Model Context Protocol

The JuicedResume MCP server

The JuicedResume MCP server is a published npm package (@juicedresume/mcp) that lets AI assistants like Claude Code read, edit, score, tailor, and export your resumes over the Model Context Protocol, so Claude can run your resume work end to end, from your editor.

Published on npm
@juicedresume/mcpView on npm ↗

One-line install via npx, no global package management. Works with Claude Code, Claude Desktop, Cursor, Zed, or any MCP client.

claude mcp add --transport stdio juicedresume -- \
  npx -y --package=@juicedresume/mcp juicedresume-mcp

Connect it in 3 steps

1
Grab your MCP token
Open Settings → AI. Your unique token is there, along with a ready-to-paste JSON config that includes it. MCP access is free for all signed-in users; AI actions use your monthly AI credits.
2
Add the server with one command
Copy the claude mcp add snippet from Settings → AI (it has your token wired in) and paste it into your terminal. Or paste the JSON config block into ~/.claude.json manually.
3
Start building
In Claude Code, run /mcp to confirmjuicedresume is enabled, then ask Claude to “score my resume” or run /resume-tailor <job URL>. Every change Claude makes shows up live in your editor.

What Claude can do once connected

Read & edit resumes
List your resumes, read any one, and edit personal info, summary, sections, and bullets.
Score
Run the full ATS scoring engine and explain the top fixes per dimension.
Tailor to a JD
Match your resume against a job description: surface matched and missing keywords.
Export
Generate an ATS-clean or template-faithful PDF, ready to submit.
Social proof

100,000+ resumes built

Scored, tailored, and shipped by job seekers who needed the interview, not another template gallery.

Rewrote my bullets against the JD and my callback rate doubled within two weeks.
Priya S.
Senior Product Manager
Went from a 58 to an 86 on the scorer, then landed three interviews in ten days.
Daniel K.
Software Engineer
The ATS export just works. First resume of mine that didn't vanish into Workday.
Amara O.
Data Analyst

Ready to let Claude drive?

Create an account, grab your token from Settings → AI, and connect in minutes.

MCP server FAQ

What is the JuicedResume MCP server?
The JuicedResume MCP server is a published npm package (@juicedresume/mcp) that exposes your resumes as tools an AI assistant can call over the Model Context Protocol. Once connected, Claude Code (or any MCP client) can list, read, edit, score, tailor, and export your resumes directly from your editor.
How do I connect JuicedResume to Claude Code?
Grab your MCP token from Settings → AI, then run: claude mcp add --transport stdio juicedresume -- npx -y --package=@juicedresume/mcp juicedresume-mcp. Run /mcp inside Claude Code to confirm the juicedresume server is enabled.
Which MCP clients does it work with?
Any MCP client that speaks stdio: Claude Code, Claude Desktop, Cursor, and Zed are all supported. The same npx command works across them; only the config location differs.
Is the JuicedResume MCP server free?
Yes. MCP access is free for all signed-in users, on every plan including Free. AI actions (scoring fixes, tailoring, rewrites) use your monthly AI credits, and you can top up or upgrade if you need more.
What can Claude do once the MCP server is connected?
Read and edit your resumes (personal info, summary, sections, and bullets), run the full 60+ check ATS scorer, tailor a resume to a job description with matched and missing keywords, and export an ATS-clean or template-faithful PDF.
Do I need to install anything globally?
No. The server runs through npx, so there is no global package to manage. The one-line claude mcp add command handles everything per project.