Lead Gen MCP Server
A free MCP server that runs a full B2B outbound pipeline inside a Claude conversation, enabling lead scraping, Google Sheets integration, and Instantly campaign creation.
README
Lead Gen MCP Server
A free MCP server that runs a full B2B outbound pipeline inside a Claude conversation.
Type one sentence. Get scraped leads → Google Sheet → Instantly campaign, all without leaving your chat.
You: Scrape 30 HVAC companies in Austin TX, create a campaign called
"HVAC Austin | Free Audit", and push the leads.
Claude: Done.
→ 28 qualified leads saved: https://docs.google.com/spreadsheets/d/...
→ Campaign created (ID: a1b2c3)
→ 28 leads uploaded. Ready to launch in Instantly.
What it does
| Tool | Description |
|---|---|
scrape_leads |
Google Maps → qualified leads → Google Sheet (via Apify) |
read_sheet |
Load leads from any existing Google Sheet |
create_instantly_campaign |
Create a new Instantly email campaign, returns campaign ID |
push_to_instantly |
Upload leads array to an Instantly campaign |
Prerequisites
- Python 3.11+
- Apify account + API token (for Google Maps scraping)
- Instantly account + API v2 key (for email campaigns)
- Google Cloud project with OAuth credentials (for Google Sheets)
Install
git clone https://github.com/Sourav333444/lead-gen-mcp
cd lead-gen-mcp
python -m venv .venv
.venv\Scripts\activate # Windows
# source .venv/bin/activate # Mac/Linux
pip install "mcp[cli]" apify-client gspread google-auth google-auth-oauthlib requests python-dotenv
Configure
Create a .env file in the project root:
APIFY_API_TOKEN=apify_api_...
INSTANTLY_API_KEY=your_instantly_v2_key
Google Sheets auth (one-time)
Download OAuth credentials from Google Cloud Console → APIs & Services → Credentials → Create OAuth 2.0 Client ID (Desktop app). Save as credentials.json in the project root.
Then run:
python -c "
from google_auth_oauthlib.flow import InstalledAppFlow
flow = InstalledAppFlow.from_client_secrets_file('credentials.json', [
'https://www.googleapis.com/auth/spreadsheets',
'https://www.googleapis.com/auth/drive'
])
creds = flow.run_local_server(port=0)
open('token.json', 'w').write(creds.to_json())
"
This saves token.json — you won't need to do this again unless the token expires.
Connect to Claude Code
Add to your .mcp.json in the project root:
{
"mcpServers": {
"lead-gen-toolkit": {
"command": "/absolute/path/to/.venv/bin/python",
"args": ["/absolute/path/to/server.py"]
}
}
}
On Windows:
{
"mcpServers": {
"lead-gen-toolkit": {
"command": "C:\\path\\to\\.venv\\Scripts\\python.exe",
"args": ["C:\\path\\to\\server.py"]
}
}
}
Restart Claude Code. Run /mcp to confirm lead-gen-toolkit is connected.
Usage
Once connected, just talk to Claude:
Scrape 30 roofing contractors in Denver CO and save to a sheet called "Denver Roofers"
Read the leads from [sheet URL] and push them to Instantly campaign [campaign_id]
Create an Instantly campaign called "Plumbers NYC | Free Estimate" and give me the campaign ID
Cost
| Component | Cost |
|---|---|
| Apify Google Maps | ~$0.01–0.02 per lead |
| Instantly | your plan's sending limits |
| Google Sheets | free |
100 leads ≈ $1.50–2.50 total.
File structure
server.py # MCP server (the thing you're installing)
execution/
gmaps_lead_pipeline.py # Google Maps scraper + Sheet writer
.env # Your API keys (never commit this)
credentials.json # Google OAuth credentials (never commit this)
token.json # Google OAuth token (never commit this)
Troubleshooting
"Google token is missing or expired" — re-run the auth command above.
"INSTANTLY_API_KEY not set" — add your key to .env. Get it from Instantly → Settings → Integrations → API Keys → select all:all scope.
Apify scrape returns 0 results — include the city in your query: "HVAC in Austin TX" not just "HVAC".
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。