BanqueUNT MCP
BanqueUNT MCP lets students study from a medical question bank through an AI assistant while keeping answer keys hidden until grading.
Count questions by course, specialty, year, and topic.
Search questions by text and filters without revealing answers.
Generate random mock exams of 1–100 questions, prioritizing unseen questions.
Grade a mock exam once with score, answer key, and explanations for wrong answers.
Review progress, accuracy by specialty/topic, weak topics, and recently failed topics.
Get full explanations only for questions already answered and graded.
Access course/topic/question resources and tutoring/practice prompts such as one-question review and weak-topic exams.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@BanqueUNT MCP Give me a 10-question mock exam on Cardiology."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
BanqueUNT MCP
An MCP server that connects the BanqueUNT medical question bank (1,400+ exam questions from the Universidad Nacional de Trujillo, Peru) to AI assistants such as Claude, Cursor and VS Code Copilot.
Students can search questions, take mock exams, get graded with detailed explanations and track their weak topics, all from a chat with their favorite assistant. The server is built so the assistant cannot see the answer key before grading, so the practice stays honest.
The full bank is private. This repository ships with a public sample of 30 questions from past exams, so everything below works out of the box.
Demo

Claude Code with the bundled sample bank (in Spanish): generar_simulacro → the student answers → corregir_simulacro → mi_progreso.
Related MCP server: Moodle Study MCP
Features
Tools
Tool | What it does |
| Counts questions by course, specialty, year and topic. Duplicates published in several exams count once. |
| Full-text search (accent and case insensitive) with filters and cursor pagination. Never returns the answer. |
| Builds a random mock exam (1–100 questions), preferring questions the student has not seen yet. Stored with an expiry time. |
| Grades a mock exam once: score, answer key and a normalized explanation for every wrong answer. Records results by topic. |
| History, accuracy by specialty and topic, the 5 weakest topics and recently failed topics. |
| Full explanation of a question the student has already answered and had graded. |
Every tool declares an input and output schema with zod and returns structuredContent; read-only tools are annotated with readOnlyHint.
Resources and prompts
banqueunt://cursos,banqueunt://cursos/{curso}/temas(with argument completion) andbanqueunt://pregunta/{id}(public version, no answer).sesion_de_repaso: a tutor that asks one question at a time, waits for the answer, grades it and explains.repasar_temas_debiles: reads your progress and builds a mock exam from your weak topics.
Use it remotely (BanqueUNT students)
The server is deployed on Cloudflare Workers. If you have a BanqueUNT account, you don't need to install anything: add this URL as a connector in your MCP client and sign in with your BanqueUNT email and password.
https://banqueunt-mcp.zumaetaadriel2.workers.dev/mcpClaude.ai (web, desktop and mobile): Settings → Connectors → Add custom connector → paste the URL → Connect.
Claude Code:
claude mcp add --transport http banqueunt https://banqueunt-mcp.zumaetaadriel2.workers.dev/mcp, then/mcp→banqueunt→ Authenticate.Cursor, VS Code and other clients that support remote MCP servers with OAuth: add it as a Streamable HTTP server with the same URL.
You only see the courses your BanqueUNT account has access to, and your progress is kept per account. Your password goes straight to BanqueUNT's sign-in and is never stored by the server.
Run it locally
Requires Node.js 22.13 or later (it uses the built-in node:sqlite).
git clone https://github.com/zumaetaadriel2/banqueunt-mcp.git
cd banqueunt-mcp
npm ci
npm run buildThen add the server to your client. Replace the path with the absolute path to dist/index.js on your machine.
