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 most efficient way to give LLMs native access to real-time B2B firmographics and intent data is by deploying our MCP-native B2B lead enrichment server directly within your IDE's agent configuration. By leveraging the Model Context Protocol (MCP), you can bypass traditional middleware and allow Cursor or Claude Desktop to query verified company profiles, technographics, and intent signals directly into your local development environment.

Core Features

Our MCP server bridges the gap between static LLM knowledge and live market data. By utilizing strict Zod-based parameter schema enforcement, the tool ensures that the LLM sends perfectly structured queries, effectively eliminating common parameter hallucination patterns.

  • Firmographic Data: Pull real-time employee counts, revenue brackets, and HQ locations.
  • Technographic Stack: Identify the software and infrastructure tools a target prospect is currently utilizing.
  • Intent Signals: Access real-time buying signals based on web traffic and search patterns.
  • Error-Resilient Integration: Every tool invocation uses strong typing to ensure the agent environment maintains high context fidelity.

Integrating the MCP Server

Add the following configuration to your claude_desktop_config.json or your Cursor MCP settings to enable the B2B enrichment toolset:

{
  "mcpServers": {
    "lead-enrichment": {
      "command": "npx",
      "args": [
        "-y",
        "@agent-infra/lead-enrichment-mcp"
      ],
      "env": {
        "LEAD_ENRICHMENT_API_KEY": "your_api_key_here",
        "API_ENDPOINT": "https://lead-enrichment-mcp.agent-infra.workers.dev/mcp"
      }
    }
  }
}
Enter fullscreen mode Exit fullscreen mode

JSON-RPC Response Example

When an agent calls the enrich_lead tool, the API returns a structured object specifically designed for LLM parsing. Below is a sample payload representing a successful enrichment result:

{
  "jsonrpc": "2.0",
  "id": 1,
  "result": {
    "companyName": "Acme Corp",
    "industry": "Cloud Infrastructure",
    "technographics": ["Kubernetes", "AWS", "Datadog"],
    "intentSignals": {
      "score": 88,
      "category": "High Intent - Infrastructure Upgrade"
    },
    "confidenceScore": 0.94,
    "revenue": "50M-100M"
  }
}
Enter fullscreen mode Exit fullscreen mode

The Value Proposition: Risk-Free Metered Billing

Stop paying for data noise. Our pricing model is architected for developers building high-efficiency agent swarms: you are only billed for successful enrichments where the Confidence Score exceeds 0.6. If the system returns low-quality data or fails to resolve the entity, that query costs $0, ensuring your autonomous agents stay within budget while maximizing the signal-to-noise ratio in your lead pipeline.

Get Started Instantly

Integrate the most precise B2B data source into your agent workflows today. Visit lead-enrichment-mcp.agent-infra.workers.dev to grab your API key, explore the interactive documentation, and activate your free tier to start enriching leads natively within your IDE.

Top comments (0)