Inbound MCP

潜在客户开发服务器文档

目录

1. 概述
2. 特性
3. 建筑
4. 先决条件
5. 安装
6. 配置
7. 运行服务器
8. API文档
9. 例子
10. 高级配置
11. 故障排除
12. 贡献
13. 许可证
14. 路线图
15. 支持

______________________________________________________________________

概述

建立在以下基础上的生产级潜在客户开发系统：

• MCP Python SDK 用于符合协议的人工智能服务
• Crawl4AI 用于智能网络爬行
• 异步IO 用于高并发操作

通过以下方式实施从发现到丰富的完整潜在客户生命周期：

• 基于UUID的潜在客户跟踪
• 多源数据聚合
• 智能缓存策略
• 企业级错误处理

______________________________________________________________________

特性

______________________________________________________________________

建筑

graph TD
    A[Client] --> B[MCP Server]
    B --> C{Lead Manager}
    C --> D[Google CSE]
    C --> E[Crawl4AI]
    C --> F[Hunter.io]
    C --> G[Clearbit]
    C --> H[LinkedIn Scraper]
    C --> I[(Redis Cache)]
    C --> J[Lead Store]

______________________________________________________________________

先决条件

• Python 3.10+
• API密钥：

  export HUNTER_API_KEY="your_key"
  export CLEARBIT_API_KEY="your_key"
  export GOOGLE_CSE_ID="your_id"
  export GOOGLE_API_KEY="your_key"

• LinkedIn会话Cookie（用于抓取）
• 4GB+RAM（建议使用8GB进行大量刮擦）

______________________________________________________________________

安装

生产设置

# Create virtual environment
python -m venv .venv && source .venv/bin/activate

# Install with production dependencies
pip install mcp crawl4ai[all] aiocache aiohttp uvloop

# Set up browser dependencies
python -m playwright install chromium

Docker部署

FROM python:3.10-slim

RUN apt-get update && apt-get install -y \
    gcc \
    libpython3-dev \
    chromium \
    && rm -rf /var/lib/apt/lists/*

COPY . /app
WORKDIR /app

RUN pip install --no-cache-dir -r requirements.txt
CMD ["python", "-m", "mcp", "run", "lead_server.py"]

______________________________________________________________________

配置

config.yaml

services:
  hunter:
    api_key: ${HUNTER_API_KEY}
    rate_limit: 50/60s
    
  clearbit:
    api_key: ${CLEARBIT_API_KEY}
    cache_ttl: 86400

scraping:
  stealth_mode: true
  headless: true
  timeout: 30
  max_retries: 3

cache:
  backend: redis://localhost:6379/0
  default_ttl: 3600

______________________________________________________________________

运行服务器

发展模式

mcp dev lead_server.py --reload --port 8080

生产

gunicorn -w 4 -k uvicorn.workers.UvicornWorker lead_server:app

码头工人

docker build -t lead-server .
docker run -p 8080:8080 -e HUNTER_API_KEY=your_key lead-server

______________________________________________________________________

API文档

1.产生潜在客户

POST /tools/lead_generation
Content-Type: application/json

{
  "search_terms": "OpenAI"
}

答复：

{
  "lead_id": "550e8400-e29b-41d4-a716-446655440000",
  "status": "pending",
  "estimated_time": 15
}

2.丰富铅

POST /tools/data_enrichment
Content-Type: application/json

{
  "lead_id": "550e8400-e29b-41d4-a716-446655440000"
}

3.监控线索

GET /tools/lead_maintenance

______________________________________________________________________

例子

Python客户端

from mcp.client import Client

async with Client() as client:
    # Generate lead
    lead = await client.call_tool(
        "lead_generation",
        {"search_terms": "Anthropic"}
    )
    
    # Enrich with all services
    enriched = await client.call_tool(
        "data_enrichment",
        {"lead_id": lead['lead_id']}
    )
    
    # Get full lead data
    status = await client.call_tool(
        "lead_status",
        {"lead_id": lead['lead_id']}
    )

卷曲

# Generate lead
curl -X POST http://localhost:8080/tools/lead_generation \
  -H "Content-Type: application/json" \
  -d '{"search_terms": "Cohere AI"}'

______________________________________________________________________

高级配置

缓存策略

from aiocache import Cache

# Configure Redis cluster
Cache.from_url(
    "redis://cluster-node1:6379/0",
    timeout=10,
    retry=True,
    retry_timeout=2
)

速率限制

from mcp.server.middleware import RateLimiter

mcp.add_middleware(
    RateLimiter(
        rules={
            "lead_generation": "100/1m",
            "data_enrichment": "50/1m"
        }
    )
)

______________________________________________________________________

故障排除

______________________________________________________________________

贡献

1. 分叉存储库
2. 创建要素分支： git checkout -b feature/new-enrichment
3. 提交更改： git commit -am 'Add Clearbit alternative'
4. 推送到分支： git push origin feature/new-enrichment
5. 提交拉取请求

______________________________________________________________________

许可证

Apache 2.0-请参阅 许可证 了解详情。

______________________________________________________________________

路线图

• \[ \] 2025年第二季度：AI驱动的领先评分
• \[ \] 2025年第3季度：分布式爬行集群支持

______________________________________________________________________

支持

对于企业支持和自定义集成：\ 📧 电子邮件： hi@kobotai.co\ 🐦 推特： @KobotAIco

______________________________________________________________________

# Run benchmark tests
pytest tests/ --benchmark-json=results.json