MCP Job Application Tracker & Resume Customizer
Automates job application tracking and resume/cover letter generation using AI, integrating with Google Drive, Notion, and Gmail.
README
š§ MCP Job Application Tracker & Resume Customizer
An MCP (Model Context Protocol) server that automates your job application process using AI. It connects with Google Drive, Notion, and Gmail to help you track applications, generate tailored resumes and cover letters, and send follow-up reminders.
⨠Features
- AI-Powered Resume & Cover Letter Generation: Uses Claude to create tailored documents for each job
- Google Drive Integration: Automatically saves generated documents to your Drive
- Notion Database Tracking: Logs all job applications with status tracking
- Follow-up Email Automation: Sends reminder emails for applications that need attention
- MCP Protocol: Works seamlessly with MCP-compatible AI assistants
š Quick Start
1. Install Dependencies
npm install
2. Set Up Environment Variables
Copy the example environment file and fill in your API keys:
cp env.example .env
For Windows users: You can also use the provided setup-env.bat or setup-env-windows.bat scripts.
ā ļø IMPORTANT: Edit these files first to replace placeholder values with your actual API keys before running them. Never commit files containing real API keys!
You'll need to set up:
- Anthropic API Key: Get from Anthropic Console
- Google OAuth Credentials: Set up a project in Google Cloud Console
- Notion Integration: Create an integration in Notion Developers
3. Build the Project
npm run build
4. Run the MCP Server
npm start
š§ Setup Instructions
Google APIs Setup
- Go to Google Cloud Console
- Create a new project or select existing one
- Enable the following APIs:
- Google Drive API
- Gmail API
- Create OAuth 2.0 credentials:
- Application type: Web application
- Authorized redirect URIs:
http://localhost:3000/auth/google/callback
- Copy the Client ID and Client Secret to your
.envfile
Notion Setup
- Go to Notion Developers
- Create a new integration
- Copy the Internal Integration Token to your
.envfile - Create a database in Notion with the following properties:
- Job Title (Title)
- Company (Text)
- Status (Select: drafted, applied, interviewing, offer, rejected, withdrawn)
- Applied Date (Date)
- Follow-up Date (Date)
- Resume URL (URL)
- Cover Letter URL (URL)
- Notes (Text)
- Created (Date)
- Last Updated (Date)
- Share the database with your integration
- Copy the database ID to your
.envfile
š Usage
Available Tools
The MCP server provides the following tools:
process_job_application
Process a new job application by generating tailored resume and cover letter.
Parameters:
jobTitle(string): The title of the job positioncompanyName(string): The name of the companyjobDescription(string): The full job description textresumeData(object): Your resume information
Example:
{
"jobTitle": "Senior Software Engineer",
"companyName": "Tech Corp",
"jobDescription": "We are looking for a senior software engineer...",
"resumeData": {
"name": "John Doe",
"email": "john@example.com",
"phone": "+1-555-0123",
"location": "San Francisco, CA",
"summary": "Experienced software engineer...",
"experience": [...],
"education": [...],
"skills": ["JavaScript", "Python", "React"],
"projects": [...]
}
}
get_job_applications
Retrieve all job applications from your Notion database.
update_job_status
Update the status of a job application.
Parameters:
pageId(string): The Notion page IDstatus(string): New status (drafted, applied, interviewing, offer, rejected, withdrawn)notes(string, optional): Additional notes
send_follow_up_emails
Send follow-up emails for applications that need attention.
Parameters:
recipientEmail(string): Email address to send follow-ups to
get_google_auth_url
Get the Google OAuth URL for setting up access.
š Workflow
- Find a Job: When you find a job you want to apply for
- Process Application: Use
process_job_applicationwith the job details and your resume data - Review Documents: Check the generated resume and cover letter in Google Drive
- Submit Application: When you submit, update the status to "applied"
- Track Progress: Monitor your applications in Notion
- Follow Up: Use
send_follow_up_emailsto send reminders
š ļø Development
Project Structure
src/
āāā config/ # Configuration management
āāā services/ # External service integrations
ā āāā openai.ts # OpenAI GPT integration
ā āāā google.ts # Google Drive & Gmail
ā āāā notion.ts # Notion database
āāā types/ # TypeScript type definitions
āāā index.ts # Main MCP server
Available Scripts
npm run dev: Run in development mode with hot reloadnpm run build: Build the TypeScript projectnpm start: Run the built servernpm run watch: Watch for changes and rebuild
š Security
- All API keys are stored in environment variables
- Google OAuth uses secure token exchange
- No sensitive data is logged or stored in plain text
ā ļø Important Security Practices
NEVER commit API keys to version control!
- Always use
.envfiles for your API keys (already in.gitignore) - If using
setup-env.batorsetup-env-windows.batscripts, replace placeholders with your actual keys locally - Keep your API keys private and rotate them immediately if exposed
- For Windows users: Copy the setup script templates, add your keys, but do NOT commit them back to the repository
š¤ Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Add tests if applicable
- Submit a pull request
š License
MIT License - see LICENSE file for details
š Support
If you encounter any issues:
- Check that all environment variables are set correctly
- Verify your API keys have the necessary permissions
- Ensure your Notion database has the correct structure
- Check the console for error messages
For more help, please open an issue on GitHub.
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.
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.
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.
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.