Assess dataset contents by listing resources with format, size, DataStore status, and download URL. Filter by format to quickly identify accessible files.
MIT
751,545 tools. Updated 2026-11-06 15:20
"Informational MCP Servers with Croissant Dataset Format Support" matching MCP tools:
- Lists installed En Croissant databases, reporting title, game count, size, and .pgn sidecar status.MIT
- Show all En Croissant repertoire files and identify the color each trains, helping you choose the right repertoire for opening practice.MIT
- Download a mainframe dataset in binary format by specifying the source dataset and an optional target file path.MIT
- Retrieve Croissant metadata for a dataset from the Hugging Face Hub, enabling structured access to machine learning datasets in a high-level format.MIT
- Checks Croissant/GeoCroissant JSON-LD descriptions for syntax, structure, and graph conformance per MLCommons rules to identify blocking errors before publishing.-
Matching MCP Servers
croissant-validationofficial
AlicenseNot gradedqualityDmaintenanceValidates MLCommons Croissant dataset metadata (JSON-LD) for schema compliance, as a stateless MCP server.MIT- AlicenseAqualityDmaintenanceMCP server that gives Claude programmatic access to a local En Croissant chess opening trainer, enabling conversational opening prep by reading its SQLite database, PGN files, and Lichess API. It supports repertoire review, due cards, and opponent statistics directly from chat.81MIT
Matching MCP Connectors
- CroissantOAuth
Search, book, and manage coworking spaces and conference rooms across 100+ cities worldwide with Croissant.
- SamDesk SupportOAuth
Read your SamDesk support inbox, find customer agreements and draft replies. Read-only.
- Extract concrete dataset download URLs from Croissant/GeoCroissant metadata, along with formats, sizes, and checksums, so ingestion code can fetch data files without manual JSON parsing.-
- Fetch dataset data or subdataset list by specifying provider and dataset path. Supports pagination, format selection, sorting, grouping, and aggregation.MIT
- Retrieve public datasets formatted as Croissant metadata to enable standardized machine learning data discovery and access.MIT
- Retrieve governed dietary consumption-dataset support and allowed-use posture by jurisdiction, dataset, or contaminant family.Apache 2.0
- Convert a document to a chosen output format, with conversion options, and return the result as text. `to` picks the format (Markdown, docling JSON with structure and page provenance, HTML, plain text, LaTeX, RAG chunks, WebVTT, Pandoc…MIT
- Retrieve per-dataset EEG/BCI pipeline rankings from the public benchmark leaderboard, sorted by mean accuracy with confidence intervals, to compare performance and find template IDs.Apache 2.0
- Discover available Teal modules with descriptions and dataset requirements. Filter by package (clinical/general) and category to find suitable analysis modules.AGPL 3.0
- Build a dataset from completed execution results to prepare records for export. Returns a job ID to track progress, then provides a dataset ID for dataset.export.MIT
- Retrieve all records from a completed dataset as text in your chosen format (jsonl, csv, json, md, xml, rag). Export directly in the response for use in LLM fine-tuning, analysis, and integration.MIT
- Index a dataset so text chunks become searchable. Splits content into RAG-ready chunks and generates embeddings for semantic retrieval.MIT
- Delete a dataset type term from the Dataset_Type controlled vocabulary. Only use for types not referenced by any datasets, as deletion fails with foreign key errors otherwise.Apache 2.0
- Split a dataset into train, test, and optional validation subsets, using random or stratified sampling to preserve class distribution for ML workflows.Apache 2.0
- Query a chosen US federal procurement dataset—opportunities, awards, contracts, entities, subawards, protests, and more—with filters to find records and support market research.MIT
- Retrieve and filter LangSmith experiment projects for model evaluation and comparison by specifying a dataset ID or name.MIT
- Create a hosted dataset in a selected project with a custom schema or source binding. Preview and confirm before it is written.Apache 2.0Destructive