Search FLOX documentation to find how-to guides, reference pages, tutorials, and error codes. Use it to answer questions about FLOX behavior, configuration, or APIs by grounding responses in actual docs.
MIT
260,649 tools. Last updated 2026-07-05 08:02
"How to fetch or scrape data from a website for use in training an LLM" matching MCP tools:
- Extract specific structured data from web pages using LLM-powered extraction. Use a prompt or schema to get details like prices, names, and descriptions.MIT
- Update local cart tracking after removing items from your Kroger cart. This tool syncs local data when you've already removed products through the Kroger app or website.MIT
- Extract structured data from web pages using LLM capabilities. Define specific information to retrieve with custom prompts and JSON schemas for organized output.MIT
- Extract content from multiple website pages by starting a crawl job. Use for comprehensive coverage of related pages, with options to control depth and scope.MIT
- Discover all indexed URLs on a website to identify pages for scraping or locate specific content when scrape results are incomplete.MIT
Matching MCP Servers
- Flicense-qualityDmaintenanceEnables Claude to query other LLMs like ChatGPT, Perplexity, and Gemini for verification and comparison, eliminating manual copy-pasting.Last updated
- Flicense-qualityBmaintenanceEnables any MCP-compatible AI assistant to search, filter, and retrieve information from a local document collection using a hybrid search pipeline with vector, BM25, reranking, and LLM enrichment.Last updated4
Matching MCP Connectors
India Open Government Data (OGD) Platform MCP — data.gov.in
- arjunkmrm-fetchOAuth
Fetch web pages and extract exactly the content you need. Select elements with CSS and retrieve co…
- Get the headline summary of a single activity—name, sport, date, distance, duration, training load, weather, and all top-level metrics—in one JSON response.MIT
- Retrieve the time-in-zone power distribution for a single activity to analyze workout intensity and training zone breakdown.MIT
- Retrieve new sentences from an active or recently completed meeting transcript. Use a cursor to fetch only additions since your last request.MIT
- Schedule a complete training plan from your workout library onto an athlete's calendar starting on a chosen date.MIT
- Extract brand colors, fonts, and logo from any website URL by parsing its HTML and CSS. Returns confidence-scored results including color roles, font frequencies, and logo preview.MIT
- Discover all indexed URLs on a website. Use the search parameter to find specific pages when scrape returns empty or incomplete results.MIT
- Fetch and store an image or video from a public URL, returning a media_id for use in publishing.MIT
- Crawl a website and extract content from multiple related pages. Returns final crawl status and data after polling.MIT
- Scrape B2B leads from Apollo.io by submitting a search URL. Returns a runId to check status later. Use webhooks for async delivery instead of polling.MIT
- Retrieve an LLM-optimized usage guide for any LPM package to understand its purpose, quick start code, exports, patterns, and pitfalls.ISC
- Retrieve all workouts stored in a specified library folder or training plan, including name, type, structure, training load, and intensity factor.MIT
- Verify if a website domain has been processed and is available for use in email marketing.MIT
- Retrieve the most recent training runs from your account. Use the limit parameter (1–100) to control how many are returned.MIT
- Download specific training datasets from CrowdCent prediction challenges to a specified .parquet file path for model training and analysis.MIT