g-mcp-tools-fast - Production-Ready Enrichment API

Enterprise-grade data intelligence API with 9 enrichment tools + bulk processing

🚀 Status: Production-Ready | SaaS-Ready | Fully Deployed 🔗 Live Endpoint: https://scaile--g-mcp-tools-fast-api.modal.run 📚 Interactive Docs: Swagger UI | ReDoc

🎯 Overview

A complete data enrichment API built on Modal.com, combining AI-powered web scraping with 8 specialized intelligence tools. Perfect for sales intelligence, market research, lead enrichment, and data validation.

Key Features

✅ 9 Enrichment Tools - Web scraping, email intel, company data, phone validation, and more ✅ Bulk Processing - Process 100s-1000s of records in parallel with auto-detection ✅ Smart Auto-Detection - Automatically detect data types and apply appropriate tools ✅ Multi-Tool Enrichment - Combine multiple tools on a single record ✅ AI-Powered Extraction - Uses Gemini 2.5 Flash for intelligent data extraction ✅ Production-Ready - Authentication, health checks, comprehensive error handling ✅ Auto-Scaling - Serverless architecture handles traffic spikes automatically ✅ 24-Hour Cache - Reduces costs and improves response times ✅ OpenAPI Docs - Swagger/ReDoc for easy integration ✅ Type-Safe - Pydantic models for all inputs/outputs

🚀 Bulk Processing & Power Features

NEW: Process multiple records in parallel with intelligent auto-detection!

Multi-Tool Enrichment (`/enrich`)

Enrich a single record with multiple tools at once:

curl -X POST https://scaile--g-mcp-tools-fast-api.modal.run/enrich \
  -H 'Content-Type: application/json' \
  -d '{
    "data": {
      "phone": "+14155552671",
      "email": "john@anthropic.com"
    },
    "tools": ["phone-validation", "email-intel", "email-pattern"]
  }'

Auto-Detection (`/enrich/auto`)

Automatically detect data types and apply appropriate tools:

curl -X POST https://scaile--g-mcp-tools-fast-api.modal.run/enrich/auto \
  -H 'Content-Type: application/json' \
  -d '{
    "data": {
      "contact_phone": "+14155552671",
      "work_email": "john@anthropic.com",
      "company_domain": "anthropic.com"
    }
  }'

Response: Automatically detected and enriched with 5 tools (phone validation, email intel, email pattern, WHOIS, tech stack)!

Bulk Processing (`/bulk`)

Process multiple records in parallel with explicit tools:

curl -X POST https://scaile--g-mcp-tools-fast-api.modal.run/bulk \
  -H 'Content-Type: application/json' \
  -d '{
    "rows": [
      {"name": "Alice Johnson", "email": "alice@example.com"},
      {"name": "Bob Smith", "email": "bob@example.com"}
    ],
    "tools": ["email-intel", "email-pattern"]
  }'

Response:

{
  "success": true,
  "batch_id": "batch_1761503726531_7AzCBh1nHak",
  "status": "completed",
  "total_rows": 2,
  "successful": 2,
  "failed": 0,
  "processing_time_seconds": 1.24,
  "results": [ /* enriched rows */ ]
}

Bulk Auto-Processing (`/bulk/auto`)

Process multiple records with automatic tool detection:

curl -X POST https://scaile--g-mcp-tools-fast-api.modal.run/bulk/auto \
  -H 'Content-Type: application/json' \
  -d '{
    "rows": [
      {"name": "Alice", "email": "alice@example.com", "website": "example.com"},
      {"name": "Bob", "phone": "+14155551234"}
    ]
  }'

Smart Features:

✅ Automatically detects emails, phones, domains, companies, GitHub usernames
✅ Applies appropriate tools (email-intel, email-pattern, whois, tech-stack, etc.)
✅ Processes rows in parallel using asyncio
✅ Handles up to 10,000 rows per batch
✅ Returns detailed success/error stats

🛠️ Individual Enrichment Tools

1. Web Scraper (`/scrape`)

Extract structured data from any website using natural language prompts.

Capabilities:

AI-powered extraction with Gemini 2.5 Flash
Multi-page scraping with auto-discovery
Custom JSON schema support
Link extraction
24-hour intelligent caching

Example:

curl -X POST https://scaile--g-mcp-tools-fast-api.modal.run/scrape \
  -H 'Content-Type: application/json' \
  -d '{
    "url": "https://anthropic.com",
    "prompt": "Extract the company mission and product names",
    "max_pages": 1
  }'

Response:

{
  "success": true,
  "data": {
    "company_mission": "Build safe, beneficial AI...",
    "product_names": ["Claude", "Claude Code", "Opus", "Sonnet", "Haiku"]
  },
  "metadata": {
    "extraction_time": 10.31,
    "pages_scraped": 1,
    "model": "gemini-2.5-flash"
  }
}

2. Email Intel (`/email-intel`)

Check which platforms an email is registered on (holehe).

curl -X POST https://scaile--g-mcp-tools-fast-api.modal.run/email-intel \
  -H 'Content-Type: application/json' \
  -d '{"email": "user@example.com"}'

3. Email Finder (`/email-finder`)

Find email addresses associated with a domain (theHarvester).

curl -X POST https://scaile--g-mcp-tools-fast-api.modal.run/email-finder \
  -H 'Content-Type: application/json' \
  -d '{"domain": "anthropic.com", "limit": 10}'

4. Company Data (`/company-data`)

Get company registration and corporate information (OpenCorporates).

curl -X POST https://scaile--g-mcp-tools-fast-api.modal.run/company-data \
  -H 'Content-Type: application/json' \
  -d '{"companyName": "Anthropic", "domain": "anthropic.com"}'

5. Phone Validation (`/phone-validation`)

Validate phone numbers with carrier, location, and line type info.

curl -X POST https://scaile--g-mcp-tools-fast-api.modal.run/phone-validation \
  -H 'Content-Type: application/json' \
  -d '{"phoneNumber": "+14155552671", "defaultCountry": "US"}'

Response:

{
  "success": true,
  "data": {
    "valid": true,
    "formatted": {
      "e164": "+14155552671",
      "international": "+1 415-555-2671",
      "national": "(415) 555-2671"
    },
    "country": "San Francisco, CA",
    "carrier": "Unknown",
    "lineType": "FIXED_LINE_OR_MOBILE",
    "lineTypeCode": 2
  }
}

6. Tech Stack (`/tech-stack`)

Detect technologies and frameworks used by a website.

curl -X POST https://scaile--g-mcp-tools-fast-api.modal.run/tech-stack \
  -H 'Content-Type: application/json' \
  -d '{"domain": "anthropic.com"}'

Response:

{
  "success": true,
  "data": {
    "domain": "anthropic.com",
    "technologies": [
      {"name": "Next.js", "category": "Framework"},
      {"name": "cloudflare", "category": "Web Server"}
    ],
    "totalFound": 2
  }
}

7. Email Pattern (`/email-pattern`)

Generate common email patterns for a domain.

curl -X POST https://scaile--g-mcp-tools-fast-api.modal.run/email-pattern \
  -H 'Content-Type: application/json' \
  -d '{"domain": "anthropic.com", "firstName": "John", "lastName": "Doe"}'

8. WHOIS (`/whois`)

Look up domain registration information.

curl -X POST https://scaile--g-mcp-tools-fast-api.modal.run/whois \
  -H 'Content-Type: application/json' \
  -d '{"domain": "anthropic.com"}'

Response:

{
  "success": true,
  "data": {
    "domain": "anthropic.com",
    "registrar": "MarkMonitor, Inc.",
    "creationDate": "2001-10-02",
    "expirationDate": "2033-10-02",
    "nameServers": ["ISLA.NS.CLOUDFLARE.COM", "RANDY.NS.CLOUDFLARE.COM"]
  }
}

9. GitHub Intel (`/github-intel`)

Analyze GitHub user profiles and repositories.

curl -X POST https://scaile--g-mcp-tools-fast-api.modal.run/github-intel \
  -H 'Content-Type: application/json' \
  -d '{"username": "anthropics"}'

Response:

{
  "success": true,
  "data": {
    "username": "anthropics",
    "name": "Anthropic",
    "location": "United States of America",
    "publicRepos": 54,
    "followers": 14565,
    "languages": {
      "Python": 6,
      "TypeScript": 3,
      "JavaScript": 1
    }
  }
}

🔐 Authentication

The API supports optional API key authentication via the x-api-key header.

