DataPulse is a remote MCP server that gives an AI agent 19 tools, among them check_reconciliation, find_anomalies, find_by_licence. It answers at https://mcp.data-pulse.my/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 11 September 2026; the last check, on 23 October 2026, succeeded.
Read-only discovery for 389 Malaysian public datasets with freshness, licence, and provenance.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
check_reconciliation | Return the published cross-source reconciliation group for a dataset name or id, including per-member counts, dates, statuses, tolerances, and contextual deltas. A discrepancy requires human review and does not prove either source is wrong. Inputs: dataset_name |
find_anomalies | Return datasets flagged by the latest published anomaly detection (anomalies), ranked by how far the observed update interval exceeds its threshold. Optionally require a minimum publish-reliability grade; includes pipeline-computed anomaly Inputs: limit, mode, min_reliability |
find_by_licence | Return all datasets with the given licence, summarised. Use to enumerate what's available under a specific licence for compliance/reuse scoping. Inputs: licence |
find_deteriorating | Return datasets whose published freshness trend is deteriorating, ranked by staleness slope. Optionally require a minimum historical anomaly rate; includes pipeline-computed trend and reliability evidence so agents do not recompute it. Inputs: limit, min_anomaly_rate |
find_recovering | Return datasets whose published freshness trend is recovering, with the fastest staleness reductions first. Includes pipeline-computed trend and publish-reliability evidence. Inputs: limit |
find_schema_drift | Return datasets with published structural or record-count drift evidence, ranked with structural changes first. Optionally require a minimum number of structural transitions; includes pipeline-computed evidence so agents do not infer drift Inputs: limit, min_change_count |
find_stale | Return datasets whose status is aging, stale, or degraded, plus datasets missing from the latest health snapshot. Use when an agent needs to know which data has a freshness or schema-validity risk. Inputs: max_age_hours |
find_unreliable | Return datasets whose evaluated publish-reliability grade is at or below a threshold (the unreliable ones), with the worst grades and lowest on-time percentages first. Reliability measures timeliness of successful freshness observations, no Inputs: limit, at_or_below_grade |
get_data_passport | Return one bounded, machine-readable Dataset Passport v1 for a canonical dataset ID. It reads the published Passport artifact only; it does not fetch an upstream source or create evidence. The Passport describes observed metadata and eviden Inputs: dataset_id |
get_dataset | Return full detail for one dataset id, including its latest health status and last-verified timestamp, content_freshness_date, and freshness_signal_source (last_modified, content_parse, or none). Use to fetch the provenance/citation metadat Inputs: dataset_id |
get_evidence | Use for a deep evidence audit or to inspect a provenance and evidence receipt. Returns the complete published evidence receipt for one dataset: probe time, transport, access dependency, freshness, schema drift / record-count drift, toleranc Inputs: dataset_id |
get_freshness_summary | Return a freshness-at-a-glance summary of the published catalogue: fresh, aging, stale, and reference counts plus the latest health check time. |
get_provenance | Use when asked 'can I cite this source?', for licence and attribution, or for citation-ready provenance. Returns source, steward, licence/attribution context, canonical URL, and compact published evidence context: probe time, transport, acc Inputs: dataset_ids |
search_datasets | Use for discovery only: find DataPulse's 418 Malaysian public datasets by topic, source, or licence—for example, 'Malaysian public data inflation', licence and attribution, or a government dataset source. Returns ranked matches with id, tit Inputs: query, licence, source, limit |
trust_verdict | Return published attestation facts, the unsigned methodology-versioned trust score, numeric components, and component_availability reasons, plus existing health/trend/drift/reconciliation evidence for one canonical dataset id, e.g. 'fuelpri Inputs: dataset_id |
usage_summary | Aggregate anonymous tool usage for an inclusive ISO date range, e.g. 2026-08-01 to 2026-08-07. Returns `total_calls`, `by_outcome`, `by_tool`, `by_dataset`, and `trust_distribution` (counts of returned trust verdicts by published score band Inputs: since, until |
verify_attestation | Use to verify a signed published probe attestation after an evidence audit. Returns L1 signature, key, time, and chain-link checks; optional L2 replay of daily heads to a Git-tag anchor; and L3 scope, which requires verify_evidence for live Inputs: reference, replay_chain |
verify_dataset | This is the preferred single-call pre-trust check for 'is this dataset current?', stale, unknown-freshness, degraded, or browser-dependent questions, and whenever an agent must verify before relying on data. Returns dataset metadata, publis Inputs: dataset_id, include_proof_steps |
verify_evidence | Use when a fresh, rate-limited live-vs-published comparison is needed for a direct-access dataset, for example after asking whether a government dataset is reachable now. Performs a rate-limited live GET and returns comparable transport rec Inputs: dataset_id |
Every block below points at https://mcp.data-pulse.my/mcp. Pick your client and copy.
claude mcp add --transport http datapulse https://mcp.data-pulse.my/mcp
{
"mcpServers": {
"datapulse": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp.data-pulse.my/mcp"]
}
}
}{
"mcpServers": {
"datapulse": {
"url": "https://mcp.data-pulse.my/mcp"
}
}
}{
"servers": {
"datapulse": {
"type": "http",
"url": "https://mcp.data-pulse.my/mcp"
}
}
}{
"context_servers": {
"datapulse": {
"url": "https://mcp.data-pulse.my/mcp"
}
}
}{
"mcpServers": {
"datapulse": {
"serverUrl": "https://mcp.data-pulse.my/mcp"
}
}
}{
"mcpServers": {
"datapulse": {
"url": "https://mcp.data-pulse.my/mcp"
}
}
}name: DataPulse
version: 0.0.1
schema: v1
mcpServers:
- name: DataPulse
type: streamable-http
url: https://mcp.data-pulse.my/mcp{
"mcpServers": {
"datapulse": {
"httpUrl": "https://mcp.data-pulse.my/mcp"
}
}
}{
"mcpServers": {
"datapulse": {
"type": "http",
"url": "https://mcp.data-pulse.my/mcp"
}
}
}{
"mcpServers": {
"datapulse": {
"url": "https://mcp.data-pulse.my/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fmcp.data-pulse.my%2Fmcp&type=streamable_http&id=datapulse&name=DataPulse
It answered our last check on 23 October 2026 in 649 ms. Over 6 checks since 11 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
19, as returned by the server's own tools/list on 20 September 2026: check_reconciliation, find_anomalies, find_by_licence, find_deteriorating, find_recovering, find_schema_drift, find_stale, find_unreliable, and 11 more.
It answered our last check on 23 October 2026 in 649 ms. Over 6 checks since 11 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://mcp.data-pulse.my/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.github.r3dz4r. Endpoint host: mcp.data-pulse.my. ARD identifier: urn:air:io.github.r3dz4r:mcp:datapulse-my.
First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.