NBMEcalc MCP

MCP serverDev tools

Remote MCP server for deterministic educational practice-assessment score conversions.

Available today. Use it from your connected AI after setup.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Then ask your AI: use NBMEcalc MCP to convert practice score

Install NBMEcalc MCP

The server’s own address, for the clients that take one directly. Or connect ahel onceand every client you use reads it from one address, with the account kept on ahel rather than in each client’s config.

  • Claude Code

    claude mcp add --transport http --scope user nbmecalc-mcp 'https://nbmecalc-mcp.chenxuanshimo.workers.dev/mcp'

    Run it once in your project, then open /mcp to approve any sign-in the server asks for.

  • Claude Desktop

    https://nbmecalc-mcp.chenxuanshimo.workers.dev/mcp

    Add a custom connector in Settings, paste this address, and approve the sign-in.

  • Cursor

    cursor://anysphere.cursor-deeplink/mcp/install?name=nbmecalc-mcp&config=eyJ1cmwiOiJodHRwczovL25ibWVjYWxjLW1jcC5jaGVueHVhbnNoaW1vLndvcmtlcnMuZGV2L21jcCJ9

    Open the link and Cursor adds the server at that address.

  • ChatGPT

    https://nbmecalc-mcp.chenxuanshimo.workers.dev/mcp

    In Settings, enable Developer mode, create an MCP app, and paste this address. Your plan and workspace must allow custom apps.

  • Codex

    codex mcp add nbmecalc-mcp --url 'https://nbmecalc-mcp.chenxuanshimo.workers.dev/mcp'

    Run it once, then sign in with codex mcp login nbmecalc-mcp if the server asks for an account.

From the project's README

As published by jiankn/nbmecalc-mcp in README.md.

A remote Model Context Protocol server exposing deterministic, offline practice-assessment conversions for integrations that complement the USMLE score predictor.

The Streamable HTTP endpoint is /mcp. The server exposes convert_practice_score and returns the estimate together with the v1.1 algorithm identifier and a required disclaimer.

It has no database, account system, analytics call, or learner-data storage. Mappings are independent model assumptions, not official conversions or examination guarantees. Do not use outputs for clinical decisions.

npm install
npm test
npm run check
npm run deploy:dry

Apache-2.0 licensed.

Tools it offers (1)

What this server listed when ahel dialed its public endpoint in Sep 2026, with no key and no account of yours. The names are the server’s own.

  • convert_practice_score

Signals

Last commit
Sep 2026
Advanced
Delivery
nbmecalc MCP server → your ahel connector (mcp.ahel.ai) → your AI.
Item type
mcp-server
Key
io-github-jiankn-nbmecalc
Source
github.com/jiankn/nbmecalc-mcp
Hosted endpoint
https://nbmecalc-mcp.chenxuanshimo.workers.dev/mcp