# Scigantic (remote · api.scigantic.com)

Search public scientific datasets and read schema cards that describe their files, columns and rows

- Trust score: 78/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `api.scigantic.com`: 78/100 (this document), [markdown](https://verifymcp.io/servers/com-scigantic-mcp/api.md), [page](https://verifymcp.io/servers/com-scigantic-mcp/api)
- pypi · `scigantic-mcp`: 74/100, [markdown](https://verifymcp.io/servers/com-scigantic-mcp/scigantic-mcp.md), [page](https://verifymcp.io/servers/com-scigantic-mcp/scigantic-mcp)

## Channel facts

- Endpoint: `https://api.scigantic.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.3.2`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Endpoint Security**: 74/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 82/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2167 tokens (~135/item across 16 items; 16 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 37/100
  - Stability observed for 11 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 16 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 17 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Scigantic MCP server?

Scigantic is a hosted endpoint at https://api.scigantic.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http com-scigantic-mcp 'https://api.scigantic.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-scigantic-mcp": {
      "url": "https://api.scigantic.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-scigantic-mcp": {
      "type": "http",
      "url": "https://api.scigantic.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-scigantic-mcp]
url = "https://api.scigantic.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-scigantic-mcp": {
      "type": "remote",
      "url": "https://api.scigantic.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-scigantic-mcp --url 'https://api.scigantic.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-scigantic-mcp:
    url: "https://api.scigantic.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-scigantic-mcp": {
      "Transport": "http",
      "Url": "https://api.scigantic.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-scigantic-mcp -t streamable-http -u 'https://api.scigantic.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-scigantic-mcp": {
      "type": "http",
      "url": "https://api.scigantic.com/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-21 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-20 (score 77, 0)

- [security] Tool “lookup_paper” rewrote its description, which is the text the model reads

### 2026-11-19 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-18 (score 76, 0)

- [security] Tool “lookup_paper” rewrote its description, which is the text the model reads

### 2026-11-17 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-16 (score 75, 0)

- [cosmetic] Tool “search” changed its title: Search datasets
- [cosmetic] Tool “search_archives” changed its title: Search datasets
- [cosmetic] Tool “surechembl_compound” changed its title: Look up a patent compound
- [cosmetic] Tool “surechembl_patent” changed its title: Get a patent
- [cosmetic] Tool “surechembl_patent_chemistry” changed its title: Compounds named in a patent
- [cosmetic] Tool “surechembl_patents_for_compound” changed its title: Patents mentioning a compound
- [cosmetic] Tool “surechembl_structure_search” changed its title: Search patent compounds by structure
- [cosmetic] Tool “surechembl_search_patents” changed its title: Search patents
- [cosmetic] Tool “fetch” changed its title: Fetch a dataset
- [cosmetic] Tool “get_archive” changed its title: Get dataset details
- [cosmetic] Tool “get_data_access” changed its title: Get loading code for a dataset
- [cosmetic] Tool “get_sample_notebook” changed its title: Get starter notebook
- [cosmetic] Tool “get_schema_card” changed its title: Get dataset schema card
- [cosmetic] Tool “list_archive_files” changed its title: List dataset files
- [cosmetic] Tool “list_compute_tiers” changed its title: List notebook compute tiers
- [cosmetic] Tool “lookup_paper” changed its title: Look up an arXiv paper

### 2026-11-15 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-12 (score 74, +1)

- [security] The server rewrote its instructions, which are the text every model session reads

## MCP tools (16)

### `search_archives` (~223 tokens)

Search datasets

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.

Input parameters:

- `category` (string): Optional category filter, e.g. "Genomics & Bioinformatics". Comma-separate for several.
- `limit` (number): Max results (default 10, max 50).
- `query` (string, required): Natural-language search, e.g. "single-cell RNA-seq of human cortex".

### `get_archive` (~42 tokens)

Get dataset details

Get full metadata for one archive by id, including its schema card (structure summary) when one exists.

Input parameters:

- `id` (string, required): Archive id from search_archives.

### `get_schema_card` (~74 tokens)

Get dataset 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.

Input parameters:

- `id` (string, required): Archive id from search_archives.

### `get_data_access` (~105 tokens)

Get loading code for a dataset

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.

Input parameters:

- `id` (string, required): Archive id from search_archives.
- `language` (string): Optional snippet-language filter, e.g. "datasets", "s3fs", "gcsfs".

