MCP server for the Scigantic catalog of public scientific data archives. Search
MCP server for the Scigantic catalog of public scientific data archives. Search thousands of datasets and get LLM-ready schema cards without downloading anything.
active Production-safe Score 92/100 http no auth
At a glance
| Endpoint | https://api.scigantic.com/mcp |
|---|---|
| Source | https://github.com/Scigantic/scigantic-mcp |
| Transport | http |
| Tools | 16 |
| Auth | none |
| First seen | 2026-08-30 03:26:15 |
| Last checked | 2026-11-17 21:52:56 |
Observed reliability
| 7-day uptime | 100% |
|---|---|
| 24-hour uptime | 100% |
| Handshake success | 100% |
| Latency p50 / p95 | 584 / 888 ms |
| Last successful check | 2026-11-17 21:52:56 |
Measured by Arclan's validator via repeated live MCP handshakes. How this is computed →
Tools (16)
search_archives— Search the Scigantic catalog of public scientific data archives by natural-language query. Matching considers both the archive's descriptionget_archive— Get full metadata for one archive by id, including its schema card (structure summary) when one exists.get_schema_card— Get the compact schema card for an archive: file format, columns, sample rows/headers, sidecar docs (READMEs/data dictionaries) and a copy-pget_data_access— Get how to load a dataset in YOUR OWN environment: storage location plus copy-paste code snippets (from the dataset's schema card, or generalist_archive_files— List a sample of the files/objects in an archive's storage (the cached file tree).get_sample_notebook— Get the pre-executed starter notebook for an archive — a worked example of loading and exploring the data. Returns a cell-by-cell summary pllookup_paper— Look up a research paper on arXiv, by bare arXiv id (e.g. "1706.03762") or by keywords/title, and return its metadata plus any Scigantic arclist_compute_tiers— List the compute tiers available for launching a Scigantic notebook (CPU/GPU options and hourly cost).search— Search the Scigantic catalog of public scientific datasets. Returns matching datasets as {results: [{id, title, url}]}; pass an id to fetchfetch— Fetch one Scigantic dataset by id (from search): its description, storage location, source link, and schema card (format, columns, sample rosurechembl_compound— Look up a compound in SureChEMBL, EMBL-EBI's database of chemistry extracted from patents, by any identifier, and report its structure, propsurechembl_patents_for_compound— List the patents in which a compound was found (SureChEMBL). Accepts the same identifier forms as surechembl_compound. Aspirin is in ~700,00surechembl_patent— A patent document from SureChEMBL: title, dates, applicants, inventors, assignees, family, priority claims, number of compounds named in thesurechembl_patent_chemistry— The compounds SureChEMBL's text-mining finds named in a patent's text: SCHEMBL id, name, SMILES, InChIKey, formula, weight. Structures thatsurechembl_search_patents— Full-text patent search over SureChEMBL with Solr syntax. Plain terms search all text; field prefixes narrow: ttl (title), ab (abstract), clsurechembl_structure_search— Search SureChEMBL's 31 million patent compounds by chemical structure.
Validation history
| Checked | Reachable | Handshake | Latency | Score | State |
|---|---|---|---|---|---|
| 2026-11-17 21:52:56 | ✓ | ✓ | 485 ms | 90 | active |
| 2026-11-17 21:37:40 | ✓ | ✓ | 429 ms | 90 | active |
| 2026-11-17 21:22:25 | ✓ | ✓ | 760 ms | 90 | active |
| 2026-11-17 21:07:11 | ✓ | ✓ | 553 ms | 90 | active |
| 2026-11-17 20:52:06 | ✓ | ✓ | 509 ms | 90 | active |
| 2026-11-17 20:37:04 | ✓ | ✓ | 548 ms | 90 | active |
| 2026-11-17 20:22:00 | ✓ | ✓ | 415 ms | 90 | active |
| 2026-11-17 20:06:56 | ✓ | ✓ | 469 ms | 90 | active |
| 2026-11-17 19:51:11 | ✓ | ✓ | 569 ms | 90 | active |
| 2026-11-17 19:36:03 | ✓ | ✓ | 429 ms | 90 | active |
| 2026-11-17 19:20:52 | ✓ | ✓ | 625 ms | 90 | active |
| 2026-11-17 19:05:39 | ✓ | ✓ | 738 ms | 90 | active |
| 2026-11-17 18:50:25 | ✓ | ✓ | 609 ms | 90 | active |
| 2026-11-17 18:35:14 | ✓ | ✓ | 411 ms | 90 | active |
| 2026-11-17 18:20:08 | ✓ | ✓ | 608 ms | 90 | active |
Query this programmatically
Agents can pull this record live over the MCP protocol or REST:
get_server("https://api.scigantic.com/mcp") # via the Arclan MCP endpoint https://arclan.ai/mcp
GET https://arclan.ai/api/registry/api-scigantic-com-mcp # JSON