Resume MCP Server

by aarangop

619 downloads
Not rated
GitHub

About

An MCP server for assistance during job search.

Details

Author
aarangop
Downloads
619
Categories
Other

- Resume tailoring for specific job descriptions
- LaTeX export to professional PDF format
- Obsidian vault integration for file search
- Career guidance and resume feedback
- MCP protocol for seamless AI integration
- Containerized LaTeX compilation for security

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name Resume MCP Server
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Install Python 3.10+, Docker/Podman (for LaTeX compilation), and optionally Obsidian. Create a .env file with paths and API keys. Start the LaTeX compilation server, then run python main.py. Connect any MCP‑compatible client and use the “Tailor CV” prompt or the provided tools (e.g., save_tailored_cv, generate_latex_cv).

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "resume mcp server": {
            "resume-mcp": {
                "command": "uv",
                "args": [
                    "pip",
                    "install",
                    "-e",
                    "."
                ]
            }
        }
    }
}

McpServers

{
    "resume-mcp": {
        "command": "uv",
        "args": [
            "pip",
            "install",
            "-e",
            "."
        ]
    }
}

Resume MCP Server

A Model Context Protocol (MCP) server for AI-powered resume tailoring. This
service lets you tailor your resume/CV for specific job descriptions
automatically, creating both Markdown and LaTeX/PDF versions optimized for ATS
systems.

🚀 Features

- Resume Tailoring: Generate custom resumes targeting specific job
descriptions
- LaTeX Support: Export to professional PDF format using LaTeX templates
- Obsidian Integration: Search and manage files from your Obsidian vault
- Career Guidance: Get feedback on your resume and career options
- MCP Protocol: Follows the Model Context Protocol for seamless AI
integration

📋 Prerequisites

- Python 3.10 or higher
- Docker or Podman (for LaTeX compilation service)
- Node.js/npm (for MCP Inspector)
- Obsidian (optional, for vault integration)
- If not using Obsidian, you can use any directory on your file system, just
make sure to set the OBSIDIAN_VAULT variable in your .env file.

⚙️ Installation

1. Clone the repository:

   git clone https://github.com/yourusername/resume-mcp.git
   cd resume-mcp
   

2. Install the required Python dependencies:

   pip install -r requirements.txt
   # Or using uv (recommended for better dependency resolution)
   uv pip install -e .
   

3. Start the LaTeX compilation server (required for PDF generation):

   # Using Docker
   cd latex-compilation-server
   docker-compose up -d
   cd ..

# OR using Podman
cd latex-compilation-server
podman-compose up -d
cd ..

You can verify the server is running with:

   curl http://localhost:7474/health
   

4. Install the MCP Inspector (for debugging/development):

   npm install -g @modelcontextprotocol/inspector

Initial Repository Setup

If you cloned the repository without the --recursive flag, you might need to
initialize the LaTeX compilation server submodule:

git submodule init
git submodule update

This ensures that you have the complete LaTeX compilation server code in the
latex-compilation-server directory.

🔧 Configuration

Create a .env file in the root directory with the following variables (or
configure them in your environment):

```env

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.