Resume Forge MCP

An MCP (Model Context Protocol) server for intelligent LaTeX resume generation with multiple template styles, quality scoring, and job description tailoring.

Features

• 3 built-in templates: Modern (color accents), Classic (traditional), Minimal (no-frills)
• Overleaf integration: Browse and fetch 350+ templates dynamically
• Multi-format import: Import resume data from .tex, .pdf, or .docx files
• Quality scoring: Bullet analysis, ATS compatibility, keyword matching
• Job tailoring: Auto-select and rank content based on job descriptions
• Visual preview: Compile to PDF and preview as images directly in your AI assistant

Installation

uvx resume-forge-mcp

With PDF and DOCX import support:

uvx --with pymupdf --with python-docx resume-forge-mcp

Configuration

Add to your AI assistant's MCP config:

{
  "mcpServers": {
    "resume-forge": {
      "command": "uvx",
      "args": ["resume-forge-mcp"],
      "env": {
        "RESUME_DATA_DIR": "/path/to/data",
        "RESUME_TEMPLATE_DIR": "/path/to/templates",
        "RESUME_OUTPUT_DIR": "/path/to/output"
      }
    }
  }
}

Environment Variables

All env vars are optional — defaults to ~/.resume-forge/ subdirectories.

Prerequisites

For PDF compilation, install LaTeX:

• macOS: brew install --cask mactex
• Ubuntu: sudo apt install texlive-latex-base texlive-latex-extra texlive-fonts-extra
• Windows: Install MiKTeX

Tools (11)

Templates

Data Management

Generation & Compilation

Analysis & Config

Usage

> List available templates
→ modern, classic, minimal + Overleaf gallery

> Import my resume from resume.tex
→ Extracts contact, education, experience, skills into structured data

> Generate my resume using the classic template
→ Creates .tex file using classic layout

> Score my resume against keywords: Python, AWS, Kubernetes
→ Returns quality scores, ATS report, keyword match percentage

> Generate a tailored resume for this job description: [paste JD]
→ Auto-selects relevant experience, generates and compiles

License

MIT