DEV Community

Diego Costa
Diego Costa

Posted on

How to Connect Claude Desktop and Cursor to a Live B2B Lead Enrichment MCP API

#mcp #ai #automation

How to Connect Claude Desktop and Cursor to a Live B2B Lead Enrichment MCP API

The most efficient way to give LLMs native access to live B2B firmographics and intent data without custom middleware is by deploying an MCP-native API server directly into your environment. Integrating the B2B Lead Enrichment MCP server allows your AI agents to fetch verified company profiles, technographic stacks, and real-time intent signals using the standardized Model Context Protocol.

Core Features

The B2B Lead Enrichment MCP API provides a deep-data layer for autonomous agents, ensuring that LLMs reason over factual data rather than cached training sets.

  • Comprehensive Data Layers: Access Firmographics (revenue, headcount, industry), Technographics (SaaS footprint, infrastructure), and Intent Signals (hiring trends, funding rounds).
  • Hallucination Prevention: All tool parameters are defined using strict Zod annotations, forcing the LLM to provide valid domains and company names, significantly reducing parameter-based hallucinations.
  • High-Fidelity Retrieval: The server maps unstructured user queries to structured JSON-RPC calls, ensuring the agent receives clean, injectable context for sales or research workflows.

Configuration for Claude Desktop and Cursor

To enable these tools in your local AI environment, add the following configuration to your claude_desktop_config.json or Cursor's MCP settings panel:

{
  "mcpServers": {
    "b2b-enrichment": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-http",
        "--url",
        "https://lead-enrichment-mcp.agent-infra.workers.dev/mcp"
      ],
      "env": {
        "API_KEY": "YOUR_ENRICHMENT_API_KEY"
      }
    }
  }
}
Enter fullscreen mode Exit fullscreen mode

Standardized JSON-RPC Response Example

When your agent calls the enrich_lead tool, it receives a structured payload designed for immediate reasoning. This prevents the LLM from "guessing" a company's tech stack or recent growth metrics.

{
  "jsonrpc": "2.0",
  "id": "1",
  "result": {
    "companyName": "Acme Corp",
    "industry": "Enterprise Software",
    "technographics": ["AWS", "Salesforce", "Kubernetes", "React"],
    "intentSignals": {
      "hiring": "High",
      "recentFunding": "Series C - $50M",
      "growthRate": "24% YoY"
    },
    "confidenceScore": 0.98,
    "metadata": {
      "lastUpdated": "2023-10-27T14:30:00Z",
      "source": "Verified Business Registry"
    }
  }
}
Enter fullscreen mode Exit fullscreen mode

Risk-Free Metered Billing

Traditional data APIs charge per request, regardless of data quality. Our MCP implementation utilizes a Risk-Free Metered Billing structure. Your account is only debited for successful enrichments that return a Confidence Score > 0.6. If the server returns low-confidence data or fails to locate a profile, the query cost is exactly $0. This allows developers to build high-volume autonomous SDR swarms and research agents without the risk of burning credits on "Not Found" responses.

Get Started with the B2B Enrichment MCP API

Ready to give your sales agents and IDE real-time firmographic superpowers? Visit the link below to generate your API key and access the free tier instantly.

Get Your B2B Lead Enrichment MCP API Key

Top comments (0)