How to Use the PhantomBuster MCP in Claude

Q: How does Claude Desktop handle large scraped datasets from PhantomBuster?

Your desktop agent uses getphantomoutput to fetch the JSON payload. Claude Desktop parses the lead data directly in your chat, allowing you to clean, filter, or export the results to your local disk.

Q: What tools does this MCP Server expose to my agent?

This MCP Server provides 10 tools including listphantoms, getworkflow, and launchphantom. They allow your agent to manage, execute, and retrieve data from your entire PhantomBuster automation library.

Run PhantomBuster automations and extract lead lists directly inside Claude Desktop without leaving your chat window.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect PhantomBuster MCP to Claude Desktop

Create your Vinkius account to connect PhantomBuster to Claude Desktop and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup PhantomBuster with Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trigger PhantomBuster Agents via Claude Desktop

`launch_phantom` starts your configured PhantomBuster web scrapers directly from the Claude Desktop chat input. You ask your local Claude Desktop window to run a specific LinkedIn scraper, and the tool immediately boots up that agent on PhantomBuster's cloud. If you need to stop a run that is eating up your execution hours, tell Claude Desktop to run `abort_phantom` to kill the process instantly. This gives you desktop-level control over your remote PhantomBuster scraper budget directly inside Claude Desktop.

Extract Scraped Leads Into Claude Desktop

`get_phantom_output` pulls raw JSON results from your completed scraper runs directly into your Claude Desktop chat workspace. Your local Claude Desktop app reads the raw scraped profiles and lets you instantly format the lead data right inside your active chat window. Running `get_phantom_setup` first lets your Claude Desktop agent inspect the exact configuration parameters used for that specific run. This ensures Claude Desktop never processes mismatched lead structures from your remote PhantomBuster scraper.

Monitor Scraping Pipelines via MCP Server

`list_workflows` displays your multi-stage PhantomBuster marketing pipeline inside Claude Desktop so you can verify active automation paths. You get a clean list of active sequences without opening a browser tab to check your PhantomBuster dashboard status inside Claude Desktop. Your Claude Desktop app uses `get_workflow` to pinpoint exactly where a specific lead enrichment sequence is stalled. This MCP Server integration turns your Claude Desktop chat interface into a live command center for your entire PhantomBuster stack.

Setup guide

Set up PhantomBuster MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The PhantomBuster MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the PhantomBuster MCP configuration

Copy the JSON snippet on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under phantombuster-mcp.

json

{
  "mcpServers": {
    "phantombuster-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by PhantomBuster. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect PhantomBuster now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about PhantomBuster MCP in Claude Desktop

Add the phantombuster-mcp configuration block to your local `claude_desktop_config.json` file. Provide your API key as an environment variable, restart Claude Desktop, and your agent can run `list_phantoms` instantly.

Yes. When you ask Claude Desktop to halt an active scraper, it invokes `abort_phantom` via the MCP connection. This stops the PhantomBuster container immediately to prevent unnecessary credit consumption.

Your desktop agent uses `get_phantom_output` to fetch the JSON payload. Claude Desktop parses the lead data directly in your chat, allowing you to clean, filter, or export the results to your local disk.

This MCP Server provides 10 tools including `list_phantoms`, `get_workflow`, and `launch_phantom`. They allow your agent to manage, execute, and retrieve data from your entire PhantomBuster automation library.

Your PhantomBuster API credentials and scraped lead data stay strictly on your local machine. Claude Desktop accesses these secrets through local environment variables configured in your config file, meaning your raw scraper tokens are never exposed to external third-party servers.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript