Job Outreach MCP Server

An MCP server for automated job outreach that helps you find companies, discover contacts, generate personalized emails with AI, and track your outreach campaigns.

Features

Setup

1. Install dependencies:

   npm install

1. Configure settings:

   cp data/config.example.json data/config.json

Edit data/config.json with your credentials.

1. Build:

   npm run build

Configuration

Edit data/config.json:

{
  "smtp": {
    "host": "smtp.your-server.com",
    "port": 587,
    "user": "your-username",
    "password": "your-password",
    "from_email": "[email protected]"
  },
  "anthropic_api_key": "sk-ant-...",
  "user_profile": {
    "name": "Your Name",
    "title": "Software Engineer",
    "resume_summary": "Your background...",
    "linkedin_url": "https://linkedin.com/in/you",
    "highlights": ["5+ years experience", "TypeScript expert"]
  },
  "smart_schedule": {
    "timezone": "America/Los_Angeles",
    "preferred_days": [2, 3, 4],
    "preferred_hours": [9, 10, 11]
  },
  "followup": {
    "enabled": true,
    "days_between": 5,
    "max_followups": 2
  },
  "tracking_server": {
    "port": 3847,
    "base_url": "http://your-server:3847"
  }
}

Usage with Claude Desktop

Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on Mac):

{
  "mcpServers": {
    "job-outreach": {
      "command": "node",
      "args": ["/path/to/auto-job-application/dist/index.js"]
    }
  }
}

Running the Email Processor

The email processor sends scheduled emails and handles tracking:

npm run processor

Run this in the background to automatically send emails at their scheduled times.

Workflow Example

1. Add a company:

   search_companies({ query: "Stripe", source: "manual" })

1. Add a contact:

   find_contacts({
     company_id: 1,
     contacts: [{ name: "Jane Doe", title: "Recruiter" }]
   })

1. Research the company:

   research_company({ company_id: 1 })

1. Add job posting (optional):

   add_job_posting({
     company_id: 1,
     title: "Senior Engineer",
     url: "https://stripe.com/jobs/123"
   })

1. Generate personalized email:

   generate_email({ contact_id: 1, job_posting_id: 1 })

1. Schedule delivery:

   schedule_email({ email_id: 1, smart_schedule: true })

1. Check status:

   check_tracking({ company_id: 1 })

1. Schedule follow-up (if no reply):

   schedule_followup({ email_id: 1 })

Architecture

src/
├── index.ts              # MCP server entry point
├── processor.ts          # Background email processor
├── types.ts              # TypeScript types
├── tools/                # MCP tool implementations
│   ├── search-companies.ts
│   ├── find-contacts.ts
│   ├── research-company.ts
│   ├── generate-email.ts
│   ├── schedule-email.ts
│   ├── check-tracking.ts
│   ├── schedule-followup.ts
│   ├── list-campaigns.ts
│   └── add-job-posting.ts
├── services/             # Core services
│   ├── database.ts       # SQLite operations
│   ├── config.ts         # Configuration loader
│   ├── scraper.ts        # Web scraping with Puppeteer
│   ├── email-patterns.ts # Email generation & SMTP verification
│   ├── llm.ts            # Claude API integration
│   ├── scheduler.ts      # Smart scheduling logic
│   └── smtp.ts           # Email sending
└── tracking/
    └── server.ts         # Open/click tracking webhook server

Email Tracking

The tracking server provides:

• Open tracking: 1x1 pixel embedded in emails
• Click tracking: Link wrapping with redirect
• Reply webhooks: Endpoint for email provider callbacks

For tracking to work, the tracking server must be accessible from the internet (use ngrok for testing or deploy the processor).

Notes

• LinkedIn scraping is not implemented (requires authentication and is against ToS)
• Email SMTP verification may be blocked by some mail servers
• Smart scheduling picks optimal send times: Tuesday-Thursday, 9-11am recipient timezone
• The background processor must be running for scheduled emails to be sent

License

MIT