DEV Community

Diego Costa
Diego Costa

Posted on

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

#mcp #ai #automation

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

Integrating a B2B lead enrichment MCP server directly into Claude Desktop or Cursor allows AI agents to pull real-time firmographic and intent data without writing custom middleware. By leveraging the Model Context Protocol (MCP), developers can eliminate data hallucinations and provide their LLMs with a verified stream of B2B contact and company insights through a native JSON-RPC interface.

Core Features

The B2B Lead Enrichment MCP API provides a robust bridge between local LLM environments and high-fidelity commercial data. The server implements strict Zod-annotated schemas for every tool, ensuring that the model strictly adheres to expected parameter types (e.g., valid domain formats or email syntax), which effectively eliminates the "parameter hallucination" common in sales-focused AI agents.

  • Firmographic Intelligence: Access real-time revenue, headcount, industry classification, and precise headquarters location.
  • Technographic Stack Analysis: Identify current software usage and digital infrastructure of target prospects.
  • Intent Signaling: Surface live buying signals and organizational shifts that trigger higher conversion rates.
  • Strict Validation: All tool inputs are governed by Zod, preventing the LLM from passing malformed data to the enrichment engine.

Configuration for Claude Desktop and Cursor

To give your local AI agent access to live B2B data, add the following configuration to your claude_desktop_config.json or Cursor's MCP settings. This config points directly to the production-ready worker endpoint.

{
  "mcpServers": {
    "b2b-enrichment": {
      "command": "npx",
      "args": [
        "-y", 
        "@agent-infra/mcp-server-lead-enrichment"
      ],
      "env": {
        "ENRICHMENT_API_KEY": "YOUR_API_KEY_HERE",
        "MCP_ENDPOINT": "https://lead-enrichment-mcp.agent-infra.workers.dev/mcp"
      }
    }
  }
}
Enter fullscreen mode Exit fullscreen mode

Standardized JSON-RPC Response Example

When Claude invokes the enrich_lead tool, it receives a structured JSON response. This clean output allows the model to synthesize high-quality outreach or score leads with high precision.

{
  "jsonrpc": "2.0",
  "id": "1",
  "result": {
    "companyName": "Acme Corp",
    "industry": "Enterprise SaaS",
    "headcount": "500-1000",
    "technographics": ["Salesforce", "AWS", "HubSpot", "Segment"],
    "intentSignals": {
      "hiringTrend": "Increasing",
      "recentFunding": "Series C",
      "webTraffic": "High Growth"
    },
    "confidenceScore": 0.94,
    "status": "success"
  }
}
Enter fullscreen mode Exit fullscreen mode

Risk-Free Metered Billing

Traditional B2B data providers charge per "attempted" query, regardless of result quality. This MCP server utilizes a Risk-Free Metered Billing structure specifically designed for autonomous agents. Your account is only debited for successful enrichments that return a Confidence Score > 0.6. If the engine fails to locate the lead or returns low-confidence data, the query cost is exactly $0. This allows for the cost-effective scaling of SDR swarms and automated research agents without the fear of burning credits on hallucinations or outdated records.

Get Started with a Free API Key

Ready to upgrade your AI agents with real-time B2B intelligence? Visit lead-enrichment-mcp.agent-infra.workers.dev to generate your API key and access the free tier instantly.

Top comments (0)