com.scigantic/mcpv0.3.1 Domain verified
Search public scientific datasets and read schema cards that describe their files, columns and rows
Maintain this server? Claim it
Try it
Call this server's tools from your browser. Nothing to install.
https://api.scigantic.com/mcp
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
fetch Read-only
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).
Dataset id from search.
Install
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http mcp https://api.scigantic.com/mcp
Tools (16)
fetchFetch 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).
read-only
fetch
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).
| Argument | Type | Description |
|---|---|---|
| id* | string | Dataset id from search. |
Input schema (JSON)
{
"type": "object",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"description": "Dataset id from search."
}
}
}get_archiveGet full metadata for one archive by id, including its schema card (structure summary) when one exists.
read-only
get_archive
Get full metadata for one archive by id, including its schema card (structure summary) when one exists.
| Argument | Type | Description |
|---|---|---|
| id* | string | Archive id from search_archives. |
Input schema (JSON)
{
"type": "object",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"description": "Archive id from search_archives."
}
}
}get_data_accessGet 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.
read-only
get_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 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.
| Argument | Type | Description |
|---|---|---|
| id* | string | Archive id from search_archives. |
| language | string | Optional snippet-language filter, e.g. "datasets", "s3fs", "gcsfs". |
Input schema (JSON)
{
"type": "object",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"description": "Archive id from search_archives."
},
"language": {
"type": "string",
"description": "Optional snippet-language filter, e.g. \"datasets\", \"s3fs\", \"gcsfs\"."
}
}
}get_sample_notebookGet 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).
read-only
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 plus each cell's source (outputs are omitted to keep the payload small).
| Argument | Type | Description |
|---|---|---|
| id* | string | Archive id from search_archives. |
Input schema (JSON)
{
"type": "object",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"description": "Archive id from search_archives."
}
}
}get_schema_cardGet 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.
read-only
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-paste starter cell. This is the fastest way to understand a dataset's structure without mounting it.
| Argument | Type | Description |
|---|---|---|
| id* | string | Archive id from search_archives. |
Input schema (JSON)
{
"type": "object",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"description": "Archive id from search_archives."
}
}
}list_archive_filesList a sample of the files/objects in an archive's storage (the cached file tree).
read-only
list_archive_files
List a sample of the files/objects in an archive's storage (the cached file tree).
| Argument | Type | Description |
|---|---|---|
| id* | string | Archive id from search_archives. |
| limit | number | Max entries to return (default 50, max 200). |
Input schema (JSON)
{
"type": "object",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"description": "Archive id from search_archives."
},
"limit": {
"type": "number",
"description": "Max entries to return (default 50, max 200)."
}
}
}list_compute_tiersList the compute tiers available for launching a Scigantic notebook (CPU/GPU options and hourly cost).
read-only
list_compute_tiers
List the compute tiers available for launching a Scigantic notebook (CPU/GPU options and hourly cost).
No arguments.
Input schema (JSON)
{
"type": "object",
"properties": {}
}lookup_paperLook 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.
read-only
lookup_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 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.
| Argument | Type | Description |
|---|---|---|
| query* | string | Bare arXiv id (e.g. "1706.03762"), or keywords/title to search arXiv. Not a DOI. |
Input schema (JSON)
{
"type": "object",
"required": [
"query"
],
"properties": {
"query": {
"type": "string",
"description": "Bare arXiv id (e.g. \"1706.03762\"), or keywords/title to search arXiv. Not a DOI."
}
}
}searchSearch 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.
read-only
search
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.
| Argument | Type | Description |
|---|---|---|
| query* | string | Natural-language search, e.g. "single-cell RNA-seq of human cortex". |
Input schema (JSON)
{
"type": "object",
"required": [
"query"
],
"properties": {
"query": {
"type": "string",
"description": "Natural-language search, e.g. \"single-cell RNA-seq of human cortex\"."
}
}
}search_archivesSearch 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.
read-only
search_archives
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.
| Argument | Type | Description |
|---|---|---|
| limit | number | Max results (default 10, max 50). |
| query* | string | Natural-language search, e.g. "single-cell RNA-seq of human cortex". |
| category | string | Optional category filter, e.g. "Genomics & Bioinformatics". Comma-separate for several. |
Input schema (JSON)
{
"type": "object",
"required": [
"query"
],
"properties": {
"limit": {
"type": "number",
"description": "Max results (default 10, max 50)."
},
"query": {
"type": "string",
"description": "Natural-language search, e.g. \"single-cell RNA-seq of human cortex\"."
},
"category": {
"type": "string",
"description": "Optional category filter, e.g. \"Genomics & Bioinformatics\". Comma-separate for several."