Enable Authentication

Create Modal secret:

modal secret create modal-api-key MODAL_API_KEY=your-secret-key-here

Redeploy the API:

./DEPLOY_G_MCP_TOOLS.sh

Include API key in requests:

curl -X POST https://scaile--g-mcp-tools-fast-api.modal.run/scrape \
  -H 'Content-Type: application/json' \
  -H 'x-api-key: your-secret-key-here' \
  -d '{"url": "https://example.com", "prompt": "Extract data"}'

Note: If MODAL_API_KEY is not set, the API is publicly accessible (useful for development).

🚀 Deployment

Prerequisites

Install Modal CLI:

pip install modal

Authenticate:

modal setup

Create Gemini API secret:

modal secret create gemini-secret GOOGLE_GENERATIVE_AI_API_KEY=your-gemini-key

Deploy

chmod +x DEPLOY_G_MCP_TOOLS.sh
./DEPLOY_G_MCP_TOOLS.sh

Or manually:

modal deploy g-mcp-tools-complete.py

🏥 Health Check

Monitor API status:

curl https://scaile--g-mcp-tools-fast-api.modal.run/health

Response:

{
  "status": "healthy",
  "service": "g-mcp-tools-fast",
  "version": "1.0.0",
  "tools": 9,
  "timestamp": "2025-10-26T17:30:00.000000Z"
}

📊 Response Format

All endpoints follow a consistent response format:

Success Response

{
  "success": true,
  "data": { ... },
  "metadata": {
    "source": "tool-name",
    "timestamp": "2025-10-26T17:30:00.000000Z"
  }
}

Error Response

{
  "success": false,
  "error": "Error message",
  "metadata": {
    "source": "tool-name",
    "timestamp": "2025-10-26T17:30:00.000000Z"
  }
}

💰 Cost Optimization

The API includes several cost-saving features:

24-Hour Cache - Repeated requests return cached results
Timeouts - Prevents runaway processes (30s default, 120s max)
Container Idle Timeout - Containers shut down after 120s of inactivity
Efficient Resource Usage - Only runs when needed

Estimated costs (Modal pricing):

Web scraping: ~$0.001 per request
Other tools: ~$0.0001 per request
Cache hits: $0 (served from memory)

🧪 Testing

Run All Tests

# Test all 9 endpoints
./test-all-endpoints.sh

Individual Endpoint Tests

# Email pattern
curl -X POST https://scaile--g-mcp-tools-fast-api.modal.run/email-pattern \
  -H 'Content-Type: application/json' \
  -d '{"domain": "anthropic.com"}'

# Phone validation
curl -X POST https://scaile--g-mcp-tools-fast-api.modal.run/phone-validation \
  -H 'Content-Type: application/json' \
  -d '{"phoneNumber": "+14155552671"}'

# GitHub intel
curl -X POST https://scaile--g-mcp-tools-fast-api.modal.run/github-intel \
  -H 'Content-Type: application/json' \
  -d '{"username": "anthropics"}'

📈 SaaS Readiness Checklist

Ready to Sell As:

✅ B2B SaaS API ✅ Data Enrichment Service ✅ Lead Intelligence Platform ✅ Market Research Tool

🔧 Monitoring & Logs

View Logs

modal app logs g-mcp-tools-fast --follow

Check App Status

modal app list | grep g-mcp-tools

View Secrets

modal secret list

🏗️ Architecture

Client Request
    ↓
FastAPI (Modal ASGI)
    ↓
Authentication Check (optional)
    ↓
Input Validation (Pydantic)
    ↓
Cache Check (24h TTL)
    ↓ (cache miss)
Tool Execution
    ├→ Web Scraper (crawl4ai + Gemini)
    ├→ Email Intel (holehe)
    ├→ Email Finder (theHarvester)
    ├→ Company Data (OpenCorporates API)
    ├→ Phone Validation (libphonenumber)
    ├→ Tech Stack (custom detection)
    ├→ Email Pattern (pattern generation)
    ├→ WHOIS (python-whois)
    └→ GitHub Intel (GitHub API)
    ↓
Cache Result
    ↓
JSON Response

📝 License

See parent repository for license information.

