Dataset Viewer MCP Server

filter

Filter rows in a Hugging Face dataset using SQL-like conditions

Input Schema

NameRequiredDescriptionDefault
auth_tokenNoHugging Face auth token for private/gated datasets
configYesDataset configuration/subset name. Use get_info to list available configs
datasetYesHugging Face dataset identifier in the format owner/dataset
orderbyNoSQL-like ORDER BY clause to sort results
pageNoPage number for paginated results (100 rows per page)
splitYesDataset split name. Splits partition the data for training/evaluation
whereYesSQL-like WHERE clause to filter rows

Input Schema (JSON Schema)

{ "properties": { "auth_token": { "description": "Hugging Face auth token for private/gated datasets", "optional": true, "type": "string" }, "config": { "description": "Dataset configuration/subset name. Use get_info to list available configs", "examples": [ "default", "en", "es" ], "type": "string" }, "dataset": { "description": "Hugging Face dataset identifier in the format owner/dataset", "examples": [ "ylecun/mnist", "stanfordnlp/imdb" ], "pattern": "^[^/]+/[^/]+$", "type": "string" }, "orderby": { "description": "SQL-like ORDER BY clause to sort results", "examples": [ "column ASC", "score DESC", "name ASC, id DESC" ], "optional": true, "type": "string" }, "page": { "default": 0, "description": "Page number for paginated results (100 rows per page)", "minimum": 0, "type": "integer" }, "split": { "description": "Dataset split name. Splits partition the data for training/evaluation", "examples": [ "train", "validation", "test" ], "type": "string" }, "where": { "description": "SQL-like WHERE clause to filter rows", "examples": [ "column = \"value\"", "score > 0.5", "text LIKE \"%query%\"" ], "type": "string" } }, "required": [ "dataset", "config", "split", "where" ], "type": "object" }