PhantomBuster MCP — Connect PhantomBuster to Claude, ChatGPT, and Other AI Assistants

If you're searching for "PhantomBuster MCP", you're asking one of two things: does PhantomBuster have an MCP server? or how do I connect PhantomBuster to an AI assistant via the Model Context Protocol?

✅ PhantomBuster has an official MCP server. Details in the setup section below.

What Is MCP?

Model Context Protocol (MCP) is an open standard developed by Anthropic that lets AI assistants — like Claude — connect to external tools, APIs, and data sources in a standardised way.

Before MCP, every AI integration required bespoke tooling: custom prompts, custom API wrappers, and custom glue code to pass context back and forth. MCP replaces that with a common interface: the AI asks the MCP server for data or actions, the server returns structured results, and the AI uses them to answer your question or complete a task.

In plain terms: MCP is how you give an AI assistant live access to PhantomBuster — not just knowledge about it, but real, up-to-date data from your account.

What a PhantomBuster MCP Integration Does

Once PhantomBuster is connected via MCP, your AI assistant can:

• Read live data — pull records, metrics, activity, and status directly from PhantomBuster
• Take actions — create, update, or log records based on your instructions
• Cross-reference context — combine PhantomBuster data with other connected tools mid-conversation

The key difference from a standard chatbot: the assistant is not working from training data or memory. It is reading your actual PhantomBuster instance, in real time.

Practical PhantomBuster MCP Use Cases

Live prospect lookups

Ask the assistant to look up a company or contact in PhantomBuster mid-conversation and return enriched data: firmographics, signals, and contact details.

Outreach personalisation at scale

Pull signal data from PhantomBuster via MCP and have the assistant generate personalised first lines or talking points for each prospect.

ICP fit scoring from chat

Describe your ICP; the assistant queries PhantomBuster and returns a scored list of accounts that match your criteria.

PhantomBuster MCP: Real Configuration & Setup

PhantomBuster is a cloud-based automation platform that scrapes profiles, extracts contact info, and automates outreach across LinkedIn, Twitter, Instagram, Facebook, and more. With MCP, your AI assistant can control your Phantoms directly — without the manual dashboard check-in loop.

PhantomBuster offers two MCP server options: a centrally-hosted OAuth server managed by PhantomBuster (recommended for teams), and a community npm package for self-hosted setups.

1. Get Your PhantomBuster API Key

For the community MCP server, you'll need an API key:

1. Log into PhantomBuster
2. Go to Workspace Settings → API
3. Copy your API key — it authenticates as the X-Phantombuster-Key header

Security tip: PhantomBuster API keys have full workspace access. Store them in environment variables, never in config files committed to version control.

2. Configure Your MCP Client

Option A: PhantomBuster's official hosted MCP server (recommended)

PhantomBuster maintains a centrally-hosted MCP server at https://mcp.phantombuster.com. It uses OAuth — no API key to copy or paste.

For Claude Desktop:

1. Go to Customize → Connectors
2. Add a custom connector pointing to https://mcp.phantombuster.com
3. You'll be redirected to sign in to PhantomBuster and pick your workspace

For Claude Code:

claude mcp add --transport http phantombuster https://mcp.phantombuster.com

For ChatGPT:

1. Add a custom connector pointing to https://mcp.phantombuster.com
2. Reference: OpenAI Apps SDK — Connect ChatGPT

The official server is the cleanest path. OAuth handles authentication, it stays updated with PhantomBuster's API changes, and there's no local process to manage. The tradeoff: it only exposes a curated subset of the API — the full API surface is larger.

Option B: Community globodai-mcp-phantombuster (self-hosted)

If you prefer running your own server, install the community npm package:

npx -y globodai-mcp-phantombuster

Claude Desktop config:

{
  "mcpServers": {
    "phantombuster": {
      "command": "npx",
      "args": ["-y", "globodai-mcp-phantombuster"],
      "env": {
        "PHANTOMBUSTER_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

This package exposes 9 tools across agent management, container monitoring, and results retrieval:

3. Real Workflow: LinkedIn Profile Extraction → AI Analysis

Here's what makes the MCP connection genuinely useful for sales teams.

Scenario: You're preparing for a call with a prospect and want to check their LinkedIn activity before reaching out.

Without MCP: Log into PhantomBuster, find the LinkedIn Profile Scraper Phantom, configure it with the prospect's URL, launch it, wait for completion, download the CSV, open it, review the data, then draft your talking points separately.

With MCP (via Cody or Claude):

You: "Scrape the LinkedIn profile for Jane Smith at Acme Corp and give me three
personalized talking points based on her recent activity."

