Skip to main content
n8n is a workflow automation platform that includes advanced AI capabilities built on LangChain. You can connect your n8n instance to LangSmith to record and monitor AI workflow runs.
LangSmith tracing is available for self-hosted n8n instances only.
This integration uses a legacy destination setting such as project_name or LANGSMITH_PROJECT. Create an agent, choose its environment, and retrieve that environment’s tracer_session_name. Use that returned value in the destination setting and any overrides. For integrations that support agent addressing, use the agent identifier and environment directly.

​
Prerequisites

​
Set up tracing

  1. Set the following environment variables in the environment where you host your n8n instance, in the same way as the rest of your n8n configuration. Required environment variables:
    • LANGCHAIN_TRACING_V2: Set to true to enable tracing.
    • LANGCHAIN_API_KEY: Your LangSmith API key.
    Optional environment variables:
    • LANGCHAIN_ENDPOINT: LangSmith API endpoint. Defaults to https://api.smith.langchain.com. Set this if using self-hosted LangSmith, GCP EU (https://eu.api.smith.langchain.com), GCP APAC (https://apac.api.smith.langchain.com), or AWS US (https://aws.api.smith.langchain.com).
    • LANGCHAIN_PROJECT: Set to the selected agent environment’s tracer_session_name. If omitted, the integration uses "default".
    • LANGCHAIN_CALLBACKS_BACKGROUND: Set to true for asynchronous trace upload (default), or false for synchronous uploads. (default: true)
  2. Restart your n8n instance for the environment variables to take effect.

​
View traces in LangSmith

After running an AI workflow:
  1. Open LangSmith.
  2. Select the agent and environment whose tracer_session_name you configured in LANGCHAIN_PROJECT.
  3. Locate the trace corresponding to your workflow execution.

​
Additional resources

Connect these docs to your agent of choice via MCP for real-time answers.
Edit this page on GitHub or file an issue.