How to Install and Use n8n in OpenClaw

Open your terminal and run the ClawHub install command. ClawHub is OpenClaw's official skill registry — the single-command way to add capabilities to your OpenClaw instance. The n8n skill installs the ability to communicate with your n8n instance's REST API directly from OpenClaw chat. After installation, the skill registers itself with OpenClaw and shows you which configuration keys it requires. The two required keys are N8N_BASE_URL (the URL of your n8n instance) and N8N_API_KEY (a personal API key generated in n8n settings). The skill will not activate until both are configured — attempting to use it early will produce a clear error pointing to the missing credentials. If the install command fails with `clawhub: command not found`, verify that OpenClaw is fully installed and that the ClawHub binary is on your system PATH. On macOS/Linux this is typically `/usr/local/bin/clawhub` or `~/.openclaw/bin/clawhub`.

1clawhub install n8n

Before configuring OpenClaw, you need to enable the REST API in your n8n instance and generate a personal API key. Log in to your n8n instance — either at your self-hosted URL or at app.n8n.cloud. Navigate to Settings (gear icon in the lower-left sidebar) > API. Toggle 'Enable API' to on. This enables n8n's built-in REST API, which the OpenClaw skill uses to communicate with your instance. Scroll down to the 'API Keys' section and click 'Create an API key'. Give it a descriptive name like 'OpenClaw Integration'. n8n generates the key immediately — it starts with `n8n_api_`. Copy the full key now. Like most API keys, n8n may not display the full key again after you navigate away, though you can always generate a new one. For self-hosted n8n instances, make sure your instance is accessible from the machine running OpenClaw. If n8n is on the same machine, the URL is typically `http://localhost:5678`. If it is on a remote server, use the server's IP or domain name with port 5678 (or whichever port you configured). Note your n8n base URL — this is your N8N_BASE_URL. Do not include a trailing slash.

With your credentials ready, add them to OpenClaw's configuration. The recommended approach is to set both values in your OpenClaw `.env` file at `~/.openclaw/.env`, or use the `clawhub config set` command for a guided experience. N8N_BASE_URL should be the root URL of your n8n instance without a trailing slash — for example `http://localhost:5678` or `https://myorg.app.n8n.cloud`. The skill appends the correct API path (`/api/v1`) automatically, so do not include the API path in the base URL. After saving the configuration, run `clawhub reload` to apply the changes. OpenClaw will validate the credentials on first use by making a test request to the n8n `/api/v1/workflows` endpoint. If the credentials are correct, you will see a count of active workflows in the OpenClaw log.

1# Option A: Add to ~/.openclaw/.env
2N8N_BASE_URL=http://localhost:5678
3N8N_API_KEY=n8n_api_your-api-key-here
4
5# Option B: Set via clawhub config commands
6clawhub config set N8N_BASE_URL http://localhost:5678
7clawhub config set N8N_API_KEY n8n_api_your-api-key-here
8
9# Verify both are set
10clawhub config get N8N_BASE_URL
11clawhub config get N8N_API_KEY

Open OpenClaw chat and test the connection by asking it to list your active workflows. This confirms the skill can authenticate with your n8n instance and retrieve workflow data. The n8n skill recognizes natural language instructions for the most common operations: listing workflows, triggering a workflow by name or ID, checking the status of a specific execution, and listing recent executions with their outcomes. For triggering workflows, the skill matches your description against workflow names in your n8n instance. If you have a workflow named 'Send Weekly Report', asking OpenClaw to 'trigger the weekly report workflow' is sufficient — the skill fuzzy-matches the name. For exact targeting, you can provide the workflow ID directly. Note that n8n workflows must be active (not in draft/inactive state) to be triggered via the API. If a workflow is inactive, the API returns a 400 error. Activate workflows in the n8n dashboard before attempting to trigger them from OpenClaw.

Once you have triggered a workflow, you can ask OpenClaw to monitor the execution and report back the result. The n8n skill polls the execution status endpoint and surfaces success or failure information, including error messages from failed nodes. For long-running workflows, the skill supports both synchronous waiting (OpenClaw waits for completion before responding) and asynchronous checking (trigger the workflow and ask for status later). For workflows expected to run longer than 30 seconds, asynchronous mode is recommended to avoid timeouts in the OpenClaw chat interface. You can also configure the skill to proactively alert you when a monitored workflow fails. This is set in the skill's YAML config file and uses OpenClaw's internal notification system. RapidDev recommends this for production workflows where failures need immediate attention — it turns OpenClaw into a lightweight workflow monitoring dashboard without requiring a separate alerting tool. The skill stores the last N execution results in memory so you can ask follow-up questions like 'what was the output of the last execution of that workflow?' without re-triggering it.

1# ~/.openclaw/skills/n8n.yaml — optional advanced configuration
2n8n:
3  base_url: "http://localhost:5678"  # Can also be set via N8N_BASE_URL env var
4  api_key: ""                         # Set via N8N_API_KEY env var (leave blank here)
5  execution_wait_timeout: 30          # Seconds to wait for execution before going async
6  max_executions_history: 20          # Number of recent executions to cache
7  alert_on_failure: true              # Notify in OpenClaw when a monitored workflow fails
8  ssl_verify: true                    # Set false only for self-signed certs on private networks