DEV Community

Diego Costa
Diego Costa

Posted on

How to Connect Cursor and VS Code to a Live B2B Lead Enrichment MCP API

#mcp #ai #automation

How to Connect Cursor and VS Code 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 within your development environment. This B2B lead enrichment MCP server allows Cursor, VS Code, and Claude Desktop to execute real-time company profiles and lead validation tasks using the Model Context Protocol, ensuring your AI agents have ground-truth data instead of relying on outdated training sets.

Core Features of the Enrichment MCP

This server implements the Model Context Protocol to expose a high-performance enrich_lead tool. It provides deep data layers including firmographic metadata (employee count, revenue, HQ location), technographic stacks (CRMs, CMS, and cloud providers used), and real-time intent signals. To prevent LLM parameter hallucinations, all tool inputs are constrained by strict Zod schema annotations, forcing the AI to provide valid domains and company identifiers before a request is ever dispatched.

IDE Configuration for Cursor and VS Code

To give your IDE-based agents the ability to look up company data while you code or build agents, add the following to your MCP settings (e.g., in claude_desktop_config.json or Cursor's MCP settings panel):

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

Clean JSON-RPC Response Example

When the LLM calls the enrich_lead tool, the MCP server returns a structured, machine-readable JSON object. This ensures the AI agent can parse specific fields like intentSignals or confidenceScore with 100% accuracy.

{
  "status": "success",
  "data": {
    "companyName": "ExampleCorp",
    "industry": "Enterprise SaaS",
    "technographics": ["Salesforce", "AWS", "HubSpot", "Segment"],
    "firmographics": {
      "employees": "500-1000",
      "revenue": "$50M-$100M",
      "headquarters": "San Francisco, CA"
    },
    "intentSignals": [
      { "type": "Cloud Migration", "intensity": 0.85 },
      { "type": "Hiring Sales Leadership", "intensity": 0.92 }
    ],
    "confidenceScore": 0.94
  }
}
Enter fullscreen mode Exit fullscreen mode

Risk-Free Metered Billing for AI Agents

One of the primary challenges in building autonomous SDR swarms is the cost of low-quality data. Our MCP server solves this with 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 "No Result Found," a low confidence score, or if the query fails, the cost is exactly $0. This allows developers to build high-volume scraping and enrichment loops without the risk of burning through budgets on hallucinations or dead leads.

Get Started with the B2B Lead Enrichment MCP

Ready to upgrade your AI agent's knowledge base? Visit the link below to generate your API key and start using the free tier immediately.

Get Your B2B Lead Enrichment API Key Now

Top comments (0)