GDP, inflation, trade, population, the real‑estate price index — 277 official GASTAT datasets, live from DataSaudi, answered right inside your AI client. You never name a dataset; the model finds it.

Here it is in Claude Desktop — one plain‑English question, and the model finds the dataset, pulls Riyadh's real‑estate price index against the national trend, and charts it:

Ask it anything

Connect it in about 2 minutes (Install), then just ask:

💬  "What was the real‑estate price index in Riyadh by quarter, and how does it compare to the national trend?"

💬  "Who are Saudi Arabia's top trading partners? Break foreign trade down by country and exports vs. imports."

🇸🇦  "اعرض الرقم القياسي لأسعار العقارات في الرياض حسب الربع"   — ask in Arabic, get Arabic back (الرياض, مكة المكرمة). See Arabic support.

The model discovers the right dataset, pulls the numbers, and answers. You don't need to know any dataset names or query syntax.

What you can ask about

277 curated GASTAT / DataSaudi datasets. Every query hits the live API, so the numbers are as current as GASTAT publishes.

[!IMPORTANT] Where it stops — on purpose. A data tool you can trust tells you its edges.

• Serves the real‑estate price index (base‑year 100) — not per‑deal prices in riyals (those live in MoJ / Srem).
• No MoJ transaction volumes, no REGA, no municipal / ZATCA / CMA data, no microdata. This is the ~277‑series headline‑indicator layer, not the full national corpus.
• Geographic detail stops at the province level for most series — no city / district breakdown.

Ask for something outside this and the server says so plainly, rather than guessing.

Install

No API key, nothing to configure — DataSaudi is keyless. You'll need uv installed.

Claude Code — one line, no file editing:

claude mcp add datasaudi -- uvx datasaudi-mcp

{
  "mcpServers": {
    "datasaudi": {
      "command": "uvx",
      "args": ["datasaudi-mcp"]
    }
  }
}

{
  "mcpServers": {
    "datasaudi": {
      "command": "uvx",
      "args": ["datasaudi-mcp"]
    }
  }
}

Then ask one of the questions above.

Arabic support

Saudi data in Arabic, as a first‑class feature — not an afterthought.

• Ask in Arabic, get Arabic back. Member names return in Arabic script: الرياض for Riyadh, مكة المكرمة for Makkah, المنطقة الشرقية for the Eastern Region.
• Catalog search works in Arabic too — an Arabic term matches the datasets' Arabic topic / source annotations.
• Numbers and structure are identical across languages — only the human‑readable captions change.

The tools

Three tools do the work; the model calls them for you.

Contributing

Contributions welcome — see CONTRIBUTING.md. To develop locally:

git clone https://github.com/mohsinmshabbir/datasaudi-mcp
cd datasaudi-mcp
uv sync --all-extras
uv run pytest -m "not live"    # offline test suite
uv run pytest -m live          # optional: hits the real API

License

MIT — see LICENSE.