Metadata-Version: 2.4
Name: resumeforge-mcp-tools
Version: 2.0.0
Summary: MCP server that turns your LinkedIn, GitHub, coding profiles and old resumes into fact-checked, ATS-ready resumes tailored to any job.
Author: Vijayakanth M
License-Expression: LicenseRef-Proprietary
Keywords: mcp,model-context-protocol,resume,ats,job-application,linkedin,github,career,llm,claude
Classifier: Development Status :: 4 - Beta
Classifier: Environment :: Console
Classifier: Intended Audience :: End Users/Desktop
Classifier: Intended Audience :: Developers
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Office/Business
Classifier: Topic :: Text Processing :: Markup :: Markdown
Classifier: Topic :: Utilities
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: mcp[cli]<2,>=1.2.0
Requires-Dist: pandas>=2.0.0
Requires-Dist: httpx>=0.27.0
Requires-Dist: pdfplumber>=0.11.0
Requires-Dist: PyMuPDF>=1.24.0
Requires-Dist: python-docx>=1.1.0
Requires-Dist: python-dateutil>=2.9.0
Requires-Dist: rapidfuzz>=3.6.0
Provides-Extra: studio
Requires-Dist: streamlit>=1.35.0; extra == "studio"
Requires-Dist: openai>=1.0.0; extra == "studio"
Requires-Dist: groq>=0.9.0; extra == "studio"
Requires-Dist: python-dotenv>=1.0.0; extra == "studio"
Provides-Extra: dev
Requires-Dist: pytest>=7.4.0; extra == "dev"
Requires-Dist: build>=1.2.0; extra == "dev"
Requires-Dist: twine>=5.0.0; extra == "dev"
Dynamic: license-file

# 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](https://docs.astral.sh/uv/getting-started/installation/).

```bash
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: <paste the job description>"*

## 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

| Command | What it does |
|---|---|
| `uvx resumeforge-mcp-tools setup` | Connect your data and AI apps |
| `uvx resumeforge-mcp-tools build` | Refresh your profile after your data changes |
| `uvx resumeforge-mcp-tools doctor` | Check settings, data and app connections |

## 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.
