Resume-Analyzer-Agent
3.3
If you are the rightful owner of Resume-Analyzer-Agent and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
This project integrates resume analysis and job fetching with a Model Context Protocol (MCP) server for seamless integration with external tools.
README.md
Resume Analyzer + LinkedIn/Naukri Job Fetcher + MCP Server
This project allows you to:
- Upload a Resume (PDF)
- Analyze Resume Summary, Skill Gaps, and Future Roadmap using EURI AI
- Auto-fetch matching jobs from LinkedIn and Naukri using Apify
- Wrap the job fetch functions into a FastMCP Server for integration with external tools like Claude Desktop, MCP Inspector, etc.
๐ช Full Setup Instructions
1. Clone the Repository
git clone <your-repo-link>
cd resume_job_fetcher_project
2. Create Conda Virtual Environment (Recommended)
conda create -n resume_fetcher_env python=3.10
conda activate resume_fetcher_env
3. Install Required Packages
Using pip:
pip install -r requirements.txt
requirements.txt contains:
- streamlit
- pymupdf
- euriai
- python-dotenv
- apify-client
- fastmcp
Alternatively, using UV:
Install UV on Windows Powershell:
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
Install requirements:
uv pip install -r requirements.txt
4. Configure Environment Variables
Create a .env file:
EURI_API_KEY=your_real_euri_api_key_here
APIFY_API_TOKEN=your_real_apify_api_token_here
5. Run the Streamlit App
streamlit run app.py
6. Run MCP Server (FastMCP)
python mcp_server.py
7. Test MCP Server (Optional)
Install MCP Inspector:
npm install -g @modelcontextprotocol/inspector
Run the Inspector:
npx @modelcontextprotocol/inspector python mcp_server.py
๐ UV-Based Project Setup (Optional)
uv init mcp-server-demo
cd mcp-server-demo
uv add "mcp[cli]"
To manually install MCP CLI:
pip install "mcp[cli]"
Running standalone MCP locally:
uv run mcp
๐ Project Structure
resume_job_fetcher_project/
โโโ app.py # Streamlit frontend app
โโโ mcp_server.py # FastMCP server exposing job fetchers
โโโ requirements.txt
โโโ README.md
โโโ .env # API keys configuration
๐ Technology Stack
| Component | Technology |
|---|---|
| Resume Analysis | EURI AI (GPT-4.1-nano) |
| Job Fetching | Apify (LinkedIn + Naukri Actors) |
| Frontend | Streamlit |
| MCP Server | FastMCP |
| Environment Management | Conda / UV |
| Inspector Tool | MCP Inspector |
๐ Important Links
- EURI API Documentation
- Apify API Documentation
- FastMCP GitHub
- Streamlit Documentation
- UV Installation Guide
- MCP Inspector GitHub
๐ซ Quick Commands Summary
| Task | Command |
|---|---|
| Create Conda Env | conda create -n resume_fetcher_env python=3.10 |
| Activate Env | conda activate resume_fetcher_env |
| Install Packages | pip install -r requirements.txt or uv pip install -r requirements.txt |
| Run App | streamlit run app.py |
| Run MCP Server | python mcp_server.py |
| Launch MCP Inspector | npx @modelcontextprotocol/inspector python mcp_server.py |
๐ช Conclusion
- Resume Analyzer + Live Job Fetcher using AI ๐
- Fully ready MCP tool server integration
- Modular, scalable, and professional setup
