DEV Community

Diego Costa
Diego Costa

Posted on

How to Equip Cursor and VS Code Copilot with Live B2B Lead Enrichment Tools via MCP

#mcp #ai #automation

How to Equip Cursor and VS Code Copilot with Live B2B Lead Enrichment Tools via MCP

You can now empower your IDE's AI agents with native access to real-time B2B firmographics and intent data by integrating a B2B lead enrichment MCP server directly into your developer workflow. By leveraging the Model Context Protocol (MCP), developers can bridge the gap between static code environments and live market intelligence, enabling Cursor and VS Code Copilot to verify leads and research company technographics without manual API duct-taping.

Core Features of the Enrichment MCP Server

To ensure high-performance retrieval and minimize the "garbage in, garbage out" cycle common in AI agents, this MCP server implements a strict schema-driven approach to data fetching:

  • Deep Firmographic Data: Access company size, revenue brackets, headquarters location, and verified industry classifications.
  • Technographic Intelligence: Real-time detection of a company's software stack, including cloud providers, CRM usage, and frontend frameworks.
  • Dynamic Intent Signals: Capture active buying signals and hiring trends directly within the LLM context.
  • Hallucination Prevention: All tool parameters are defined using strict Zod annotations, forcing the LLM to provide valid domain formats and preventing the generation of synthetic, non-existent lead data.

Configuration for Cursor and Claude Desktop

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_KEY": "YOUR_FREE_API_KEY_HERE",
        "MCP_ENDPOINT": "https://lead-enrichment-mcp.agent-infra.workers.dev/mcp"
      }
    }
  }
}
Enter fullscreen mode Exit fullscreen mode

Standardized JSON-RPC Response Payload

When your agent invokes the enrich_lead tool, the MCP server returns a clean, structured JSON-RPC object. This ensures the LLM receives a "ground truth" data layer that is easy to parse and reason over:

{
  "jsonrpc": "2.0",
  "result": {
    "companyName": "Acme Corp",
    "industry": "Enterprise Software",
    "technographics": ["AWS", "Salesforce", "React", "Snowflake"],
    "intentSignals": {
      "hiring_status": "Aggressive",
      "recent_funding": "Series C"
    },
    "confidenceScore": 0.94,
    "status": "success"
  }
}
Enter fullscreen mode Exit fullscreen mode

Risk-Free Metered Billing Architecture

Building cost-effective AI workflows requires precision. This MCP server utilizes a Risk-Free Metered Billing model. Unlike traditional APIs that charge for every request, this server only bills for successful enrichments where the confidenceScore exceeds 0.6. If the data is low quality, or if the server cannot find a high-probability match for the lead, the query cost is $0. This allows developers to build high-volume SDR swarms and research agents without the risk of burning credits on empty results.

Get Your Free B2B Enrichment API Key Today

Ready to give your AI agents a live intelligence layer? Visit lead-enrichment-mcp.agent-infra.workers.dev to grab an API key on our free tier and start enriching B2B leads natively within your favorite IDE.

Top comments (0)