DEV Community

Diego Costa
Diego Costa

Posted on

How to Give Cursor and VS Code Copilot Live B2B Firmographic Tools via MCP

#mcp #ai #automation

How to Give Cursor and VS Code Copilot Live B2B Firmographic Tools via MCP

The fastest way to empower Cursor and VS Code Copilot with live B2B firmographics and intent data is by integrating a Model Context Protocol (MCP) server directly into your IDE settings. This native integration allows AI coding assistants to retrieve real-time company profiles and lead enrichment data using standardized JSON-RPC tools, eliminating the need for manual API calls or custom middleware.

Core Features

The B2B Lead Enrichment MCP API provides a robust bridge between LLMs and high-fidelity business intelligence. By leveraging the Model Context Protocol, developers can grant their AI agents native access to three critical data layers:

  • Firmographic Intelligence: Real-time retrieval of company size, revenue brackets, headquarters location, and industry classification.
  • Technographic Data: Deep insights into a target company's current software stack and infrastructure, allowing for highly personalized outreach or competitive analysis.
  • Intent & Signal Scoring: Live detection of growth signals, recent funding rounds, and executive transitions.

To ensure reliability, every tool parameter is defined with strict Zod annotations. This prevents common LLM parameter hallucinations by forcing the model to adhere to schema-validated inputs (e.g., ensuring a domain is a valid string rather than an imaginative guess).

Configuration for Cursor and Claude Desktop

To enable these tools in your environment, 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"
      }
    }
  }
}
Enter fullscreen mode Exit fullscreen mode

JSON-RPC Payload Example

When your agent invokes the enrich_lead tool, it receives a structured, high-density JSON response. This clean output allows the LLM to synthesize data without parsing unstructured HTML or noisy text.

{
  "jsonrpc": "2.0",
  "result": {
    "companyName": "Acme Corp",
    "industry": "Enterprise SaaS",
    "technographics": ["Salesforce", "AWS", "Segment", "HubSpot"],
    "intentSignals": [
      {"type": "Funding", "detail": "Series B - $25M", "date": "2023-11-15"}
    ],
    "confidenceScore": 0.94,
    "employeeCount": 250,
    "hqLocation": "San Francisco, CA"
  }
}
Enter fullscreen mode Exit fullscreen mode

Risk-Free Metered Billing

Unlike traditional B2B data providers that charge per query regardless of result quality, this MCP server utilizes a Risk-Free Metered Billing structure. The system is designed for autonomous agents where reliability is paramount:

  • Confidence Threshold: You are only billed for successful enrichments that return a Confidence Score > 0.6.
  • Zero-Cost Failures: If the data is low quality, the record is not found, or the confidence score falls below the threshold, the query cost is exactly $0.
  • LLM Optimized: This allows you to build autonomous SDR swarms that can perform bulk lookups without the fear of burning budget on "Not Found" responses or halluncinated data.

Get Your Free B2B Lead Enrichment API Key

Ready to upgrade your AI agent's business intelligence? Visit lead-enrichment-mcp.agent-infra.workers.dev to grab an API key on the free tier and start enriching leads directly within Cursor, VS Code, or Claude Desktop.

Top comments (0)