ResumeForge

Fact-checked, ATS-ready resumes from your real career data, inside the AI app you already use.

ResumeForge is an MCP server for Claude Desktop, Claude Code, Cursor and Windsurf. It reads your LinkedIn export, GitHub projects, LeetCode / Codeforces stats and old resumes, then helps your AI write a one-page resume tailored to any job description, and checks that every number, skill and employer in it really comes from your data.

Get started (about 3 minutes)

You need Python 3.10+ and uv.

uvx resumeforge-mcp-tools setup

Setup asks where your data is (the LinkedIn .zip is fine as downloaded), connects ResumeForge to the AI apps on your computer, and builds your profile. Then restart your AI app and ask:

"Tailor my resume for this job: "

What it does

• Builds your profile from LinkedIn, GitHub, coding sites and old resumes.
• Reads the job: required vs preferred skills, "any of" options, the experience level.
• Picks only the relevant facts, so the AI focuses on what matters for the job.
• Truth check: flags invented numbers, skills, employers, projects and dates.
• ATS-style score in five categories (keyword match, skills coverage, formatting, role alignment, impact) with concrete suggestions.

Your data stays on your computer. ResumeForge only contacts GitHub, LeetCode and Codeforces to read your public profiles.

Commands

Licence

Proprietary. Copyright (c) 2025-2026 Vijayakanth M. All rights reserved. You may install and use ResumeForge for your own resumes; copying, modifying, reselling or redistributing it is not permitted. See the LICENSE file included in the package.

ATS scores are estimates of how keyword-based screening software ranks a resume, not the score of any specific vendor's system.