Datasets

Explore and visualize CSV datasets with the power of pandas and matplotlib.

Securely query and analyze Google BigQuery datasets via natural language.

Access LangSmith observability data including traces, prompts, datasets, experiments, and billing usage.

Provides a powerful Ethereum blockchain data extraction and analysis interface using Cryo and DuckDB, enabling efficient SQL-based querying of on-chain datasets with advanced filtering capabilities.

Provides a JSON manipulation interface using JSONPath syntax for querying, transforming, and analyzing structured data across diverse datasets.

Integrates with Ragie's knowledge base retrieval system to enable efficient querying and information extraction from large-scale datasets.

Query and analyze large datasets using Tinybird analytics.

Generates realistic, multi-table synthetic datasets from natural language descriptions, YAML schemas, or existing databases with referential integrity.

Handles massive contexts exceeding token limits by chunking content strategically, enabling recursive sub-queries with tool access and parallel processing for analyzing large codebases, documents, or datasets.

Connects to any CKAN open data portal for searching datasets, exploring organizations, querying tabular data, and reading metadata.

Integrates with Google's Vertex AI and Discovery Engine APIs to enable advanced search and retrieval operations on large datasets, supporting semantic search and natural language understanding.

Integrates with Excel files to enable efficient processing and analysis of large spreadsheet datasets through automatic chunking and pagination.

Provides a bridge to NASA's Earthdata platform for searching and retrieving Earth science datasets and data granules based on keywords, temporal ranges, and geographic boundaries.

Comprehensive Apache Superset integration with 128+ tools for dashboards, charts, datasets, SQL Lab, security management, and access control automation.

Integrates with TrueNAS Core storage systems to enable natural language control of user management, pool monitoring, dataset creation, ZFS properties, permissions, and Kubernetes storage provisioning with automated snapshot policies and NFS/iSCSI target configuration.

Integrates with Data.gov to enable searching, retrieving, and accessing U.S. government datasets for data-driven analysis and research projects.

Transforms CSV and Excel files into conversational data analysis by generating and executing Python code to answer natural language questions about datasets with automatic error correction and visualization capabilities.

Provides offline Wikipedia access through local dataset downloads from HuggingFace's finewiki collection with multi-language support and configurable fallbacks for scenarios requiring encyclopedic knowledge without internet connectivity or reduced query latency.

Integrates with Dify's dataset retrieval capabilities, exposing knowledge base querying as a discoverable tool for retrieving information from Dify datasets

Provides tools to interact with Powerdrill datasets to perform data work.

Bridges to Palantir Foundry platform, enabling ontology data interaction and SQL query execution against datasets with tools for listing types, querying objects, executing SQL, and running ontology functions.

Integrates with Korean Open Data Portal APIs through a three-step workflow that searches for APIs by keywords, retrieves detailed documentation, and executes calls with automatic service key injection for accessing government datasets and building data analysis applications.

Enables data analysis and visualization by integrating with pandas, scikit-learn, matplotlib, and seaborn libraries for dataset exploration, statistical analysis, and chart generation

Organizes and analyzes numerical research data through a structured knowledge graph, enabling tracking of projects, datasets, variables, hypotheses, and statistical tests with their relationships and results.

Integrates with phosphobot automation service to replay recorded user interaction episodes from datasets, enabling testing scenarios and development workflows that require reproducible user behavior sequences.

Integrates with Biomart to enable advanced biological data queries, including gene information retrieval, ID translation, and dataset exploration using the pybiomart package.

Provides structured access to International Monetary Fund datasets, enabling retrieval of economic indicators and financial statistics for research and analysis workflows.

Generates customizable human face images using thispersondoesnotexist.com, offering options for shape, dimensions, and batch processing for UI prototyping and dataset creation.

Provides a bridge between AI assistants and machine learning datasets, enabling search, validation, and retrieval of ML Croissant metadata from the MLCBakery system without switching contexts.

Integrates with France's national open data portal and IGN geographic services to provide access to government datasets, administrative data, and official geographic references for location-aware applications and urban planning research.

Provides access to Berlin's open data portal with 6 tools for CKAN catalog search, dataset analysis, and exploration across 2500+ municipal datasets.

Bridges to NASA's Common Metadata Repository for searching and retrieving Earth science datasets by date range, provider, and keywords with structured information including concept IDs and descriptions.

Integrates with Elasticsearch and OpenSearch clusters for index management, document operations, search queries, snapshot handling, and cluster monitoring across large datasets.

Search and browse the FMHY free media resource dataset by keyword, section, or URL.

Provides real-time access to Spanish government open data through 26 specialized tools covering grants, legislation, company registry, statistics, and national datasets for legal research, business intelligence, and policy analysis.

Provides Excel file analysis through pandas-powered tools for loading spreadsheets, extracting schemas, sampling data, generating statistics, and assessing data quality to enable quick dataset exploration without manual navigation.

Integrates with Kaggle platform for searching competitions, downloading datasets, submitting predictions, managing notebooks, and engaging with the data science community.

Enables safe SQL query execution on Google BigQuery datasets with built-in safeguards that prevent data manipulation and limit query size to 1 TB.

Integrates with Singapore's government data APIs (data.gov.sg and SingStat) to enable browsing, searching, filtering, and downloading of open datasets for policy research, economic analysis, demographic studies, and data journalism.

Query and download datasets from the ColabFit materials science database

Integrates with Observe platform for performance monitoring through OPAL queries, dataset management, monitor configuration, and semantic search of troubleshooting runbooks to enable natural language root cause analysis and system reliability investigations.

Explore open research datasets from OpenAlex, Crossref, ORCID, and DataCite on Google BigQuery.

Provides a fact-checking tool that compares input facts against a predefined dataset using string similarity algorithms and integrates external services like NLTK and a poker win calculator for flexible information verification.

Integrates with Apache Airflow through Bearer token authentication to provide DAG operations, task instance management, connection handling, variable management, dataset operations, and monitoring functions with optional read-only mode and automatic UI link generation.

Access 5,000+ OECD economic and statistical datasets

Access 1,053 datasets from the Dominican Republic open government data portal.

Search and query Eurostat datasets covering EU economy, demography, trade, and NUTS regional statistics.

Integrates with Microsoft Dataverse to execute FetchXML queries, create bulk contacts with progress tracking, and generate Chart.js reports while using intelligent prompts for large dataset management and markdown table transformation.