"How to fetch or scrape data from a website for use in training an LLM" matching MCP servers:

MCP server to access India Open Government Data (data.gov.in) resources via natural language queries.

Enables AI assistants to fetch public data from 120+ sources via natural language and save it locally as Excel, GeoJSON, or KML files.

Independent latency and uptime data for 46 hosted AI inference APIs, probed every 5 minutes from 4 regions with no gateway, plus a verified model deprecation calendar and Claude Code / Codex speed and accuracy drift. Four read-only tools, no API key; data CC BY 4.0.

Enables fetching patents from multiple global sources by patent ID, returning PDF, Markdown, and metadata with automatic caching.

Provides crystal structure generation, inspection, and export tools via MCP, supporting vacancy, interstitial, doping, solid-solution, surface, grain-boundary, interface, stacking-fault, and dislocation generators with deterministic outputs and optional Materials Project integration.

Enables AI agents to discover official public data sources, inspect their metadata and endpoint parameters, and execute live queries through a unified response envelope with a 500 ms budget.

An educational MCP server that wraps the Materials Project API, exposing tools to search chemical systems, get material summaries, find semiconductors by band gap, and retrieve crystal structure facts.

An MCP server that lets AI assistants discover and retrieve official statistics from SDMX services, returning actual data observations rather than just query URLs.

A MCP server exposing 95 US government open-data tools as agent-callable tools, enabling direct access to official APIs for environmental, financial, licensing, and infrastructure data with honest run-status reporting.

The only MCP server providing structured Chinese fashion supply chain intelligence for AI platforms. No equivalent data source exists in the MCP ecosystem. Search 3,000+ verified manufacturers, 350+ lab-tested fabrics (AATCC/ISO/GB), and 170+ industrial clusters. Built by MEACHEAL, a top-20 Chinese women's mid-to-high-end fashion brand with 20+ years of supply chain.

MCP server for the Mamba Labs Website Traffic Rank Estimator actor on Apify. Get a research grade Tranco popularity rank and trend for any company domain.

A single MCP server that transparently routes user requests to 83 open-data sources with built-in discovery and autonomous plugin creation.

An MCP server for discovering, downloading, querying, and analyzing datasets from Ontario's open data portals, allowing natural language questions and high-performance analytics via DuckDB.

Enables local read-only access to TheRundown Product API data including sports, affiliates, market definitions, events, futures, and open main lines using your own API key.

An MCP server that gives agents reliable access to LatAm data: tax-ID validation for 12 countries, live economic indicators, exchange rates, Brazilian company lookups, holidays, and business-day math.

Provides access to Japan Meteorological Agency (JMA) weather data including real-time observations, historical weather data, and forecasts from 1286 AMeDAS stations across Japan.

Enables natural-language research queries across marine data sources including FAO FishStat, BarentsWatch Fish Health, and Copernicus Marine, with data provenance and local file exports.

Enables AI assistants to convert raw and cooked weights for meat and poultry by cut and cooking method from USDA data, calculate how much raw meat to buy for cooked servings, and look up cooking yields and sample ranges.

Enables answering questions about Ukrainian open data from the data.gov.ua CKAN portal by searching datasets, inspecting resource schemas, and running read-only SQL aggregates over a single tabular resource. Every data-backed answer is computed from retrieved data and returned with machine-readable provenance, and unsupported or unanswerable requests are refused rather than guessed.

Ten tools I built to get facts from official open data, not guesses.

Enables searching and analyzing over 3,400 datasets from the Serbian government open data portal, with built-in charting and data transformation tools.

Enables access to Australian real estate data through the Realty In Au API, supporting property listings, agent/agency information, property details, school lookups, and property search with various filters.

Enables anonymous read-only queries of dated, evidence-qualified citizenship-by-investment research across eleven programmes, exposing eight tools for listing, retrieving, comparing, costing, travel rules, sources, change history and coverage. Runs as a hosted Streamable HTTP endpoint or a local stdio adapter with no accounts, keys or storage.

Enables AI agents to search, retrieve metadata, and query tabular resources from Latvia's Open Data portal (data.gov.lv) via CKAN.

Enables searching and querying Winnipeg Open Data datasets through natural language or SoQL, with tools for datasets, metadata, and row-level data.

Enables natural language search and discovery of open-access scientific datasets through the EOSC Data Commons OpenSearch service. Provides tools to search datasets and retrieve file metadata using LLM-assisted queries.

An MCP server that makes live Earth data usable by AI agents. Its initial data sources cover natural hazards: earthquakes from the USGS FDSN event catalog and volcanic activity from the Smithsonian Global Volcanism Program.

Enables querying Washington DC open data from opendata.dc.gov and ArcGIS REST API through MCP.

Enables searching and querying Île-de-France open data datasets (transport, environment, economy, etc.) via natural language or direct tool calls.

Enables AI agents to search, query, and explore datasets from the Centre-Val de Loire Open Data portal, covering regional services, transport, education, and environment.