AI: "Launching LinkedIn Profile Scraper for Jane Smith... Done. Here's what I found:
- Recently posted about their Series B announcement (2 days ago)
- Commented on 3 AI automation threads this week
- Promoted to VP Sales 4 months ago

Three talking points:
1. Congratulate on the Series B — ask how the team is scaling
2. Mention their AI automation interest — pitch Cody as an AI assistant for their sales stack
3. Reference the VP transition — ask about their new priorities"

This turns a 15-minute manual workflow into a 30-second conversation.

4. Building Dynamic Lead Lists From Chat

PhantomBuster's MCP server can build and update filtered lead lists — the same dynamic lists you'd create in the PhantomBuster dashboard — directly from a prompt.

You: "Create a lead list of all LinkedIn profiles we scraped this week where the
person has 'Head of Sales' in their title and works at a company with 50-200 employees."

AI: "Built list 'Head of Sales — SMB — Jun 21' with 47 leads. Want me to launch
the Email Finder Phantom against this list?"

5. Common Pitfalls

• Platform blocking: LinkedIn, Instagram, and other platforms actively block scrapers. If a Phantom returns errors or empty results, the problem is likely on PhantomBuster's side — not the MCP connection. Check the PhantomBuster dashboard for platform-specific status updates.
• Execution time limits: PhantomBuster plans have execution time caps. Launching multiple large Phantoms via MCP can burn through your monthly allocation fast. Consider adding a confirm step before large launches.
• Agent ID discovery: The MCP server uses agent IDs (not names) to target Phantoms. If you don't know the IDs, first have your AI assistant run list_agents to build the mapping — then reference by name in your skill file.
• Output size: Some Phantoms extract thousands of rows from LinkedIn Sales Navigator or Twitter. Full CSV output into a chat message isn't practical. Configure your skill file to have the assistant summarize or filter results rather than dumping raw data.
• OAuth workspace binding: The official hosted server only works within one PhantomBuster workspace at a time. If your team uses multiple workspaces, you'll need to reconnect to switch.

6. PhantomBuster + Other Sales Tools

PhantomBuster MCP is most powerful when combined with your other sales tools. A typical outreach stack:

LinkedIn → PhantomBuster (scrape profiles)
   ↓
Hunter.io MCP (find emails)
   ↓
Apollo.io MCP (enrich with firmographics)
   ↓
Slack MCP (notify sales team)

With all tools connected via MCP, your AI assistant can orchestrate the entire pipeline: scrape → enrich → notify — in one conversation.

How to Connect PhantomBuster via MCP

There are two main paths:

Option A: Use PhantomBuster's official MCP server

PhantomBuster maintains an official PhantomBuster MCP server. This is the recommended starting point — it's built and maintained by the PhantomBuster team, so it stays up to date with API changes.

Note: Two deployment options: PhantomBuster's centrally-hosted OAuth MCP server (https://mcp.phantombuster.com), or the community globodai-mcp-phantombuster npm package for self-hosted setups.

What the server exposes:

• agent management
• execution monitoring
• results retrieval
• lead search & filtering
• dynamic list building
• workspace exploration

What you'll need:

• An MCP-compatible client (Claude Desktop, OpenClaw, or another host)
• PhantomBuster credentials configured per the server's setup guide

This path gives you the most control but requires you to handle client configuration and credential management yourself.

Option B: Use Cody (OpenClaw-based, managed)

Cody is built on OpenClaw and supports MCP-compatible integrations out of the box. You connect PhantomBuster once from the Cody dashboard — no server to run, no code to write — and Cody handles authentication, context passing, and write-back actions with appropriate guardrails.

Cody works where your team already operates: Slack, Telegram, or the web chat. The PhantomBuster connection is available to your entire team without each person setting up their own MCP client.

MCP vs Other AI Integration Patterns

MCP wins when you need live data from PhantomBuster and want to avoid rebuilding integrations as APIs change.

Common Mistakes

• Using training data when live data is needed — if the AI doesn't have an MCP connection, it will answer from memory, which is often outdated or wrong for account-specific questions
• No write-back guardrails — MCP can write to PhantomBuster, so it's worth adding an approval step for any action that modifies records
• Too many tools exposed at once — give the AI access to the PhantomBuster actions it actually needs; a scoped connection is easier to reason about and audit
• Skipping structured outputs — ask the AI to return structured JSON or clear fields when writing back to PhantomBuster; free-form output is harder to validate

Related MCP Guides

• Apollo.io MCP
• Clay MCP
• LinkedIn MCP

Want the full workflow picture? See: PhantomBuster AI Automation and How to Connect PhantomBuster to OpenClaw.