🤝 Support

Documentation: Swagger UI
Issues: Report via GitHub Issues
Modal Support: modal.com/docs

🎯 Use Cases

Sales Intelligence

Enrich lead data with company info
Find contact emails and phone numbers
Validate contact information

Market Research

Scrape competitor websites
Analyze tech stacks
Track company changes via WHOIS

Developer Intelligence

Analyze GitHub profiles
Detect technologies used
Research developer ecosystems

Data Validation

Validate phone numbers
Verify email patterns
Check domain registrations

Built with: Modal.com | FastAPI | Gemini 2.5 Flash | crawl4ai

Name		Name	Last commit message	Last commit date
Latest commit History 4 Commits
.gitignore		.gitignore
API_SCHEMAS.md		API_SCHEMAS.md
DEPLOY.sh		DEPLOY.sh
DEPLOY_ENRICHMENT.sh		DEPLOY_ENRICHMENT.sh
DEPLOY_G_MCP_TOOLS.sh		DEPLOY_G_MCP_TOOLS.sh
LICENSE		LICENSE
QUALITY_CHECK_REPORT.md		QUALITY_CHECK_REPORT.md
README.md		README.md
SAAS_READINESS_ASSESSMENT.md		SAAS_READINESS_ASSESSMENT.md
flexible_scraper.py		flexible_scraper.py
g-mcp-tools-complete.py		g-mcp-tools-complete.py

License

SCAILE-it/g-mcp-tools-fast

Folders and files

Latest commit

History

Repository files navigation

g-mcp-tools-fast - Production-Ready Enrichment API

🎯 Overview

Key Features

🚀 Bulk Processing & Power Features

Multi-Tool Enrichment (/enrich)

Auto-Detection (/enrich/auto)

Bulk Processing (/bulk)

Bulk Auto-Processing (/bulk/auto)

🛠️ Individual Enrichment Tools

1. Web Scraper (/scrape)

2. Email Intel (/email-intel)

3. Email Finder (/email-finder)

4. Company Data (/company-data)

5. Phone Validation (/phone-validation)

6. Tech Stack (/tech-stack)

7. Email Pattern (/email-pattern)

8. WHOIS (/whois)

9. GitHub Intel (/github-intel)

🔐 Authentication

Enable Authentication

🚀 Deployment

Prerequisites

Deploy

🏥 Health Check

📊 Response Format

Success Response

Error Response

💰 Cost Optimization

🧪 Testing

Run All Tests

Individual Endpoint Tests

📈 SaaS Readiness Checklist

Ready to Sell As:

🔧 Monitoring & Logs

View Logs

Check App Status

View Secrets

🏗️ Architecture

📝 License

🤝 Support

🎯 Use Cases

Sales Intelligence

Market Research

Developer Intelligence

Data Validation

About

Topics

Resources

License

Uh oh!

Stars

Watchers

Forks

Releases

Packages 0

Languages

Multi-Tool Enrichment (`/enrich`)

Auto-Detection (`/enrich/auto`)

Bulk Processing (`/bulk`)

Bulk Auto-Processing (`/bulk/auto`)

1. Web Scraper (`/scrape`)

2. Email Intel (`/email-intel`)

3. Email Finder (`/email-finder`)

4. Company Data (`/company-data`)

5. Phone Validation (`/phone-validation`)

6. Tech Stack (`/tech-stack`)

7. Email Pattern (`/email-pattern`)

8. WHOIS (`/whois`)

9. GitHub Intel (`/github-intel`)

Packages