Server definition
- Hash
- sha256:d0a9452186f690d99abbef1f61cae78b9a4745b02bda755805b880ad88906064
- What it is
- What a remote MCP server returned when asked what it offers: 16 tools
The blob, as servednamed by its sha256
{
"instructions": "Scigantic exposes a catalog of public scientific data archives. Use search_archives to find datasets, get_schema_card to understand a dataset's structure, list_archive_files to inspect contents, and get_sample_notebook for a worked example. lookup_paper goes from a paper to its underlying datasets. search and fetch are the same catalog in the shape ChatGPT deep research expects. The surechembl_* tools cover patent chemistry from SureChEMBL (EMBL-EBI): look a compound up by any identifier, list the patents that mention it, read a patent's bibliography and text, list the compounds named in its text, search US, EP, WO, JP and CN patents by Solr query, and run similarity or substructure searches over 31 million compounds. If you can read files on the user's machine and they ask about data on it, \"locally\", or in a mounted folder: first read ~/scigantic-mounts/mounts.json (also README.md there). The Scigantic Datasets extension for VS Code and Cursor mounts archives there as read-only folders, each listed with its archive id, local path and rclone `commands` to list a folder, read a file and download a file. Use those commands (replace {path}); they work from any app. Reading the local path can fail on macOS with \"Operation not permitted\" when the app lacks Network Volumes permission; then use the commands, not another source. Never run a recursive find, grep -r, du or ls -R in or above ~/scigantic-mounts: each mount is a remote bucket and a crawl can take hours.",
"tools": [
{
"description": "Fetch one Scigantic dataset by id (from search): its description, storage location, source link, and schema card (format, columns, sample rows, caveats, and how to load it).",
"inputSchema": {
"properties": {
"id": {
"description": "Dataset id from search.",
"type": "string"
}
},
"required": [
"id"
],
"type": "object"
},
"name": "fetch",
"outputSchema": null
},
{
"description": "Get full metadata for one archive by id, including its schema card (structure summary) when one exists.",
"inputSchema": {
"properties": {
"id": {
"description": "Archive id from search_archives.",
"type": "string"
}
},
"required": [
"id"
],
"type": "object"
},
"name": "get_archive",
"outputSchema": null
},
{
"description": "Get how to load a dataset in YOUR OWN environment: storage location plus copy-paste code snippets (from the dataset's schema card, or generated as a fallback). Use this after finding a dataset when you want to run analysis where you are, rather than in a hosted notebook.",
"inputSchema": {
"properties": {
"id": {
"description": "Archive id from search_archives.",
"type": "string"
},
"language": {
"description": "Optional snippet-language filter, e.g. \"datasets\", \"s3fs\", \"gcsfs\".",
"type": "string"
}
},
"required": [
"id"
],
"type": "object"
},
"name": "get_data_access",
"outputSchema": null
},
{
"description": "Get the pre-executed starter notebook for an archive — a worked example of loading and exploring the data. Returns a cell-by-cell summary plus each cell's source (outputs are omitted to keep the payload small).",
"inputSchema": {
"properties": {
"id": {
"description": "Archive id from search_archives.",
"type": "string"
}
},
"required": [
"id"
],
"type": "object"
},
"name": "get_sample_notebook",
"outputSchema": null
},
{
"description": "Get the compact schema card for an archive: file format, columns, sample rows/headers, sidecar docs (READMEs/data dictionaries) and a copy-paste starter cell. This is the fastest way to understand a dataset's structure without mounting it.",
"inputSchema": {
"properties": {
"id": {
"description": "Archive id from search_archives.",
"type": "string"
}
},
"required": [
"id"
],
"type": "object"
},
"name": "get_schema_card",
"outputSchema": null
},
{
"description": "List a sample of the files/objects in an archive's storage (the cached file tree).",
"inputSchema": {
"properties": {
"id": {
"description": "Archive id from search_archives.",
"type": "string"
},
"limit": {
"description": "Max entries to return (default 50, max 200).",
"type": "number"
}
},
"required": [
"id"
],
"type": "object"
},
"name": "list_archive_files",
"outputSchema": null
},
{
"description": "List the compute tiers available for launching a Scigantic notebook (CPU/GPU options and hourly cost).",
"inputSchema": {
"properties": {},
"type": "object"
},
"name": "list_compute_tiers",
"outputSchema": null
},
{
"description": "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 archives linked to or suggested by it. Useful for going from a paper an agent is reading to the underlying datasets. Lookup is arXiv-backed: DOIs, \"arXiv:\"-prefixed ids, and papers that are not on arXiv do not resolve.",
"inputSchema": {
"properties": {
"query": {
"description": "Bare arXiv id (e.g. \"1706.03762\"), or keywords/title to search arXiv. Not a DOI.",
"type": "string"
}
},
"required": [
"query"
],
"type": "object"
},
"name": "lookup_paper",
"outputSchema": null
},
{
"description": "Search the Scigantic catalog of public scientific datasets. Returns matching datasets as {results: [{id, title, url}]}; pass an id to fetch for the full description and schema card.",
"inputSchema": {
"properties": {
"query": {
"description": "Natural-language search, e.g. \"single-cell RNA-seq of human cortex\".",
"type": "string"
}
},
"required": [
"query"
],
"type": "object"
},
"name": "search",
"outputSchema": null
},
{
