How it works

    Your AI assistant
    learns to find data.

    01·Discovery

    21 platforms, one query

    Every search fans out in parallel: Kaggle, Hugging Face, Zenodo, arXiv, World Bank, NASA, and 15 more. Results stream back as they arrive.

    search_datasets("air quality")
    SCANNING 21 PLATFORMS...
    KaggleGlobal Air Pollution Dataset23,463CC BY 4.0
    data.govUS EPA Air Quality Index1.2MPublic Domain
    WHO GHOAmbient Air Quality Database67,200CC BY-NC-SA
    ZenodoEuropean Air Quality 2000–20214,891CC BY 4.0
    arXivUrban PM2.5 Sensor Calibration12,044Open Access
    02·Evaluation

    Preview before you download

    Inspect the first N rows of any dataset. Compare side by side. Check schema compatibility and data quality before committing.

    preview_dataset · zenodo:5016186 · showing 5 of 67,200 rows
    idcountryyearpm2.5pm10no2
    1USA20218.218.412.1
    2Germany202110.120.315.7
    3Japan202111.824.118.9
    4Brazil202114.331.622.0
    5India202128.755.238.3
    03·Output

    Cite, visualize, monitor

    Generate APA, BibTeX or Chicago citations. Check license compliance. Open interactive dashboards. Watch for new results.

    generate_citation · BibTeX
    @dataset{WHO2021,
  author  = {World Health Org.},
  title   = {Ambient Air Quality},
  year    = {2021},
  license = {CC BY-NC-SA},
  url     = {https://who.int/data/gho}
}
    Commercial use
    Attribution required
    Share-alike
    15 MCP tools

    Everything in
    one server.

    Connect once to Cursor or Claude Desktop. All tools appear automatically in the chat.

    View on GitHub →
    Discovery
    search_datasets()
    Search all 21 platforms at once
    find_research_datasets()
    Datasets used in papers
    find_similar()
    Datasets similar to one you have
    Evaluation
    get_dataset_details()
    Full metadata
    preview_dataset()
    First N rows
    compare_datasets()
    2–5 side by side
    Quality & Compliance
    assess_quality()
    Missing values, duplicates, stats
    check_license()
    Commercial / academic / internal
    check_compatibility()
    Schema match against yours
    Citation & Output
    generate_citation()
    APA, BibTeX, Chicago
    visualize_dataset()
    Interactive ECharts dashboard
    watch_query()
    Monitor for new datasets
    Advanced Research
    get_dataset_provenance()
    Introducing paper & history
    get_dataset_lineage()
    Variants & derivatives
    trace_citation_graph()
    Citation chain analysis
    Open source, MIT licensed. Built for the community.
    ★ mobus-ai / Mobus