DEV Community

Diego Costa
Diego Costa

Posted on

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

#mcp #ai #automation

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

Integrating the Model Context Protocol (MCP) into your IDE allows LLMs to query a B2B lead enrichment MCP server for real-time company profiles and technographic data natively. This architectural shift eliminates the need for manual copy-pasting or brittle web-scraping scripts, enabling your AI agent to fetch live B2B intent signals and firmographics directly within the coding context.

Core Features

Our MCP server provides a high-fidelity bridge between your AI development environment and the global B2B data ecosystem. By utilizing strict Zod-based schema annotations, we ensure that LLMs like Claude 3.5 Sonnet and GPT-4o provide valid parameters every time, virtually eliminating tool-call hallucinations.

  • Real-time Firmographics: Access up-to-date headcount, revenue brackets, industry classifications, and founding dates.
  • Technographic Intelligence: Identify the specific software stack used by a lead, including CRM, cloud providers, and frontend frameworks.
  • Intent Signaling: Retrieve high-intent data points to prioritize leads based on recent funding, hiring trends, or technology migrations.
  • Zod-Validated Inputs: Every tool call is governed by a strict JSON schema, ensuring the LLM passes valid domains and email addresses without formatting errors.

Configuration for Cursor and VS Code

To give your AI coding agent native access to these tools, add the following configuration to your mcpServers block. This connects the IDE directly to our edge-deployed MCP worker.

{
  "mcpServers": {
    "b2b-enrichment": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-http",
        "--url",
        "https://lead-enrichment-mcp.agent-infra.workers.dev/mcp"
      ],
      "env": {
        "ENRICHMENT_API_KEY": "YOUR_FREE_API_KEY_HERE"
      }
    }
  }
}
Enter fullscreen mode Exit fullscreen mode

Standardized JSON-RPC Response

When the enrich_lead tool is invoked, the MCP server returns a clean, structured JSON object. This allows the LLM to reason about the company profile instantly, without parsing unstructured HTML or messy API responses.

{
  "jsonrpc": "2.0",
  "result": {
    "companyName": "Acme Corp",
    "industry": "Enterprise SaaS",
    "technographics": ["AWS", "Salesforce", "React", "Snowflake"],
    "intentSignals": {
      "hiringTrend": "aggressive",
      "recentFunding": "Series C"
    },
    "confidenceScore": 0.94,
    "status": "enriched"
  }
}
Enter fullscreen mode Exit fullscreen mode

Cost-Efficiency via Confidence-Weighted Billing

Building autonomous SDR swarms or data pipelines can become expensive if you pay for low-quality data. Our MCP implementation utilizes a Risk-Free Metered Billing model. Your account is only debited for successful enrichments that return a Confidence Score > 0.6. If our engine cannot find the lead or if the data quality is low, the request is processed at $0 cost, making it the most cost-effective solution for high-volume AI workflows.

Get Started with the Free Tier

Stop letting your LLMs guess about company data. Move to a native, protocol-based enrichment flow today.

Visit lead-enrichment-mcp.agent-infra.workers.dev to generate your API key and start enriching leads for free.

Top comments (0)