scigantic-mcp

A Model Context Protocol server that exposes the Scigantic catalog of public scientific data archives to any MCP client.

It is built to drop into Kiro for Life Sciences alongside its domain database servers. Where each Kiro server wraps one domain's APIs (genomics, proteomics, structural, …), Scigantic is the cross-domain launchpad: about 6,900 curated public archives spanning every domain, each with an LLM-ready schema card (file format, columns, sample rows/headers, inlined READMEs/data dictionaries, and a copy-paste starter cell) so an agent can understand a dataset's structure before downloading anything.

It is discovery-only and zero-config — every tool calls public, read-only Scigantic endpoints, so there is no API key to set up.

Since 0.3.0 it also carries six surechembl_* tools for patent chemistry, backed by SureChEMBL (EMBL-EBI, 31M compounds extracted from 45M patents) through the scigantic-surechembl library: look a compound up by any identifier, list the patents that mention it, read a patent, list the compounds named in it, search patents with Solr syntax, and run structure searches. Also public, read-only, no key.

SureChEMBL replaced its REST API in November 2026. Since 0.3.2 these tools run on scigantic-surechembl 0.4, the port to the new API. Three things the new API no longer offers show up in the output: a patent's CPC codes, citations and legal events are not returned; surechembl_patent_chemistry lists the compounds named in a patent's text, not those that appear only in images or attachments; and full-text search and patent families cover US, EP, WO, JP and CN publications only. A chemical name is now resolved through PubChem, since SureChEMBL has no name lookup any more.

Requires Python 3.10+ and MCP SDK 2.x.

Prefer the hosted server if your client speaks HTTP. Scigantic also runs a remote MCP server at https://api.scigantic.com/mcp (no auth, nothing to install, and it carries five extra tools: search, fetch, get_sample_notebook, lookup_paper and list_compute_tiers): add https://api.scigantic.com/mcp as a streamable HTTP server in your client (Cursor, VS Code, Windsurf and others), or run claude mcp add --transport http scigantic https://api.scigantic.com/mcp. This package exists for clients that launch stdio servers, such as Kiro.

Tools

Tool	What it does
`search_archives(query, category?, limit?)`	Natural-language search across the whole catalog.
`get_archive(id)`	Full metadata for one archive.
`get_schema_card(id)`	The compact schema card — the fastest way to learn a dataset's structure.
`get_data_access(id, language?)`	How to load the dataset in your own environment: storage location + copy-paste code snippets.
`list_archive_files(id, limit?)`	A sample of the files/objects in the archive.

Patent chemistry (SureChEMBL)

Tool	What it does
`surechembl_compound(identifier)`	A compound by SureChEMBL id, ChEMBL id, `pubchem:CID`, `drugbank:ID`, InChIKey, SMILES or name: structure, properties, cross-references, patent count.
`surechembl_patents_for_compound(identifier, limit?)`	The patents in which the compound was found, with the total.
`surechembl_patent(doc_id, include_text?)`	A patent's bibliography, abstract, family, priority claims, count of compounds named in the text, and optionally its claims and description.
`surechembl_patent_chemistry(doc_id, limit?)`	The compounds SureChEMBL's text-mining finds named in the patent.
`surechembl_search_patents(query, limit?)`	Full-text patent search with Solr field syntax (`ttl:`, `asg:`, `pdyear:`, `cpc:`, ...) over US, EP, WO, JP and CN publications.
`surechembl_structure_search(structure, mode?, limit?)`	Similarity, substructure, identical or connectivity search over 31M compounds.

Identifiers are preserved verbatim in the output (SureChEMBL's attribution terms ask that SCHEMBL ids and publication numbers be kept), and each result links to surechembl.org. SureChEMBL data is CC BY 4.0.

Prompts (guided workflows)

These surface as slash commands in Claude Code (/mcp__scigantic__<name>):

Prompt	What it does
`explore_dataset(topic)`	Search → inspect schema cards → recommend the best dataset → offer load code.
`start_analysis(archive_id, goal?)`	Pull schema card + data-access snippet for an archive and outline an analysis plan.
`patent_landscape(compound)`	Resolve a compound, count and list its patents, summarize assignees, years and CPC areas, read the key documents.

Install & register in Kiro

Add an entry under mcpServers in ~/.kiro/settings/mcp.json.

Option A — uvx (zero-install, recommended):

{
  "mcpServers": {
    "scigantic": {
      "command": "uvx",
      "args": ["scigantic-mcp"]
    }
  }
}

Option B — install into a venv (matches the Kiro servers' own mcp.json form):

python3 -m venv .venv && . .venv/bin/activate
pip install scigantic-mcp                 # or: pip install /path/to/scigantic-mcp

{
  "mcpServers": {
    "scigantic": {
      "command": "/path/to/.venv/bin/scigantic-mcp",
      "env": {
        "SCIGANTIC_API_URL": "https://api.scigantic.com"
      }
    }
  }
}

Works the same in Claude Desktop / Claude Code (claude mcp add scigantic -- uvx scigantic-mcp) or any MCP client that launches stdio servers.

Configuration

Env var	Default	Purpose
`SCIGANTIC_API_URL`	`https://api.scigantic.com`	API base (set to `https://staging-api.scigantic.com` for staging).
`SCIGANTIC_API_ORIGIN`	`https://scigantic.com`	Origin header → selects the public (default) catalog tenant.

Stability

This package is a thin client over the public Scigantic REST API. That API is not versioned and may change without notice — if a response shape moves, a pinned older release of this package can break. Pin a version you have tested, and open an issue if a tool starts returning something unexpected.

The MCP tool names and their arguments are treated as the stable surface, and will not change without a minor version bump.

Develop & test

The tool/client layer has no mcp dependency, so those tests run on any Python with httpx and need no network (mocked transport):

python3 tests/test_tools.py     # or: pytest

tests/test_server_import.py covers the wiring layer — that the server module imports, and that the registered tools and prompts are the expected set. It needs the mcp SDK installed (Python ≥ 3.10) and is skipped otherwise:

pip install -e '.[test]' && pytest

Keep it that way: the tool tests skip server.py on purpose, so an SDK breaking change is invisible to them. All 12 passed while the server could not import at all under SDK 2.x, which is what test_server_import.py now guards against.

Roadmap

Richer discovery for agents — structured tool outputs and MCP resources (attach an archive + its schema card as durable context).
Upstream inclusion as life-sciences-scigantic in aws-samples/sample-kiro-power-life-sciences.
Hosted compute is intentionally not exposed here. Scigantic's notebooks are interactive (a JupyterLab URL a human opens); handing an external agent that URL is a dead end. The agent-to-agent path is get_data_access — the caller runs the analysis in its own environment. Letting Scigantic execute code for an agent (run against an ephemeral kernel with the dataset mounted, return outputs) is a separate capability the platform would need to build first.

License

MIT-0.

mcp

Documentation