About Resume-MCP

Last updated: July 7, 2026

Why we built this

Applying for jobs is broken. The average opening draws hundreds of applicants, most filtered by software before a human ever reads a word. Tailoring a CV and writing a fresh cover email for each role takes 30 to 60 minutes, so most people either skip the tailoring (and get filtered out) or burn out before they have applied to enough roles to matter.

Resume-MCP collapses that whole loop into under a minute. Paste a job post, and the AI rewrites your CV to match the role, builds a clean ATS-safe PDF, drafts a short application email, and sends it from your own Gmail. You stay in control of every send; the busywork disappears.

How it works under the hood

Every document is generated as LaTeX and compiled with pdflatex, not filled into a template. That means deterministic, recruiter-clean typography that parses cleanly through Applicant Tracking Systems. The tailoring runs as parallel AI calls against the job description, and applications go out through the Gmail API using only the gmail.send scope - we never read your inbox. The same engine is exposed three ways: a web dashboard, a Telegram bot, and a Model Context Protocol (MCP) server that any AI assistant can call.

Who builds it

A
Anup Ojha
Backend & AI Developer

Backend & AI engineer at Jackson and Frank. Building Resume-MCP - the AI pipeline that turns a LinkedIn job post into a sent application in under 60 seconds. Python · FastAPI · Gemini AI · LaTeX · Telegram bots · MCP servers.

Our stack

PythonFastAPIGemini AILaTeXTelegram BotsMCP ServersVue 3Cloudflare R2

Get in touch

Questions, feedback, or press? See our contact page, or read the Privacy Policy and Terms of Service.