MCP Dubai
Dubai and UAE public data for AI assistants
From the maker
MCP-Dubai is an open-source Model Context Protocol server connecting AI assistants to Dubai and UAE public APIs, reference datasets, and curated business setup resources. It covers weather, currencies, prayer times, places, public dataset discovery, free zones, visas, banking, and company setup. It runs locally over stdio on Python 3.11+ and is MIT licensed. The repository source includes 120 tools across 37 features; the published PyPI 0.2.0 package includes 91 tools and runs with uvx mcp-dubai. Some integrations require credentials or depend on upstream availability. See the README for installation and data freshness. This is an independent community project.
How to connect
This server runs locally. Its maker says to start it with:
uvx mcp-dubai
We have not run this command. We do not execute commands submitted to us, so this listing carries no connection record. What we could check without running anything is below.
What we found on PyPI
We did not run this server. Its start command names a package, so on 29 September 2026 we asked PyPI what it holds under that name. This describes the published package, not what the server does once it is running.
- Package
- mcp-dubai
- Latest version
- 0.2.0
- That version published
- 2026-04-15
- First published
- 2026-04-13
- Licence field says
- MIT
- Repository it points at
- https://github.com/mahdi-salmanzade/MCP-Dubai
- Asked
- 2026-09-29 09:58 UTC
Anything above describes one moment on the date shown. We do not re-test on a schedule, so nothing here says what this server is doing now. We have not audited its code, its data handling or its permissions, and this is not a safety rating.
1 comment
What readers said about this product. Comments are people's own opinions and are not part of anything we checked.
Rated 4 out of 5 4.0 from 1 rating. Includes ratings from makers reviewing earlier launches as part of launching their own. Ratings do not affect rank.
Documentation review: The README clearly distinguishes public APIs, bundled reference data, and credential-protected government datasets, and documents freshness and upstream limitations. This is useful for developers building UAE-focused assistants. The main onboarding gap is the release mismatch: the documented source has 120 tools, while the uvx/PyPI release has 91. A current package release and a short end-to-end client example would make the first connection easier. I have not tested runtime reliability.
Sign in to comment. Same account that votes.
Comments are written by readers, not by us, and we do not endorse them. Nothing here is held back or approved first: a comment goes up when it is posted, and you can edit or delete your own at any time. Report anything illegal or abusive with the link on each comment, or by email from our contact page if you do not have an account.