scigantic-mcp
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SCIGANTIC_API_URL | No | API base URL. Set to https://staging-api.scigantic.com for staging. | https://api.scigantic.com |
| SCIGANTIC_API_ORIGIN | No | Origin header selects the public (default) catalog tenant. | https://scigantic.com |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_archivesA | Search the Scigantic catalog of public scientific data archives by natural-language query. Returns ranked matches with id, title, category and a short summary across all domains. Follow up with get_schema_card to understand a match's structure. Args: query: Natural-language search, e.g. "single-cell RNA-seq of human cortex". category: Optional category filter, e.g. "Genomics & Bioinformatics" (comma-separate for several). limit: Max results (default 10, max 50). |
| get_archiveB | Get full metadata for one archive by id, including whether a schema card exists. Args: id: Archive id from search_archives. |
| get_schema_cardA | 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 downloading it. Args: id: Archive id from search_archives. |
| list_archive_filesB | List a sample of the files/objects in an archive's storage. Args: id: Archive id from search_archives. limit: Max entries (default 50, max 200). |
| get_data_accessA | 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. Args: id: Archive id from search_archives. language: Optional filter for the snippet language (e.g. "datasets", "s3fs", "gcsfs"). |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| explore_dataset | Find and understand a Scigantic dataset on a topic, end to end. |
| start_analysis | Set up analysis of a specific Scigantic archive in your own environment. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
Most tools are clearly distinct: search returns matches, get_archive fetches full metadata, get_schema_card explains structure, list_archive_files samples files, get_data_access provides load code. However, get_archive and get_schema_card overlap somewhat since both retrieve metadata about an archive, and list_archive_files could be confused with get_schema_card's file/column info. Descriptions mostly clarify boundaries.
All use snake_case with verb_noun structure, but verbs are mixed in style: 'search_archives' and 'get_archive' share the archives noun base, while 'get_schema_card', 'list_archive_files', and 'get_data_access' diverge to different nouns. Each tool combines get/search/list with a distinct noun, but the noun targeting is inconsistent (archives vs schema_card vs archive_files vs data_access).
Five tools is well-scoped for a scientific data catalog server. Each tool has a clear purpose: discovery (search), metadata (get_archive), structure (get_schema_card), file listing (list_archive_files), and access guidance (get_data_access). Together they cover a complete discovery-to-access workflow without redundancy.
The workflow is well covered: search to find datasets, get_archive for metadata, get_schema_card for structure, list_archive_files for contents, and get_data_access for loading. Minor gaps exist, such as no tool to filter/sort search results more granularly, no preview/download of actual data contents, and get_archive is somewhat redundant given get_schema_card. But core discovery and access needs are met.