Search and fetch public web pages, or run Firecrawl search, scrape, and crawl to retrieve ranked results, readable content, or crawl job pages.
Apache 2.0
Destructive
742,046 tools. Updated 2026-11-04 12:21
"How to fetch or scrape data from a website for use in training an LLM" matching MCP tools:
- Check an EasyDeploy AI training job by job_id and optionally wait for it to complete or fail, returning status, training time, and model version.MIT
- Start an asynchronous crawl from a URL, following links matching a regex to scrape multiple pages. Returns a job ID for tracking progress via polling or webhook.MIT
- Retrieve training datasets in your account to locate dataset IDs and names for use in AI Toolkit configurations. Optionally returns full dataset payloads.MIT
- Starts a model training job for a model version, using one training credit and returning a job ID to track completion.MITDestructive
- Check if a domain allows an AI agent to scrape, summarize, train, or search its content. Returns allowed status, reason code, and policy signals.MIT
Matching MCP Servers
- AlicenseNot gradedqualityDmaintenanceA minimal MCP server with get_weather and create_ticket tools, used for testing MCP servers across protocol, unit, eval, transport, and auth layers.MIT
- AlicenseAqualityCmaintenanceEnables AI agents to fetch one or many web pages concurrently and receive clean, LLM-ready Markdown with navigation, ads and boilerplate stripped away, plus extracted metadata such as title, description, author, Open Graph tags and canonical URL. It runs locally over stdio with no API key or account, requiring only a single command.3MIT
Matching MCP Connectors
Video how-to search for AI agents: 2,000+ video skills, tutorials and FFmpeg recipes. No key.
Browser agents and stealth cloud browsers for AI: run web tasks, fill forms, extract data.
- Register a generation model for testing by selecting an LLM from the registry, enabling use with run_test.Apache 2.0
- Fetch a public X/Twitter profile by handle: display name, bio, location, website, join date, verification, avatar/banner URLs, and follower/following/post counts. Use it to identify an account or check if it exists.MIT
- Start a Google Maps lead scrape by categories and locations, returning businesses with contact details, emails, websites, and social profiles for building targeted lists.MIT
- Run an AI-visibility audit for a website and get scores, citation matrix, competitors, and top gaps. Get fresh, current data or use cached results when a recent measurement exists.MIT
- Creates an empty dataset in an execution context with description, type labels, and version metadata, ensuring provenance tracking for data management.Apache 2.0
- Fetch detailed workout data by ID or UUID, including segments and step structure. Resolves Garmin Coach and training-plan workouts; rest-day UUIDs return minimal records.MIT
- Turn a web page into structured JSON with an LLM. Provide a sample JSON shape to control output, or let the AI infer it; does not save data.MIT
- Submit a scrape job asynchronously and get a job_id right away, so long-running scrapes with heavy JS rendering or full-page screenshots never block the connection. Poll with scrape_status and fetch results when done.Apache 2.0
- Scrape a URL with a pre-created AI parser to extract structured data as JSON. Use when you have a finished parser and need consistent data from similar pages.MIT
- Estimate USDT cost for a given MB volume in a specific country. Use for reference queries like 'how much would 2GB in Japan cost?' without pre-purchasing data.MIT
- Refresh historical training data for listed tickers from Yahoo Finance or FRED, with full backfill from 2000 for new features and incremental updates to today for existing ones.MITDestructive
- Create an empty training dataset in draft status, ready for file uploads and status polling before submitting a training job.MIT
- Track VO2 max trends over a date range to assess fitness gains, detect insufficient training, or identify overreaching from Garmin data.MIT
- List all website monitors, or fetch one monitor's configuration and status—check times, active state, credit cost, alert settings. Use it to find monitor IDs for changes or control.Apache 2.0
- Checks how businesses rank in Bing local results for a keyword and location, returning rank, name, address, phone, website, and hours. Use it to track Bing and Copilot local visibility.MIT