Find datasets on Kaggle by entering a search query. This tool uses the Kaggle API to match and retrieve relevant datasets for analysis or machine learning projects.
MIT
131,150 tools. Last updated 2026-05-07 19:56
"A server for searching research papers, Kaggle datasets, and websites for ML/AI model training data" matching MCP tools:
- Find recent AI/ML research papers by searching arXiv, Papers with Code, and Hugging Face using keywords and date filters.MIT
- Perform AI-powered web searches to extract structured data from search results for research, competitive analysis, and multi-source information gathering.MIT
- Download ML model artifacts (e.g., .pkl, .onnx) from GitLab Model Registry for inference or evaluation. Requires Premium/Ultimate plan.MIT
- Search scholarly works including papers, articles, and preprints using keywords to access academic research with quality-scored results and source verification.
- Search the SHARE database for research outputs including papers, datasets, and preprints with quality scores and audit-ready citations.
Matching MCP Servers
- Alicense-qualityBmaintenanceEnables searching for upcoming academic conferences and events from WikiCFP by keywords, returning detailed information including dates, locations, submission deadlines, and related resources.Last updated5GPL 3.0
- Alicense-qualityCmaintenanceProvides AI assistants with a standardized interface to interact with the Todo for AI task management system. It enables users to retrieve project tasks, create new entries, and submit completion feedback through natural language.Last updated39Apache 2.0
Matching MCP Connectors
The verified hub for conferences and journals. Powered by AI to match your scholarly ambitions with the world's most prestigious academic opportunities.
Search for local businesses worldwide. Structured data optimized for AI agents. • Search Millions of businesses over 49 countries (Europe, Northamerica, Southamerica, Asia, Oceania) • Quality & demand scoring for every business • Ranking based on real user click-through data
- Search open datasets from Gdansk's public data portal to access government information, with quality scoring and source verification for reliable research.
- Search INSPIRE-HEP for high-energy physics literature and retrieve recent papers with quality metrics and source verification.
- Search U.S. Department of Energy research publications from OSTI.gov to find journal articles, technical reports, conference papers, and dissertations. Returns results with quality scoring and verifiable citations.
- Search academic papers on Semantic Scholar to find titles, abstracts, citations, and links with quality-scored results for research verification.
- Search arXiv preprint server for scientific papers to find titles, authors, abstracts, and arXiv IDs with quality-scored results and verifiable citations.
- Search NHS Scotland's open health data portal to find datasets with quality scores, source citations, and audit information for research and analysis.
- Search U.S. federal open government datasets on Data.gov to access public domain data with quality scoring and verifiable citations for research and analysis.
- Search the web for current information, news, articles, and websites to find up-to-date content, research topics, or answer questions about recent events.Apache 2.0
- Retrieve datasets from LangSmith with filtering options for IDs, names, data types, and metadata to organize and access training data.
- Find academic papers and preprints on SSRN for social sciences, economics, law, finance, and humanities research.Apache 2.0
- Search academic papers and preprints on arXiv to find research papers, scientific studies, and technical literature across fields like AI, physics, and mathematics.Apache 2.0
- Download specific training datasets from CrowdCent prediction challenges to a specified .parquet file path for model training and analysis.
- Extract structured financial data from investor relations websites and online sources for investment research when APIs are unavailable.MIT
- Retrieve available training datasets for CrowdCent prediction challenges to prepare data for model development and analysis.