About NBMEcalc MCP
NBMEcalc MCP is a remote server for deterministic conversions of educational practice-assessment scores. It returns an estimate with its algorithm version and a disclaimer, for integrations complementing the USMLE score predictor.
Key features
- 01Deterministic practice-score conversion
- 02Estimate includes algorithm identifier
- 03Required disclaimer
- 04Offline operation without learner-data storage
Use cases
- 01Add practice-score estimates to an integration
- 02Inspect the conversion algorithm version
MCP support
The remote MCP server exposes `convert_practice_score` over Streamable HTTP at `/mcp`. It returns an estimate, the `v1.1` algorithm identifier, and a disclaimer.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://nbmecalc-mcp.chenxuanshimo.workers.dev/mcpclaude mcp add --transport http jiankn-nbmecalc https://nbmecalc-mcp.chenxuanshimo.workers.dev/mcp{"mcpServers":{"jiankn-nbmecalc":{"type":"http","url":"https://nbmecalc-mcp.chenxuanshimo.workers.dev/mcp"}}}Open in Cursor{"servers":{"jiankn-nbmecalc":{"type":"http","url":"https://nbmecalc-mcp.chenxuanshimo.workers.dev/mcp"}}}Open in VS Code{"mcpServers":{"jiankn-nbmecalc":{"type":"http","url":"https://nbmecalc-mcp.chenxuanshimo.workers.dev/mcp"}}}{"mcpServers":{"jiankn-nbmecalc":{"serverUrl":"https://nbmecalc-mcp.chenxuanshimo.workers.dev/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
1| Parameter | Type | Required | Description |
|---|---|---|---|
| form | integer | No | Optional NBME form number |
| step | enum | Yes | STEP_1 | STEP_2 | STEP_3 |
| score | number | Yes | |
| source | enum | Yes | NBME | UWSA_1 | UWSA_2 | FREE_120 | AMBOSS | CMS |
Details
From the project READMENBMEcalc MCP
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.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.