so you can keep secrets out of your config files.
Last modified on March 22, 2026