DEV Community

Diego Costa
Diego Costa

Posted on

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

#ai #mcp #automation

How to Connect Claude Desktop 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 local environment. This integration leverages the Model Context Protocol to bridge the gap between Claude Desktop and real-time company profiles, ensuring your AI agent has the ground truth data required for high-stakes sales and marketing workflows.

Core Features

Our Model Context Protocol (MCP) server provides a unified interface for deep B2B intelligence, optimized for low-latency retrieval by LLMs. To eliminate the "parameter hallucination" common in sales agents, all tool definitions utilize strict Zod schema annotations, forcing the LLM to provide valid domain names or email addresses before execution.

  • Firmographic Intelligence: Instant access to company revenue, headcount, industry classification, and headquarters location.
  • Technographic Layer: Real-time detection of a company's software stack, from CRM systems to cloud infrastructure.
  • Intent Signals: Identify companies currently showing high-intent behavior based on hiring trends and news cycles.
  • Structured Output: Every response is formatted as a clean JSON object, pre-validated for immediate ingestion into your LLM's context window.

Configuration for Claude Desktop & Cursor

To enable these tools, update your claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/claude_desktop_config.json) with the following configuration. This points Claude to our secure, hosted MCP endpoint.

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

JSON-RPC Response Example

When you ask Claude, "What can you tell me about the company at example.com?", the enrich_lead tool triggers a JSON-RPC 2.0 request. The server returns a structured response that includes a confidence score to ensure data integrity:

{
  "method": "tools/call",
  "params": {
    "name": "enrich_lead",
    "arguments": {
      "domain": "example.com"
    }
  },
  "result": {
    "content": [
      {
        "type": "text",
        "text": {
          "companyName": "Example Corp",
          "industry": "Enterprise Software",
          "headcount": "500-1000",
          "technographics": ["AWS", "Salesforce", "HubSpot"],
          "intentSignals": ["Recent Expansion", "Active Hiring for AI Roles"],
          "confidenceScore": 0.98
        }
      }
    ]
  }
}
Enter fullscreen mode Exit fullscreen mode

Risk-Free Metered Billing

We have designed this service specifically for autonomous agent developers who need to scale without financial risk. Our Risk-Free Metered Billing structure ensures that you are only charged for successful enrichments where the Confidence Score is > 0.6. If our system cannot verify the company data or the query fails due to low-quality input, the cost is $0. This allows you to build autonomous SDR swarms and lead scoring engines with predictable unit economics.

Get Your Free API Key

Ready to upgrade your AI agent's B2B intelligence? Visit lead-enrichment-mcp.agent-infra.workers.dev to grab your API key on our generous free tier and start enriching leads natively within Claude, Cursor, or your custom MCP-compatible application.

Top comments (0)