globodai-mcp-phantombuster
A Model Context Protocol (MCP) server that provides tools to interact with the PhantomBuster automation platform, enabling agent management, execution monitoring, and result retrieval through MCP-compatible AI assistants.
README
MCP Server for PhantomBuster
A Model Context Protocol (MCP) server that provides tools to interact with the PhantomBuster automation platform. Manage your agents (phantoms), monitor executions, and retrieve results — all through MCP-compatible AI assistants.
Features
- 🤖 Agent Management — List, get, launch, stop, and delete agents
- 📦 Container Monitoring — List and inspect execution containers
- 📊 Results Retrieval — Get agent output and structured result objects
- 🔒 Secure — API key via environment variable, never hardcoded
Quick Start
Using npx (recommended)
No installation required:
npx globodai-mcp-phantombuster
Install globally
npm install -g globodai-mcp-phantombuster
mcp-phantombuster
Configuration
Environment Variable
Set your PhantomBuster API key:
export PHANTOMBUSTER_API_KEY="YOUR_API_KEY"
📝 Get your API key from PhantomBuster Workspace Settings
Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"phantombuster": {
"command": "npx",
"args": ["-y", "globodai-mcp-phantombuster"],
"env": {
"PHANTOMBUSTER_API_KEY": "YOUR_API_KEY"
}
}
}
}
Cursor
Add to your Cursor MCP settings:
{
"mcpServers": {
"phantombuster": {
"command": "npx",
"args": ["-y", "globodai-mcp-phantombuster"],
"env": {
"PHANTOMBUSTER_API_KEY": "YOUR_API_KEY"
}
}
}
}
Available Tools
Agent Tools
| Tool | Description |
|---|---|
phantombuster_list_agents |
List all agents in your organization |
phantombuster_get_agent |
Get details of a specific agent by ID |
phantombuster_launch_agent |
Launch an agent (add to queue), with optional arguments |
phantombuster_stop_agent |
Stop a running agent |
phantombuster_delete_agent |
Permanently delete an agent |
Container Tools
| Tool | Description |
|---|---|
phantombuster_list_containers |
List all containers (runs) for an agent |
phantombuster_get_container |
Get details of a specific container |
Result Tools
| Tool | Description |
|---|---|
phantombuster_get_agent_output |
Get console output from the latest execution |
phantombuster_get_container_result |
Get structured result data from a container |
Usage Examples
List all your agents
"List all my PhantomBuster agents"
Launch an agent with custom arguments
"Launch PhantomBuster agent 12345 with argument: {"search": "AI startups"}"
Monitor an execution
"What's the output of agent 12345? Is it still running?"
Get results from a run
"Get the results from container abc123"
Development
# Clone the repository
git clone https://github.com/globodai-group/mcp-phantombuster.git
cd mcp-phantombuster
# Install dependencies
npm install
# Run in development mode
PHANTOMBUSTER_API_KEY="YOUR_API_KEY" npm run dev
# Build
npm run build
# Type check
npm run lint
API Reference
This MCP server wraps the PhantomBuster API v2:
- Base URL:
https://api.phantombuster.com/api/v2 - Auth:
X-Phantombuster-Keyheader - Full API Documentation
Contributing
Contributions are welcome! Please open an issue or submit a pull request.
License
Built with ❤️ by GlobodAI
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。