Research databases your AI assistant can search
Kahubi connects to national archives, scholarly literature, clinical registries, life-science databases, official statistics and EU law through the open Model Context Protocol (MCP). Connect a source in one click, ask in plain language, and every answer cites the records it came from.
- databases ready to connect
- 100
- databases ready to connect
- research fields
- 10
- research fields
- more on the way
- 8
- more on the way
Archives & heritage
National archives, digitised manuscripts, museum and library collections.
Riksarkivet (Swedish National Archives)
Search AI-transcribed handwritten records from the 1600s onward, the national archive catalogue, church books, court records and more.
Europeana
Search 50+ million digitised items from European museums, libraries and archives.
Trove (National Library of Australia)
Australian newspapers, books, images, maps and archives from the National Library of Australia.
Libris (Kungliga biblioteket)
The Swedish national union catalogue: books, journals, theses, maps and music in Swedish libraries.
Kubhist historical newspapers (Språkbanken Korp)
Full-text concordance search in digitised Swedish newspapers 1645–1926, by title and decade.
Nasjonalbiblioteket (Norway)
Norwegian newspapers from 1763, books, periodicals, photos and maps with full-text search.
Gallica (Bibliothèque nationale de France)
French national library: newspapers, manuscripts, maps, books and images, with OCR full-text search.
Delpher (KB, Netherlands)
Dutch newspapers 1618–1995 with article-level OCR text.
Internet Archive
Digitised books, periodicals, audio, film and software from archive.org, with full text for scanned texts.
HathiTrust
Look up digitised library volumes by OCLC, ISBN, LCCN, ISSN or HathiTrust id.
Open Library
Books, editions and authors from the Internet Archive’s Open Library, including search inside scanned texts.
Smithsonian Open Access
Objects, specimens and archives from the Smithsonian museums and research centres.
Nationalmuseum (Sweden)
Sweden’s national museum of art and design: paintings, sculpture, drawings, prints and applied art.
The Met collection
The Metropolitan Museum of Art’s 490,000+ objects, most with public-domain images.
Art Institute of Chicago
The Art Institute of Chicago collection with IIIF images.
Scholarly literature
Paper, preprint, citation and researcher-identity databases.
OpenAlex
Works, authors, institutions and citation graphs across 270M+ scholarly records.
Crossref
DOI metadata, reference lists, journals, funders and publisher members.
ORCID
Researcher profiles, works, affiliations, funding and peer-review records.
arXiv
Preprint search with metadata, category browsing and full-paper reading.
Europe PMC
Life-science literature: 40M+ abstracts, preprints and open-access full text.
OpenAIRE Graph
Open-science graph linking publications, datasets, software and projects across Europe and beyond.
DOAJ (Directory of Open Access Journals)
Peer-reviewed open-access journals and their articles, with APC and licence details.
bioRxiv & medRxiv
Biology and medicine preprints: search, recent postings by category, full text and the published journal version.
HAL (French open archive)
1M+ full texts from French research: articles, theses, conference papers and preprints.
zbMATH Open
Mathematics reviews and bibliography since 1868 with MSC classification.
Medical & clinical
Biomedical literature, trials and drug data.
PubMed & Europe PMC
Biomedical literature: search, MeSH terms, related articles, citations and lawful full text.
ClinicalTrials.gov
Search registered clinical trials, read full study records, posted results and eligibility criteria.
Clinical evidence (trials, FDA labels, adverse events)
ClinicalTrials.gov, openFDA drug labels, adverse-event reports and approvals alongside PubMed.
CDC data and WONDER
US public-health datasets (data.cdc.gov) and CDC WONDER mortality and natality queries.
NCATS Inxight Drugs
Every FDA-registered substance with its UNII, plus NCATS-curated approval status, indications, targets and pharmacokinetics.
openFDA
FDA drug and device adverse events, recalls, labels and shortages.
EMA medicines (EU authorisations)
Centrally authorised EU medicines, orphan designations, safety communications and shortages from the European Medicines Agency.
WHO Global Health Observatory
WHO health indicators for every member state: life expectancy, mortality, disease burden, health systems.
DailyMed (US drug labels)
Current FDA-submitted prescribing information for every US drug, section by section.
USDA FoodData Central
Nutrient composition of foods from the USDA reference database.
RxNorm (NLM drug vocabulary)
Normalised US drug names: ingredients, brands, clinical drugs with strength and form, and NDC codes.
Open Food Facts
Crowd-sourced database of 3M+ packaged food products: ingredients, nutrition, labels, Nutri-Score.