"description": "Search the Scigantic catalog of public scientific data archives by natural-language query. Matching considers both the archive's description AND a sample of its actual object/file names, so a distinctive filename or path pattern can surface a match even when the prose description never mentions it. Returns ranked matches with id, title, category, a short summary, and two payload-derived trust signals: probeStatus (\"empty\" means the archive's storage was probed and found to have no accessible objects despite being tagged public — likely credentialed, don't spend a turn on it) and objectCountEstimate (a real count/estimate from that probe, not the description's prose). Follow up with get_schema_card to understand a match's structure before doing any analysis.",
"inputSchema": {
"properties": {
"category": {
"description": "Optional category filter, e.g. \"Genomics & Bioinformatics\". Comma-separate for several.",
"type": "string"
},
"limit": {
"description": "Max results (default 10, max 50).",
"type": "number"
},
"query": {
"description": "Natural-language search, e.g. \"single-cell RNA-seq of human cortex\".",
"type": "string"
}
},
"required": [
"query"
],
"type": "object"
},
"name": "search_archives",
"outputSchema": null
},
{
"description": "Look up a compound in SureChEMBL, EMBL-EBI's database of chemistry extracted from patents, by any identifier, and report its structure, properties, cross-references (ChEMBL, PubChem, DrugBank, ChEBI, PDB) and how many patents mention it.",
"inputSchema": {
"properties": {
"identifier": {
"description": "A SureChEMBL id (\"SCHEMBL1353\" or \"1353\"), a ChEMBL id (\"CHEMBL25\"), a PubChem CID as \"pubchem:2244\", a DrugBank id as \"drugbank:DB00945\", a standard InChIKey, a SMILES, or a chemical name (\"aspirin\"; resolved through PubChem to a structure, since SureChEMBL has no name lookup).",
"type": "string"
}
},
"required": [
"identifier"
],
"type": "object"
},
"name": "surechembl_compound",
"outputSchema": null
},
{
"description": "A patent document from SureChEMBL: title, dates, applicants, inventors, assignees, family, priority claims, number of compounds named in the text, abstract, and (optionally) the claims and description text. SureChEMBL no longer returns CPC codes, citations or legal events with a document.",
"inputSchema": {
"properties": {
"doc_id": {
"description": "Publication number with kind code, e.g. \"US-10000000-B2\", \"WO2016144528A1\", \"EP-3268771-B1\".",
"type": "string"
},
"include_text": {
"description": "Also return the claims and description (can be long). Default false.",
"type": "boolean"
}
},
"required": [
"doc_id"
],
"type": "object"
},
"name": "surechembl_patent",
"outputSchema": null
},
{
"description": "The compounds SureChEMBL's text-mining finds named in a patent's text: SCHEMBL id, name, SMILES, InChIKey, formula, weight. Structures that appear only in images or MOL attachments are not included.",
"inputSchema": {
"properties": {
"doc_id": {
"description": "Publication number with kind code, e.g. \"US-5399578-A\".",
"type": "string"
},
"limit": {
"description": "Max compounds to list (default 50, max 500).",
"type": "number"
}
},
"required": [
"doc_id"
],
"type": "object"
},
"name": "surechembl_patent_chemistry",
"outputSchema": null
},
{
"description": "List the patents in which a compound was found (SureChEMBL). Accepts the same identifier forms as surechembl_compound. Aspirin is in ~700,000 documents, so read the total and narrow with surechembl_search_patents when it is large.",
"inputSchema": {
"properties": {
"identifier": {
"description": "A SureChEMBL id (\"SCHEMBL1353\" or \"1353\"), a ChEMBL id (\"CHEMBL25\"), a PubChem CID as \"pubchem:2244\", a DrugBank id as \"drugbank:DB00945\", a standard InChIKey, a SMILES, or a chemical name (\"aspirin\"; resolved through PubChem to a structure, since SureChEMBL has no name lookup).",
"type": "string"
},
"limit": {
"description": "Max patents to list (default 20, max 200).",
"type": "number"
}
},
"required": [
"identifier"
],
"type": "object"
},
"name": "surechembl_patents_for_compound",
"outputSchema": null
},
{
"description": "Full-text patent search over SureChEMBL with Solr syntax. Plain terms search all text; field prefixes narrow: ttl (title), ab (abstract), clm (claims), desc, asg (assignee), inv (inventor), pdyear, cpc, ic (IPCR), fam (family id). Quote publication numbers: pn:\"US-10000000-B2\". Combine with AND/OR/NOT. Only US, EP, WO, JP and CN publications are searchable.",
"inputSchema": {
"properties": {
"limit": {
"description": "Max patents to list (default 20, max 200).",
"type": "number"
},
"query": {
"description": "e.g. 'ttl:kinase AND asg:novartis AND pdyear:2024'.",
"type": "string"
}
},
"required": [
"query"
],
"type": "object"
},
"name": "surechembl_search_patents",
"outputSchema": null
},
{
"description": "Search SureChEMBL's 31 million patent compounds by chemical structure.",
"inputSchema": {
"properties": {
"limit": {
"description": "Max hits (default 20, max 500).",
"type": "number"
},
"mode": {
"description": "\"similarity\" (Tanimoto at or above 0.8, default), \"substructure\" (at least 5 atoms; the server caps results at 10,000), \"identical\" (all features must match), or \"connectivity\" (same skeleton, any stereo/isotopes).",
"enum": [
"substructure",
"similarity",
"identical",
"connectivity"
],
"type": "string"
},
"structure": {
"description": "A SMILES.",
"type": "string"
}
},
"required": [
"structure"
],
"type": "object"
},
"name": "surechembl_structure_search",
"outputSchema": null
}
]
}Verify it yourself
curl -s https://api.teppi.xyz/v1/evidence/sha256:d0a9452186f690d99abbef1f61cae78b9a4745b02bda755805b880ad88906064 | sha256sum