lead-enrichment-mcp
Enriches B2B company profiles with structured data including firmographic, technographic, and intent signals.
README
B2B Lead Enrichment MCP API
The MCP-native API that AI agents use to enrich B2B company profiles with structured data.
Live Production URL
https://lead-enrichment-mcp.agent-infra.workers.dev
Status: Live and accepting requests
Quick Start
# Test the API
curl https://lead-enrichment-mcp.agent-infra.workers.dev/health
# Enrich a company (replace with your API key)
curl -X POST https://lead-enrichment-mcp.agent-infra.workers.dev/mcp \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"enrich_lead","arguments":{"domain":"stripe.com"}}}'
Pricing
| Tier | Monthly | Price | Overage |
|---|---|---|---|
| Free | 100 enrichments | $0 | N/A |
| Pro | 10,000 enrichments | $49/month | $0.05/enrichment |
| Enterprise | Unlimited | Contact us | Custom |
Billing: Only for successful, high-confidence enrichments (confidence > 0.6). No charge for failed or low-quality enrichments.
Get an API Key
- Visit https://lead-enrichment-mcp.agent-infra.workers.dev
- Sign up for free tier or upgrade
- Copy your API key
MCP-Native for AI Agents
This API is built on the Model Context Protocol (MCP), making it natively discoverable and callable by AI agents like Claude, Cursor, and ChatGPT.
Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"lead-enrichment": {
"command": "npx",
"args": ["-y", "@anthropic-ai/mcp-server-lead-enrichment"],
"env": {
"API_KEY": "your-api-key-here"
}
}
}
}
Cursor
Add in Cursor Settings > MCP > Add New Server:
{
"mcpServers": {
"lead-enrichment": {
"type": "http",
"url": "https://lead-enrichment-mcp.agent-infra.workers.dev/mcp",
"headers": {
"Authorization": "Bearer your-api-key-here"
}
}
}
}
VS Code Copilot
Create .vscode/mcp.json:
{
"servers": {
"lead-enrichment": {
"transport": "streamable-http",
"url": "https://lead-enrichment-mcp.agent-infra.workers.dev/mcp",
"headers": {
"Authorization": "Bearer your-api-key-here"
}
}
}
}
ChatGPT GPTs
Use the OpenAPI schema:
https://lead-enrichment-mcp.agent-infra.workers.dev/openapi.json
API Endpoints
| Method | Endpoint | Description |
|---|---|---|
| POST | /mcp |
MCP JSON-RPC endpoint |
| GET | /health |
Health check |
| GET | /.well-known/mcp-server.json |
MCP Server Card |
| GET | /openapi.json |
OpenAPI 3.1 spec |
| GET | /docs |
Human-readable docs |
| GET | /test/enrich?domain=stripe.com |
Test endpoint (auth required) |
Example Response
For stripe.com:
{
"companyName": "Stripe, Inc.",
"industry": "Fintech",
"employeeCount": "5000+",
"revenue": "$1B+",
"technologies": [
"React",
"Ruby on Rails",
"PostgreSQL",
"Redis",
"Kubernetes",
"AWS"
],
"intentSignals": [
"Recently hired 3 Sales VPs in Q2 2026",
"Expanding EU operations with new Dublin office"
],
"confidenceScore": 0.95,
"enrichedAt": "2026-06-19T12:00:00.000Z",
"insights": [
"High buying intent: Recently hired multiple sales VPs indicating expansion phase",
"Enterprise-grade requirements suggest need for robust security and compliance features",
"European expansion signals potential need for multi-currency and regional compliance"
]
}
The enrich_lead Tool
When to Use
- Qualify a lead before outreach
- Research a company before a sales call
- Enrich a list of companies for a campaign
- Understand a prospect's technology stack
- Detect buying intent signals
Input
| Parameter | Type | Required | Description |
|---|---|---|---|
domain |
string | Yes | Company domain (e.g., "stripe.com") |
attributes |
string[] | No | Data types: firmographic, technographic, intent, contacts |
requiredFields |
string[] | No | Fields that must be present |
Error Handling
All errors follow RFC 9457 Problem Details format:
{
"type": "https://api.lead-enrichment-mcp.com/errors/rate-limit-exceeded",
"title": "Rate Limit Exceeded",
"detail": "You have exceeded the rate limit...",
"status": 429,
"extensions": {
"code": "RATE_LIMIT_EXCEEDED",
"retry_after": 60
}
}
Rate Limits
| Tier | Burst | Sustained |
|---|---|---|
| Free | 10 req/sec | 5 req/sec |
| Pro | 50 req/sec | 20 req/sec |
Development
# Install dependencies
npm install
# Start local dev server
npm run dev
# Deploy
npm run deploy
Tech Stack
- Hono (TypeScript) - Fast, lightweight web framework
- Cloudflare Workers - Edge runtime
- Zod - Schema validation with .describe() annotations
- MCP SDK - Model Context Protocol
- Stripe - Metered billing
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.