DataPulse MCP server

DataPulse

Live dashboard: https://www.data-pulse.my

Open in Google Colab:

-success?style=flat&logo=anthropic) <!-- m8ven-verify: d1505f0f7e0429963789e95995216ca3 -->

🤖 AI-agent-ready — Wire DataPulse into Claude Desktop, Cursor, Cline, or

any MCP-compatible client with one config block. Your agent gets

<!-- BEGIN readme-hero -->

418 official Malaysian datasets — including 30 GTFS transit feeds (KTMB, Prasarana, BAS.MY) — with declared licences and an honest ten-status trust taxonomy instead of a blanket green checkmark. <!-- END readme-hero -->

→ Connect your AI agent in 30 seconds

This is DataPulse

When an AI quote is wrong, it is often wrong because the underlying data was stale, mis-licensed, or unverifiable — not because the model hallucinated. An official-looking page does not tell an agent when the dataset behind it last updated, who published it, whether it may legally be reused, or whether the observation can be reproduced by a second party.

DataPulse exists to make that uncertainty explicit. It is an open, read-only verification layer for Malaysian public data: it continuously probes <!-- BEGIN readme-cover -->418 official datasets<!-- END readme-cover -->, and publishes — for each one — machine-readable evidence about whether the source is reachable, how fresh the content is, what licence applies, how the schema behaves, and when the observation was signed.

It does not replace the official source. It documents, on an honest and reproducible basis, what the official portal states and whether that material is current, so you know what you are reusing or citing. The verification speaks for itself: every claim here is a live, checkable artefact, not a promise.

What we do, simply

declared cadence and records what it actually finds — reachability, an honest freshness signal, schema shape, record counts, and collection quirks.

• We watch the sources. A scheduled probe revisits each dataset under its

dataset carries one of ten honest health statuses (fresh, aging, stale, discontinued, degraded, browser-dependent, unreachable, unknown, unknown-freshness, reference). A dataset that cannot be proven fresh is labelled unknown-freshness — not silently treated as healthy.

• We state the truth plainly. Instead of a blanket green checkmark, each

and recorded to an immutable public log, so you can verify when DataPulse observed the source and that the record has not been altered.

• We publish evidence, not just claims. Each dated observation is signed

from one index and queryable over a read-only MCP server, so an agent receives the same freshness, licence, and provenance signal a careful human reviewer would.

• We make it machine-readable first. The whole portfolio is discoverable

Who this serves

Shortened. The full README is on GitHub.