}
}
}surechembl_compoundLook 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.
read-only
surechembl_compound
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.
| Argument | Type | Description |
|---|---|---|
| identifier* | string | 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"). |
Input schema (JSON)
{
"type": "object",
"required": [
"identifier"
],
"properties": {
"identifier": {
"type": "string",
"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\")."
}
}
}surechembl_patentA patent document from SureChEMBL: title, dates, applicants, inventors, assignees, CPC codes, family, number of extracted compounds, abstract, and (optionally) the claims and description text.
read-only
surechembl_patent
A patent document from SureChEMBL: title, dates, applicants, inventors, assignees, CPC codes, family, number of extracted compounds, abstract, and (optionally) the claims and description text.
| Argument | Type | Description |
|---|---|---|
| doc_id* | string | Publication number with kind code, e.g. "US-10000000-B2", "WO2016144528A1", "EP-3268771-B1". |
| include_text | boolean | Also return the claims and description (can be long). Default false. |
Input schema (JSON)
{
"type": "object",
"required": [
"doc_id"
],
"properties": {
"doc_id": {
"type": "string",
"description": "Publication number with kind code, e.g. \"US-10000000-B2\", \"WO2016144528A1\", \"EP-3268771-B1\"."
},
"include_text": {
"type": "boolean",
"description": "Also return the claims and description (can be long). Default false."
}
}
}surechembl_patent_chemistryEvery compound SureChEMBL extracted from a patent (from its text, images and MOL attachments): SCHEMBL id, name, SMILES, InChIKey, formula, weight.
read-only
surechembl_patent_chemistry
Every compound SureChEMBL extracted from a patent (from its text, images and MOL attachments): SCHEMBL id, name, SMILES, InChIKey, formula, weight.
| Argument | Type | Description |
|---|---|---|
| limit | number | Max compounds to list (default 50, max 500). |
| doc_id* | string | Publication number with kind code, e.g. "US-5399578-A". |
Input schema (JSON)
{
"type": "object",
"required": [
"doc_id"
],
"properties": {
"limit": {
"type": "number",
"description": "Max compounds to list (default 50, max 500)."
},
"doc_id": {
"type": "string",
"description": "Publication number with kind code, e.g. \"US-5399578-A\"."
}
}
}surechembl_patents_for_compoundList 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.
read-only
surechembl_patents_for_compound
List the patents in which a compound was found (SureChEMBL). Accepts the same identifier forms as surechembl_compound. Aspirin is in ~700,000 documents, so read the total and narrow with surechembl_search_patents when it is large.
| Argument | Type | Description |
|---|---|---|
| limit | number | Max patents to list (default 20, max 200). |
| identifier* | string | 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"). |
Input schema (JSON)
{
"type": "object",
"required": [
"identifier"
],
"properties": {
"limit": {
"type": "number",
"description": "Max patents to list (default 20, max 200)."
},
"identifier": {
"type": "string",
"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\")."
}
}
}surechembl_search_patentsFull-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.
read-only
surechembl_search_patents
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.
| Argument | Type | Description |
|---|---|---|
| limit | number | Max patents to list (default 20, max 200). |
| query* | string | e.g. 'ttl:kinase AND asg:novartis AND pdyear:2024'. |
Input schema (JSON)
{
"type": "object",
"required": [
"query"
],
"properties": {
"limit": {
"type": "number",
"description": "Max patents to list (default 20, max 200)."
},
"query": {
"type": "string",
"description": "e.g. 'ttl:kinase AND asg:novartis AND pdyear:2024'."
}
}
}surechembl_structure_searchSearch SureChEMBL's 31 million patent compounds by chemical structure.
read-only
surechembl_structure_search
Search SureChEMBL's 31 million patent compounds by chemical structure.
| Argument | Type | Description |
|---|---|---|
| mode | string | "similarity" (Tanimoto, 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). |
| limit | number | Max hits (default 20, max 500). |
| structure* | string | A SMILES. |
Input schema (JSON)
{
"type": "object",
"required": [
"structure"
],
"properties": {
"mode": {
"enum": [
"substructure",
"similarity",
"identical",
"connectivity"
],
"type": "string",
"description": "\"similarity\" (Tanimoto, 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)."
},
"limit": {
"type": "number",
"description": "Max hits (default 20, max 500)."
},
"structure": {
"type": "string",
"description": "A SMILES."
}
}
}Security checkA100/100
We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 10, 2026.
- Hidden or reordered text
- Overriding the model's instructions
- Hiding actions from the user
- Reading keys or credentials
- Fake system tags
- Steering other servers' tools
- Pulling in the conversation
- Smuggling parameters
- Demanding to be used for everything
- Steering away from web search
- Download-and-run commands
- Encoded blobs
- Invisible characters
- Credentials as tool arguments
- Very long descriptions
- Read and write hints