What's inside​

• Mingo Sprint — two rounds of five lesson questions, Relaxed or Beat the Clock, 2 Sparks per right answer.
• Twelve quick games — six for Basic 1 to 6 and six for secondary school, each with step-by-step screenshots of the real game and its levels.
• Sparks and the Style Lab — every way to earn, the 60-a-day limit, outfit prices and the Beginner, Stylish and Iconic ranks.
• The Mingo Ladder — 70 steps from Rookie to Legend, gift boxes, streak shields and term seasons.
• Stickers and playing with friends.
• The Sunday class competition — 4 pm to 5 pm Lagos time, three knockout rounds, monthly points and prize Sunday, plus how MMT tokens from lessons can earn a seat in the class final.

Written for families​

Every page is in plain language, with numbered steps, tables and screenshots taken from the app itself — no made-up drawings. Every number in it comes from the rules the app actually runs. If the team changes a price in the Style Lab, the app always shows the current one.

Why MCP matters for edtech​

A lot of new study software isn't a traditional app at all — it's an agent. A chat tutor, an IDE-style "explain this" assistant, a WhatsApp study buddy. Those agents are only as good as the tools they can reach.

The problem with most AI tutors is the same one we've always had: when an LLM invents exam questions, students practise on material that won't appear and sometimes isn't even correct. MCP fixes the plumbing; MirrorMingo fixes the content. Together, the agent stops guessing and starts pulling real past papers, then marks the student against the verified answer key.

What is MCP, briefly​

The Model Context Protocol is an open standard for connecting AI assistants to tools and data. A "server" exposes tools; a "client" lets the model call them. MirrorMingo ships an MCP server, so MCP-capable clients can use our exam tools with zero glue code.

Setup​

pip install mirrormingo
export MIRRORMINGO_API_KEY=mirrormingo_xxx   # from Account → Developer

Add it to your MCP client config:

{
  "mcpServers": {
    "mirrormingo": {
      "command": "mirrormingo-mcp",
      "env": { "MIRRORMINGO_API_KEY": "mirrormingo_xxx" }
    }
  }
}

Restart your MCP client. That's the whole integration.

Use it​

You: Use MirrorMingo to give me 5 real JAMB Physics questions, one at a time. Mark each answer and explain what I get wrong.

Behind the scenes the agent calls list_mock_papers to find a Physics paper, open_mock_paper to pull real questions, and submit_mock_attempt to score your answers — all against verified content, none of it invented.

The tools​

Safe by design​

The MCP server is a thin layer over the same public API as our SDKs. It uses your API key, so it inherits the same authentication and rate limits — an agent can never reach beyond what your key allows. And because it's the same contract, your MCP tutor and your REST-based app stay perfectly in sync.

SDK or MCP — which?​

Both, usually. Use the SDKs for deterministic app logic (a timed exam UI, a nightly sync job). Use the MCP server when an LLM should decide when to fetch questions and how to coach. Same content underneath.

Get an API key →

Why we built it​

Every team building a study app in Nigeria — and across Africa — hits the same wall. The questions.

Authentic past papers are scattered across PDFs, photocopies and link-rot. Re-keying them is slow and error-prone, and the tempting shortcut — asking an LLM to "generate JAMB questions" — produces plausible nonsense that quietly teaches students the wrong things.

We spent years assembling and verifying this content against official exam-board sources. Our one rule has never changed: we never fabricate a question. Now you can build on that same foundation instead of rebuilding it.

What you get​

• An exam registry — supported exams with official section specs, timing, question types and scoring rubrics.
• Verified past papers — grouped by year, each with a stable paper_id.
• A mock-exam engine — open a paper into a timed attempt, page through questions, submit answers, get scored feedback.
• Verified source links — official exam-board and past-question references.

Hello, world​

import { MirrorMingo } from "@mirrormingo/sdk";

const mm = new MirrorMingo({ apiKey: process.env.MIRRORMINGO_API_KEY });
const learnerId = "student-42";

const catalog = await mm.mockExams.listPapers("jamb");
const attempt = await mm.mockExams.open("jamb", {
  paperId: catalog.years[0].papers[0].paper_id,
  questionLimit: 10,
  learnerId,
});

const answers = Object.fromEntries(
  attempt.questions.slice(0, 3).map((question) => [
    question.answer_id ?? String(question.question_number),
    "A",
  ]),
);
const result = await mm.mockExams.submit("jamb", {
  attemptId: attempt.attempt_id,
  answers,
  learnerId,
});
console.log(result.feedback);

Six SDKs, one source of truth​

We ship official SDKs for TypeScript/Node, Python, Java, PHP, Go and Dart. All six are generated from a single OpenAPI spec, so they never drift from the API. The TypeScript SDK is hand-crafted for the DX we wanted across our own apps.

Built for the agent era too​

Because so much new learning software is being built by AI agents, we also ship a Model Context Protocol (MCP) server. Point any MCP-capable app, IDE, or agent at it and it can pull real JAMB questions and mark answers — no glue code. More on that in the next post.

Pricing & access​

Start free in the sandbox with non-billable test keys. Production keys are metered per request with a generous free tier. Create your first key at Account → Developer.

Get started​

• Quickstart
• Integration guide
• API reference

We can't wait to see what you build. Tell us at developers@mirrormingo.com.