Claude Code
claude mcp add --scope user banqueunt -- node /absolute/path/to/banqueunt-mcp/dist/index.jsClaude Desktop
Edit claude_desktop_config.json (Settings → Developer → Edit Config) and restart the app:
{
"mcpServers": {
"banqueunt": {
"command": "node",
"args": ["C:\\path\\to\\banqueunt-mcp\\dist\\index.js"]
}
}
}Cursor
Add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (project):
{
"mcpServers": {
"banqueunt": {
"command": "node",
"args": ["/absolute/path/to/banqueunt-mcp/dist/index.js"]
}
}
}VS Code (GitHub Copilot agent mode)
Add to .vscode/mcp.json:
{
"servers": {
"banqueunt": {
"type": "stdio",
"command": "node",
"args": ["/absolute/path/to/banqueunt-mcp/dist/index.js"]
}
}
}Then ask: "How many questions are there per specialty?" or "Give me a 10-question mock exam."
Configuration
All settings are environment variables, passed through the env field of your client config.
Variable | Default | Description |
| (unset: bundled sample) | Path to a local bank folder containing |
|
| Enabled courses, comma separated. |
|
| SQLite file for mock exams and progress ( |
| (unset: no limit) | Maximum questions a user can receive per day (resets at midnight, Peru time). |
Architecture
flowchart LR
client["AI assistant<br/>(Claude, Cursor, VS Code)"] -- "MCP over stdio" --> server
subgraph server["banqueunt-mcp"]
tools["tools · resources · prompts"]
dominio["domain<br/>search · mock exams · grading · progress"]
publico["aPreguntaPublica()<br/>strips key, explanation and topic"]
tools --> dominio
dominio --> publico
end
dominio --> fuente["question source<br/>sample JSON or local bank folder"]
dominio --> repo[("SQLite<br/>mock exams · results · call log")]src/
index.ts stdio entry point
worker.ts Cloudflare Workers entry point: OAuth 2.1 + Streamable HTTP
remoto/ remote mode: Supabase sign-in, token props, login rate limit, consent page, R2 bank
server.ts registers tools, resources and prompts
datos/ zod schema, explanation normalizer, dedup signature, question sources
dominio/ pure logic: search, mock exams, grading, progress, daily limit
persistencia/ ProgresoRepo interface + SQLite (local) and Cloudflare D1 (remote) implementations
tools/ one file per group of tools
tests/ Vitest: unit tests + end-to-end tests with a real MCP client in memoryDesign decisions
No answer leaks before grading. Every pre-grading output goes through a single function,
aPreguntaPublica(), which removes the key, the explanation and also the topic (a topic such as "Digoxin toxicity" gives the answer away). Integration tests serialize the response of every tool and fail if any of that appears.Two explanation formats, one output. The bank mixes an old
{correcta, descarte}format with a richer one (key idea, why each option is wrong, what to remember, reference). Both are validated with a zod union and normalized into a singleExplicacion.Deduplication. The same question often appears in several exams. A signature over the normalized stem and sorted options (ported from the original app) keeps counts and mock exams free of repeats.
Bank protection. Searches return at most 20 questions per call, an optional daily cap limits how many questions a user can receive, and every call is logged (
npm run uso) to spot bulk extraction.Async persistence interface.
ProgresoRepois async so the local SQLite implementation and the planned Cloudflare D1 one share the same contract.
Development
npm test # Vitest (set BANQUEUNT_DATA to also validate the full bank)
npm run lint # ESLint
npm run typecheck # tsc --noEmit
npm run inspector # open MCP Inspector against dist/index.js
npm run uso -- 7 # calls and questions served per user in the last 7 daysRoadmap
Test more clients (Cursor, ChatGPT, Gemini) against the remote server.
More courses (ENCIB, Residentado) and images.
npx banqueunt-mcpon npm.
License
Code under the MIT License. The bundled sample (data/muestra.json) contains questions from past exams for demonstration only; the full BanqueUNT bank is not part of this repository.
Available Tools
6 toolsbuscar_preguntasBuscar preguntasARead-only
Busca preguntas del banco por texto y filtros. Devuelve enunciado y alternativas, nunca la respuesta ni la explicación. Para practicar con corrección usa generar_simulacro.
Inputs: anio, tema, curso, texto, +5 more. Returns: curso, total, preguntas, siguiente
corregir_simulacroCorregir simulacroA
Corrige un simulacro generado con generar_simulacro. Devuelve la nota, la clave de cada pregunta y la explicación de las falladas. Las preguntas sin respuesta cuentan como incorrectas. Cada simulacro se corrige una sola vez.