### `list_archive_files` (~60 tokens)

List dataset files

List a sample of the files/objects in an archive's storage (the cached file tree).

Input parameters:

- `id` (string, required): Archive id from search_archives.
- `limit` (number): Max entries to return (default 50, max 200).

### `get_sample_notebook` (~66 tokens)

Get starter 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).

Input parameters:

- `id` (string, required): Archive id from search_archives.

### `lookup_paper` (~208 tokens)

Look up an arXiv 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 two separate lists: `paperLinks`, the datasets named in the paper's own text (each with the matched catalog archive, if any, how it was matched, and a one-sentence summary of how the paper uses it, written by the extraction model and not a quote), and `suggestedArchives`, catalog archives found by a keyword search on the paper that the paper itself does not mention. Only `paperLinks` are evidence that the paper used a dataset. Lookup is arXiv-backed: DOIs, "arXiv:"-prefixed ids, and papers that are not on arXiv do not resolve.

Input parameters:

- `query` (string, required): Bare arXiv id (e.g. "1706.03762"), or keywords/title to search arXiv. Not a DOI.

### `list_compute_tiers` (~31 tokens)

List notebook compute tiers

List the compute tiers available for launching a Scigantic notebook (CPU/GPU options and hourly cost).

### `search` (~69 tokens)

Search datasets

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.

Input parameters:

- `query` (string, required): Natural-language search, e.g. "single-cell RNA-seq of human cortex".

### `fetch` (~59 tokens)

Fetch a dataset

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).

Input parameters:

- `id` (string, required): Dataset id from search.

### `surechembl_compound` (~171 tokens)

Look up a patent 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.

Input parameters:

- `identifier` (string, required): 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_patents_for_compound` (~187 tokens)

Patents mentioning a 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.

Input parameters:

- `identifier` (string, required): 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"…
- `limit` (number): Max patents to list (default 20, max 200).

### `surechembl_patent` (~141 tokens)

Get a patent

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.

Input parameters:

- `doc_id` (string, required): 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.

### `surechembl_patent_chemistry` (~108 tokens)

Compounds named in a patent

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.

Input parameters:

- `doc_id` (string, required): Publication number with kind code, e.g. "US-5399578-A".
- `limit` (number): Max compounds to list (default 50, max 500).

### `surechembl_search_patents` (~161 tokens)

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. Only US, EP, WO, JP and CN publications are searchable.

Input parameters:

- `limit` (number): Max patents to list (default 20, max 200).
- `query` (string, required): e.g. 'ttl:kinase AND asg:novartis AND pdyear:2024'.

### `surechembl_structure_search` (~123 tokens)

Search patent compounds by structure

Search SureChEMBL's 31 million patent compounds by chemical structure.

Input parameters:

- `limit` (number): Max hits (default 20, max 500).
- `mode` (string): "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 st…
- `structure` (string, required): A SMILES.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-scigantic-mcp/api#diagnostics

## Score history

- 2026-11-21: 78
- 2026-11-20: 77
- 2026-11-19: 77
- 2026-11-18: 76
- 2026-11-17: 76
- 2026-11-16: 75
- 2026-11-15: 75
- 2026-11-14: 74
- 2026-11-13: 74
- 2026-11-12: 74
- 2026-11-11: 73
- 2026-11-10: 73

## Common questions

### What is the Scigantic MCP server?

Scigantic is an MCP server listed in the public MCP registry as com.scigantic/mcp. Search public scientific datasets and read schema cards that describe their files, columns and rows. This page covers its hosted endpoint (https://api.scigantic.com/mcp).

### Is the Scigantic MCP server safe to use?

Scigantic scores 78 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Scigantic MCP server expose?

Scigantic exposes 16 tools: search_archives, get_archive, get_schema_card, get_data_access, list_archive_files, and 11 more. Their descriptions and schemas cost roughly 1,828 tokens of context every time the server is loaded.

### Does the Scigantic MCP server require authentication?

No. We connected to Scigantic without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Scigantic MCP server still maintained?

Scigantic is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the Scigantic MCP server?

VerifyMCP ran 13 checks on Scigantic, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://api.scigantic.com/mcp
- Repository: https://github.com/Scigantic/scigantic-mcp
- Website: https://scigantic.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-scigantic-mcp/api.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-scigantic-mcp/api/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/com-scigantic-mcp/api.json
- HTML version of this page: https://verifymcp.io/servers/com-scigantic-mcp/api