DrugCentral
Approved drugs worldwide: approvals by agency, indications and contraindications, mechanism targets and FAERS safety signals.
ClinGen (clinical gene and variant curation)
Expert-panel gene-disease validity, dosage sensitivity and ACMG variant classifications.
Life science
Proteins, genes, variants, compounds, structures and pathways.
TogoMCP (UniProt, ChEMBL, PubChem, PDB, Reactome, NCBI)
One service across 30+ life-science databases: proteins, genes, compounds, structures, pathways, variants and MeSH.
Open Targets Platform
Target–disease–drug associations with the evidence behind them, from EMBL-EBI.
Protein structures (PDB, AlphaFold)
Search experimental and predicted protein structures, find similar folds, track ligands and fetch annotations.
NCBI E-utilities
Gene, ClinVar, dbSNP, Taxonomy, Nucleotide, Protein, PMC and other NCBI databases.
GBIF (biodiversity occurrences)
2.5 billion species occurrence records from museums, surveys and citizen science worldwide.
iNaturalist
Citizen-science observations with photos, research-grade identifications and places.
UniProt
The universal protein knowledgebase: function, disease links, domains, locations and structures for every known protein.
Human Protein Atlas
Where every human protein is expressed: tissues, single cells, blood, brain, cancers and subcellular location.
Paleobiology Database
Fossil occurrences, taxa, collections and diversity through geological time.
Pharos (NIH druggable targets)
Target development levels, disease associations, ligands and pathways for the whole human proteome, from NIH NCATS.
gnomAD (population variant frequencies)
Allele frequencies for 800,000+ exomes and genomes, gene constraint scores and ClinVar overlap.
PRIDE Archive (proteomics datasets)
The world’s largest repository of mass-spectrometry proteomics datasets, from EMBL-EBI.
MetaboLights (metabolomics studies)
Curated repository of metabolomics experiments and their metabolites, from EMBL-EBI.
ProteomicsDB
Mass-spectrometry evidence and tissue abundance for human proteins, from TU Munich.
Chemistry & materials
Compounds, structures, bioactivity, reactions, safety data and crystal structures.
PubChem
Compound identity, properties, similarity and substructure search, GHS safety data, from 119M compounds.
ChEMBL (bioactivity)
Drug-like molecules with measured bioactivities, targets and mechanisms of action, curated by EMBL-EBI.
ChEBI (chemical ontology)
Curated dictionary of chemical entities: definitions, classes, roles and synonyms.
OPSIN (name to structure)
Turns a systematic IUPAC name into a structure by rule, also for compounds no database lists.
Crystallography Open Database
Over 500,000 open-access crystal structures: organic, inorganic, metal-organic and minerals.
Rhea (biochemical reactions)
Expert-curated, balanced biochemical reactions linked to enzymes and ChEBI compounds.
Official statistics
Statistical offices and international economic data.
Eurostat
EU official statistics: economy, demography, trade, health and NUTS regions.
OECD
OECD statistics on economy, education, health, labour and environment (SDMX).
IMF data
International Monetary Fund macroeconomic datasets.
Statistics Sweden (SCB)
Swedish official statistics: population, economy, labour market, education and environment.
Sveriges Riksbank
Policy rate, exchange rates and interbank rates from the Swedish central bank.
Kolada (Swedish municipal indicators)
6,000 key indicators for every Swedish municipality and region: schools, care, finances, environment.
Statistics Norway (SSB)
Norwegian official statistics from the StatBank.
Statistics Denmark (StatBank)
Danish official statistics from Danmarks Statistik.
World Bank
Country profiles, World Development Indicators and poverty data for 200+ economies.
ECB Data Portal
Euro-area monetary, financial and macro statistics from the European Central Bank.
Our World in Data
Thousands of cleaned, sourced charts on health, population, poverty, energy, climate, education, food and conflict.
ILOSTAT
ILO labour statistics: employment, unemployment, wages, working conditions by country.
UN Comtrade (preview)
International goods trade by reporter, partner, year and HS commodity code.
US Census Bureau
American Community Survey, decennial census and other Census datasets by geography.
NOAA climate data
Historical climate observations and normals from NOAA’s National Centers for Environmental Information.
SMHI meteorological observations
Swedish weather station observations: temperature, precipitation, wind, snow, back to the 1800s for some stations.
Open-Meteo historical weather
Daily historical weather for any coordinate since 1940 (ERA5 reanalysis), plus geocoding.
USGS Earthquake Catalog
Global earthquake catalogue (ComCat) searchable by time, magnitude and location.
