mcpField
E
exam-sheet

exam-sheet

Local
github.com/giuliobmbScience & Education

About exam-sheet

exam-sheet is an MCP server for creating timed exams on any topic and taking them in an interactive sheet inside an MCP host. It supports objective and open questions, with grading and a final score report.

Key features

  1. 01Timed interactive exams
  2. 02True/false, multiple-choice, and open questions
  3. 03Instant grading for objective questions
  4. 04Model-graded open answers
  5. 05Final report with score out of 100

Use cases

  1. 01Create a timed exam on a chosen topic
  2. 02Practice with immediate feedback on objective answers
  3. 03Review model feedback and a final exam score

MCP support

The server registers an interactive exam sheet as an MCP Apps resource, with an adaptation for ChatGPT's Apps SDK. It can run locally over stdio or as a remote Streamable HTTP endpoint; remote sessions use MCP sampling through the connected client's model.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"giuliobmb-exam-sheet": {
"command": "npx",
"args": [
"-y",
"@giuliobmb/exam-sheet-mcp"
],
"env": {
"ANTHROPIC_API_KEY": "<ANTHROPIC_API_KEY>"
}
}
}
}
Run commandnpx -y @giuliobmb/exam-sheet-mcp
Environment variables to set
ANTHROPIC_API_KEYSecretAPI key used to generate questions and grade open answers.

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@giuliobmb/exam-sheet-mcp1.0.0

Tools

3

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
topicstringYesSubject or topic for the exam.
typesarrayNoQuestion types to mix.
numQuestionsintegerNo
timeLimitMinutesanyNoTime limit in minutes, or null for no limit.

Details

The maintainer has not added details yet. Check the README in the repository.

Comments

Markdown supported

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.