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 live B2B firmographics and intent data without custom middleware is by deploying an MCP-native API server directly into your IDE’s configuration. By integrating our B2B lead enrichment MCP server, you enable your AI agents to query verified company profiles, technographic stacks, and intent signals directly within the Claude Desktop or Cursor context window.

Core Features and Data Precision

Our MCP server bridges the gap between static LLM training data and volatile sales intelligence. Key features include:

  • Firmographic Intelligence: Real-time access to employee count, HQ location, and revenue data.
  • Technographic Analysis: Identify software stacks and infrastructure providers used by target accounts.
  • Intent Signals: Real-time triggers based on recent funding, hiring, or organizational changes.
  • Strict Zod-Schema Constraints: Every tool call is governed by strict Zod annotations at the MCP layer. This eliminates LLM parameter hallucinations by forcing the agent to conform to required schema types, ensuring the company_domain or email input is perfectly formatted before the request reaches the server.

Integrating with Cursor or Claude Desktop

To authorize your local environment to access our enrichment endpoints, add the following configuration to your MCP settings file (located at ~/Library/Application Support/Claude/mcp_settings.json or equivalent):

{
  "mcpServers": {
    "b2b-enrichment": {
      "command": "npx",
      "args": ["-y", "@agent-infra/lead-enrichment-mcp"],
      "env": {
        "API_KEY": "your_api_key_here"
      }
    }
  }
}
Enter fullscreen mode Exit fullscreen mode

JSON-RPC Response Structure

The tool returns a clean JSON-RPC object, specifically optimized for LLM token efficiency. When your agent calls enrich_lead, it receives a structured response designed for immediate downstream processing:

{
  "jsonrpc": "2.0",
  "result": {
    "companyName": "Acme Corp",
    "industry": "Cloud Infrastructure",
    "technographics": ["Kubernetes", "AWS", "Datadog"],
    "intentSignals": "High intent: recently increased cloud spend by 20%",
    "confidenceScore": 0.94
  },
  "id": "req_12345"
}
Enter fullscreen mode Exit fullscreen mode

Risk-Free Metered Billing

Efficiency in AI workflows is often stifled by unpredictable API costs. Our model adopts a Confidence-Based Billing structure: you are only charged for successful enrichments where the confidenceScore exceeds 0.6. Any data return that is stale, low-quality, or results in a null lookup is completely free, allowing you to scale your autonomous SDR swarms without runaway costs.

Get Your API Key

Ready to supercharge your AI agents with real-time intelligence? Visit lead-enrichment-mcp.agent-infra.workers.dev to generate your API key and start your free tier integration today.

Top comments (0)