Inputs: respuestas (required), simulacro_id (required). Returns: curso, items, total, aciertos, +3 more
estadisticas_bancoEstadísticas del bancoARead-only
Cuenta las preguntas del banco por curso, especialidad y año (y por tema si se indica una especialidad). Las preguntas repetidas en varios exámenes se cuentan una sola vez. No devuelve preguntas ni respuestas.
Inputs: curso, especialidad. Returns: cursos, origen
explicar_preguntaExplicar preguntaARead-only
Devuelve la clave y la explicación completa de una pregunta que el alumno YA corrigió en un simulacro. No sirve para preguntas que todavía no respondió.
Inputs: pregunta_id (required). Returns: tema, pregunta, explicacion
generar_simulacroGenerar simulacroA
Arma un simulacro al azar con preguntas del banco, sin repetir y priorizando las que el alumno aún no vio. Devuelve un simulacro_id y las preguntas numeradas SIN respuesta. Muéstralas al alumno sin resolverlas y, cuando responda, llama a corregir_simulacro.
Inputs: anios, curso, temas, cantidad, +4 more. Returns: curso, total, nuevas, expira_en, +4 more
mi_progresoMi progresoARead-only
Resume los simulacros corregidos del alumno: porcentaje global, rendimiento por especialidad, temas débiles (2+ respuestas), temas fallados recientemente y últimos simulacros. Úsalo para recomendar qué repasar.
Inputs: curso. Returns: ultimos, aciertos, porcentaje, simulacros, +4 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
Each tool targets a clearly distinct action in the study workflow: counting bank statistics, searching questions, generating a practice exam, summarizing progress, grading an exam, and explaining an already-graded question. The descriptions explicitly clarify boundaries, such as buscar_preguntas never returning answers and explicar_pregunta only working after correction.
All names use consistent snake_case and are readable. However, four tools follow a verb_noun pattern (buscar_preguntas, generar_simulacro, corregir_simulacro, explicar_pregunta) while two use noun/possessive forms (estadisticas_banco, mi_progreso), a minor deviation from a single predictable convention.
Six tools is well-scoped for a question-bank practice assistant. Each tool covers a necessary step in the student workflow without redundancy or filler.
The surface covers the core lifecycle: inspect bank stats, search questions, generate a simulacro, grade it, review progress, and explain missed questions. Minor gaps include no explicit tool to list available courses/specialties/themes for filter discovery, though estadisticas_banco partially surfaces that metadata.
Maintenance
Related MCP Connectors
Build study flashcards and exam-prep decks from your AI chat, all stored locally.
Create AI-generated exam questions and save them to your paperee question bank for review.
Turn what you learn with AI into study books with readings, flashcards and quizzes.
Spaced-repetition flashcards your AI writes, quizzes you on by voice, and schedules with FSRS.
Related MCP Servers
AlicenseBqualityBmaintenanceEnables AI assistants to interact with the EduBase educational platform to create quizzes, upload questions, schedule exams, manage educational content, and analyze user results through natural language.1531,294 npm28MIT- FlicenseNot gradedqualityDmaintenanceEnables AI assistants to read your Moodle courses, list materials, quizzes, and search content to plan exam preparation through natural language.1-
- AlicenseNot gradedqualityCmaintenanceEnables MCP-compatible AI assistants to search an exam-prep catalog, retrieve 204 free practice questions with answers and explanations across 15 IT and nursing certifications, check pricing, and get official exam facts.MIT
- AlicenseAqualityNot gradedmaintenanceEnables AI hosts to import PDFs, photos, and exam papers through local stdio MCP tools, using TextIn OCR to build a versioned wrong-answer bank that keeps original evidence and image crops for human review. Supports retrieval, revision history, practice attempts, dated review queues, and printable offline HTML exports of error notebooks, student workbooks, and answer books.32MIT