Skip to main content
Glama
Mokksh-bhatt

MCP Resume Scorer with Leaderboard

by Mokksh-bhatt
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

MCP Resume Scorer with Leaderboard

Welcome to the MCPs repository! This project showcases custom MCP server implementations designed to provide AI models with secure, contextual access to tools and data. Whether you're building resume scoring endpoints, integrating OAuth, or experimenting with FastAPI and Gemini, this repo is your playground for creative, real-world AI utilities.

🚀 Features

  • ✅ Resume scoring with AI-based feedback

  • 🔐 Google OAuth integration for secure access

  • ⚡ FastAPI endpoints with robust error handling

  • 🧪 Swagger UI for easy testing and documentation

  • 🌐 ngrok tunneling for public access and webhook testing

Related MCP server: Enhanced MCP Server

📁 Project Structure

mcp-starter-main/
├── mcp-bearer-token/
│   ├── app.py                # Flask app with OAuth and token handling
│   ├── credentials.json      # Google OAuth secrets (not committed)
│   ├── requirements.txt      # Python dependencies
│   └── README.md             # You're reading it!

🔧 Setup Instructions

1. Clone the repo

git clone https://github.com/Mokksh-bhatt/MCPs.git
cd MCPs/mcp-bearer-token

2. Create a virtual environment

python -m venv venv
.\venv\Scripts\activate  # Windows

3. Install dependencies

pip install -r requirements.txt

4. Add your Google OAuth credentials

  • Download credentials.json from Google Cloud Console

  • Place it in the project root

  • If named differently, set the environment variable:

$env:GOOGLE_CLIENT_SECRETS = "your_file_name.json"

5. Run the server

python app.py

🌍 Expose Locally with ngrok

ngrok http 5000

Visit http://127.0.0.1:4040 for the ngrok dashboard and copy your public URL.

🧠 Future Plans

  • Add leaderboard scoring and resume feedback visualization

  • Integrate Gemini fallback models

  • Deploy to cloud platforms for persistent access

🤝 Contributing

Pull requests, ideas, and feedback are welcome! Feel free to fork and build your own MCP extensions.

📄 License

This project is open-source under the MIT License.

✨ Author

Built with curiosity and creativity by Mokksh Bhatt

This server cannot be deployed

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • MCP Resume Chat Server

    TharakaJayz
    A
    license
    Not graded
    quality
    D
    maintenance
    Enables AI-powered conversations about resume/CV content and email notification sending through a comprehensive MCP server. Features a modern Next.js frontend with resume chat interface, email forms, and resume viewer for SE interview demonstrations.
    239 npm
    MIT

  • AI Applyd

    aiapplyd
    A
    license
    A
    quality
    B
    maintenance
    ATS resume scoring, job-description analysis, interview prep, cover letters, resume building and auto-apply that submits on the employer's own hiring system. Hosted remote server over Streamable HTTP with OAuth 2.1.
    10
    MIT

Appeared in Searches