OpenAQ air quality
Ground-level air-quality measurements from government and research monitors worldwide.
Knowledge bases
Structured knowledge graphs and reference corpora.
Project Gutenberg
Search and read 70,000+ public-domain books.
Getty Vocabularies (AAT, TGN, ULAN)
Controlled vocabularies for art, architecture, historical place names and artist names.
OEIS (integer sequences)
The On-Line Encyclopedia of Integer Sequences: identify a sequence from its terms.
Wikidata
Structured knowledge graph: entity search, statements and SPARQL queries.
Wikipedia
Article search, summaries, full articles and sections in any language edition.
Glottolog
Reference catalogue of the world’s languages, dialects and families.
MusicBrainz
Open music encyclopedia: artists, works, releases, recordings and relationships.
Datasets & code
Machine-learning datasets, models and code documentation.
DataCite
DOIs for research datasets, software, samples and other non-article outputs.
Zenodo
CERN’s open repository for datasets, software, papers, posters and supplementary material.
Hugging Face Hub
Search models, datasets, Spaces and papers on the Hugging Face Hub.
Stack Exchange
Q&A across Stack Overflow, Cross Validated, MathOverflow, Academia and 170+ sites.
Law & politics
Legislation, case law, parliaments and public records.
EUR-Lex (EU law and case law)
EU legislation, treaties, preparatory acts and Court of Justice case law with their amendment graph.
Riksdagen (Swedish parliament open data)
Bills, committee reports, motions, protocols, SOU reports and SFS statutes with full text.
CourtListener (US case law)
US court opinions, dockets, citations, judges and oral arguments from the Free Law Project.
US Federal Register
Federal rules, proposed rules, notices and presidential documents since 1994.
Congress.gov
US bills, laws, members, committees, votes, nominations and CRS reports.
SEC EDGAR
US company filings: 10-K, 10-Q, 8-K, insider transactions and institutional holdings.
CORDIS (EU research projects)
EU-funded projects and results from FP7, Horizon 2020 and Horizon Europe.
NSF Awards (USA)
US National Science Foundation grants by keyword, investigator or institution.
News & places
Global news coverage and geographic data.
US National Weather Service
Forecasts, alerts, observations and forecast discussions for the United States.
GDELT (global news coverage)
Search three months of world news in 65+ languages; coverage volume, tone and country breakdowns over time.
OpenStreetMap
Geocode places, reverse-geocode coordinates and query map features near a point or within an area.
From question to cited answer in three steps
- 1
Connect
Pick sources under Settings, Integrations, Data sources. One click each, no API key for most.
- 2
Ask
Write your question in chat. The assistant chooses the right database tools and runs precise queries.
- 3
Verify
Answers cite DOIs, NCT and CELEX numbers, dataset codes and archive references you can open.
Read the guide: worked examples and prompts that stay grounded
Bring your own MCP server
Any MCP server that speaks streamable HTTP on a public address can be added under Settings, Integrations, Data sources: paste the endpoint, test the connection and choose which tools the assistant may use. Institutions running their own archive or database servers can make them available to their researchers this way.
Only the search the assistant writes is sent to a source, never your files. Results are treated as retrieved material and cited with the source’s own identifiers.
Other integrations
Coming soon
Open-source servers Kahubi plans to host so they are reliable enough for research use. Missing a database?
- Open museum collectionsFederated, licence-checked search across the Met, Rijksmuseum, Smithsonian, SMK, Wellcome and more.
- PubCrawl (clinical literature & regulation)PubMed, Europe PMC, FDA and UK drug labels, ClinicalTrials.gov in thin deterministic wrappers.
- Drug pipeline (trials, approvals, patents)Pharma R&D: trials, FDA/EMA approvals, safety signals, patents and publications.
- FRED (Federal Reserve economic data)US economic time series from the St. Louis Fed.
- NASA open APIsAstronomy imagery, near-earth objects and earth observation.
- European Parliament open dataMEPs, plenary activities, votes and documents.
- UK legislationSearch statutes on legislation.gov.uk.
- Espacenet (EPO worldwide patents)140 million patent documents from 100+ countries, including all Swedish patents, with abstracts, claims, families and legal status.
Frequently asked questions
What is a data source in Kahubi?
How do I connect a source?
Does it cost extra?
Can I add my own MCP server?
What is sent to the database?
How often are new databases added?
Ask the archives, the registries and the statistics office in one place
Free to start. Connect PubMed, Eurostat or EUR-Lex in one click and get answers with references you can check.