exam-sheet-mcp

exam-sheet-mcp

Generates timed exams on any topic with an interactive exam sheet in MCP hosts; supports true/false, multiple-choice, and open questions with instant or model grading and a final report out of 100.

Category
Visit Server

README

Exam Sheet — an MCP App

Generate a timed exam on any topic and take it in an interactive exam sheet that renders directly inside an MCP host (Claude Desktop, VS Code, etc.). Supports true/false, multiple-choice, and open questions. Objective questions are graded instantly; open answers are graded by the model. At the end you get a report with a grade out of 100.

Installation

Add the server to your MCP host config, e.g. claude_desktop_config.json:

{
  "mcpServers": {
    "exam-sheet": {
      "command": "npx",
      "args": ["-y", "@giuliobmb/exam-sheet-mcp"],
      "env": { "ANTHROPIC_API_KEY": "sk-ant-..." }
    }
  }
}

Restart the host after saving the config.

As a remote connector (Claude.ai or ChatGPT)

The same server also runs as a remote Streamable HTTP endpoint at /mcp (src/httpServer.ts), so it can be added as a connector by URL instead of a local install — on Claude.ai directly, or on ChatGPT via Settings → Apps → Advanced settings → Developer mode → Add connector. In that mode it has no API key of its own — question generation and grading go through MCP sampling, i.e. the connected client's own model — and each session gets its own isolated exam store.

The exam sheet UI is registered twice: once as an MCP Apps resource for Claude, once adapted for ChatGPT's Apps SDK (_meta["openai/outputTemplate"] on generate_exam, via @mcp-ui/server's appsSdk adapter) — same HTML, no changes needed between hosts.

Deploy it anywhere that runs a Node web service (a render.yaml blueprint is included for Render's free tier); then add https://<your-deployment>/mcp as a connector URL.

Usage

Ask the host to run generate_exam with a topic, e.g. "Generate an exam on the French Revolution." The interactive sheet opens with a timer; answer each question and submit to see instant grading (or model-graded feedback for open questions). At the end you get a full report with a grade out of 100.

Local development

npm install
npm test          # runs the unit tests (no network, no API key needed)
npm run typecheck
npm run build     # compiles TypeScript to dist/
export ANTHROPIC_API_KEY=sk-ant-...
npm start         # runs the server over stdio
npm run start:http  # runs the remote (Streamable HTTP) entrypoint on :3000

To try a local build in Claude Desktop, point the config at the compiled file instead of the npm package:

{
  "mcpServers": {
    "exam-sheet": {
      "command": "node",
      "args": ["/absolute/path/to/exam-mcp/dist/index.js"],
      "env": { "ANTHROPIC_API_KEY": "sk-ant-..." }
    }
  }
}

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured