PHANTOMBUSTER n8n INTEGRATION: AUTOMATE PHANTOMBUSTER WITH N8N

This is arguably the most critical action in the Phantombuster n8n integration—it lets you programmatically start any of your Phantombuster agents directly from your workflow. Instead of scheduling agents within Phantombuster or manually clicking "Launch," you can trigger them based on any event: a new row in Google Sheets, an incoming webhook, a form submission, or a scheduled time.

Key parameters:

• Agent Name or ID: This required text field specifies which agent to launch. You can use either the human-readable agent name or the unique agent ID (found in your Phantombuster dashboard URL). Using the ID is more reliable if you tend to rename agents.
• Resolve Data: This toggle switch, when enabled, tells n8n to wait for the agent to complete and return its processed output. Enable this when you need the extracted data immediately in subsequent workflow steps. Disable it for fire-and-forget scenarios where you'll retrieve results later.
• JSON Parameters: An optional toggle that, when enabled, reveals a field for passing additional parameters to your agent as a JSON object. This is powerful for dynamic inputs—for example, passing a list of LinkedIn URLs to scrape rather than hardcoding them in the agent configuration.
• Additional Fields: Optional key-value pairs for advanced agent configurations specific to certain Phantombuster phantoms.

Typical use cases:

• Trigger a LinkedIn profile scraper whenever a new lead is added to your CRM
• Launch an Instagram follower extractor when a specific Slack command is received
• Run a Twitter scraper on a daily schedule and compile results into a report
• Dynamically pass search URLs to a Sales Navigator agent based on incoming webhook data

When to use it: Whenever you need to initiate data extraction or automation tasks in Phantombuster as part of a larger workflow. This action is your primary interface for controlling Phantombuster's execution.

Once your Phantombuster agent has finished running, the Get Output action retrieves the extracted data and brings it into your n8n workflow for further processing. This is essential for building end-to-end automation pipelines where Phantombuster is the data source.

Key parameters:

• Agent Name or ID: A required text field identifying which agent's output to retrieve. Use the same identifier you would for launching the agent.
• Resolve Data: When this toggle is enabled, n8n processes and structures the raw output from Phantombuster into a more usable JSON format. This is highly recommended for most use cases, as it makes the data easier to map to subsequent nodes.
• Additional Fields: Optional parameters that may include filters or date ranges for retrieving specific output batches, depending on the agent type.

Typical use cases:

• Retrieve LinkedIn profile data after a scraping agent completes and push enriched contacts to HubSpot
• Pull extracted email addresses and add them to your Mailchimp audience
• Fetch scraped company data and update corresponding records in Airtable
• Combine outputs from multiple agents into a single consolidated dataset

When to use it: Pair this action with "Launch Agent" (with Resolve Data disabled) when you want to separate the launch and retrieval steps—useful for long-running agents or when you need to process results at a different time.

This action retrieves a list of all agents configured in your Phantombuster account. It's perfect for building dashboards, auditing your agent inventory, or creating dynamic workflows that adapt based on available agents.

Key parameters:

• Return All: A toggle switch that, when enabled, fetches every single agent in your account regardless of the limit setting. Enable this for complete inventory exports; disable it for paginated or limited retrieval.
• Limit: A number field (default: 25) that caps how many agents are returned when "Return All" is disabled. Useful for sampling or when you only need to check a subset of agents.

Typical use cases:

• Generate a daily report of all active agents and their last run status
• Build a monitoring workflow that checks agent configurations for consistency
• Create a cleanup automation that identifies and flags agents that haven't run recently
• Dynamically populate a dropdown in a Slack command with available agent names

When to use it: Ideal for administrative and monitoring workflows rather than day-to-day data extraction. Use this action when you need visibility into your Phantombuster infrastructure.

While "Get Many Agents" retrieves your full agent list, this action fetches detailed information about a single specific agent. Use it when you need to check an agent's configuration, status, or metadata before taking action.

Key parameters:

• Agent ID: A required text field specifying the unique identifier of the agent to retrieve. You can use either a fixed value or an expression to dynamically reference agents from previous workflow steps.

Typical use cases:

• Verify an agent exists and is properly configured before attempting to launch it
• Check the last run timestamp to determine if fresh data is available
• Retrieve agent settings to log or audit configurations
• Conditionally branch your workflow based on agent status

When to use it: Use this action as a preliminary check in complex workflows, especially when dealing with dynamically selected agents or when you need to validate state before proceeding.

This action permanently removes an agent from your Phantombuster account. It's powerful for housekeeping and automating the cleanup of temporary or obsolete agents, but use it with caution—deleted agents cannot be recovered.

Key parameters:

• Agent Name or ID: A required text field specifying which agent to delete. Double-check this value, especially when using dynamic expressions, as deletion is irreversible.

Typical use cases:

• Automatically clean up temporary agents created for one-time scraping tasks
• Remove agents that haven't been used in 60+ days as part of a monthly maintenance workflow
• Delete test agents after a QA workflow completes
• Implement a self-destructing agent pattern for sensitive or time-limited data extraction

When to use it: Reserve this action for maintenance and cleanup workflows. Always include confirmation logic or safeguards (like checking agent age or last run date) before automating deletions to avoid accidentally removing active agents.