Give Cursor and VS Code Live B2B Lead Enrichment with a Production-Ready MCP Server

#mcp #ai #automation

Give Cursor and VS Code Live B2B Lead Enrichment with a Production-Ready MCP Server

Integrating real-time firmographic and technographic data directly into your development environment is now possible by connecting Cursor or VS Code to a dedicated Model Context Protocol (MCP) server. This setup allows AI agents to fetch verified B2B lead enrichment data via native tools, utilizing strict Zod-validated schemas to ensure LLMs retrieve high-accuracy company profiles without the risk of parameter hallucinations.

Core Features

The B2B Lead Enrichment MCP API provides a comprehensive data layer designed specifically for LLM consumption and agentic workflows:

Real-time Firmographics: Access up-to-the-minute data on company size, revenue, industry classification, and headquarters location.
Technographic Intelligence: Identify a target company's current software stack, including cloud providers, CRM usage, and frontend frameworks.
Verified Intent Signals: Surface buying signals and market movements directly within your AI's context window.
Hallucination Prevention: Every tool parameter is defined with strict Zod schemas, forcing the LLM to provide valid input types (e.g., valid domain formats) and preventing the "guessing" of API arguments.

Implementation: Configuring Your IDE

To give your AI agent access to these tools, add the following configuration to your claude_desktop_config.json or your Cursor MCP settings.

{
  "mcpServers": {
    "b2b-enrichment": {
      "command": "npx",
      "args": [
        "-y",
        "@agent-infra/mcp-server-lead-enrichment"
      ],
      "env": {
        "ENRICHMENT_API_URL": "https://lead-enrichment-mcp.agent-infra.workers.dev/mcp",
        "API_KEY": "YOUR_FREE_API_KEY_HERE"
      }
    }
  }
}

JSON-RPC Response Example

When the LLM calls the enrich_lead tool, it receives a clean, structured JSON-RPC response. This data is injected directly into the conversation context, allowing the agent to reason about the lead immediately.

{
  "method": "tools/call",
  "params": {
    "name": "enrich_lead",
    "arguments": {
      "domain": "stripe.com"
    }
  },
  "result": {
    "companyName": "Stripe",
    "industry": "Financial Services",
    "technographics": ["AWS", "React", "Ruby on Rails", "Salesforce"],
    "intentSignals": ["High: Expanding EMEA Operations"],
    "employeeCount": "7,000+",
    "confidenceScore": 0.98
  }
}

Risk-Free Metered Billing

Traditional data APIs charge for every request, regardless of whether the data found was useful or accurate. This MCP server implements a Risk-Free Metered Billing model. Your account is only debited for successful enrichments that return a Confidence Score > 0.6. If the server returns a low-confidence result or fails to find a matching profile, the cost of that query is $0. This allows developers to scale autonomous SDR swarms and research agents without worrying about the cost of "hallucinated" or "missing" data hits.