Run a configured Spec pipeline on workspace documents or public file URLs to extract structured rows in one call.
MIT
619,810 tools. Updated 2026-09-28 18:01
"Scraping Public Documents" matching MCP tools:
- Extract raw text and metadata from any public HTTPS URL. Get page title, word count, and content from online articles and documents.MIT
- Retrieve recently focused documents to identify which files a user was last working on, excluding chat, browser, and terminal documents.-
- Route requests through datacenter IPs for high-volume scraping of APIs and public data feeds without aggressive anti-bot protections. Supports geo-targeting and sticky IP sessions.MIT
- List saved scraping flows to find flow IDs and discover available flows before running one.MIT
- Search the web to find relevant pages, returning URLs, titles, and snippets immediately for pre-scraping discovery.Apache 2.0
Matching MCP Servers
- AlicenseAqualityAmaintenanceSearch Vascue's public healthcare-operations documentation: AI front desk for clinics, provider-side insurance claims automation, Cliniko integration, security. Public content only.1MIT
- FlicenseAqualityBmaintenanceEnables AI assistants to fetch public web pages as readable text or HTML, with caching, live refresh, and parallel job handling.2-
Matching MCP Connectors
Web scraping for AI agents. Extract text and metadata from any URL worldwide. $0.005/page.
Congressional Documents — full-text search and retrieval over the official
- List scrape strategies with protection levels and credit estimates to prepare for scraping unknown protected websites.-
- Search Federal Register documents including proposed rules, final rules, notices, and presidential documents by query, agency, type, and date range.MIT
- Crawl a website to discover and scrape multiple pages, following links up to a set depth. Filter URLs with regex and use saved or custom scraping configs.MIT
- Browse files stored in your workspace. Filter by type to find specific assets like fonts, images, or documents, and retrieve public URLs for each file.MIT
- Retrieve a list of all documents in your Shortcut workspace for easy access and management.MIT
- Retrieve all mapped scraping pages in your Gluedly workspace to review configured scrapes.MIT
- Add a product to your shop catalog using your own data, with no scraping needed. Specify details like title, price, and affiliate URL to create the entry directly.MIT
- Extract clean content from a public URL, returning Markdown, text, metadata, links, JSON-LD schema, and sections for scraping, RAG ingestion, or content analysis.MIT
- Insert new documents or update existing ones by ID in a Zvec collection. Modify documents without checking existence first.Apache 2.0
- Search your published PasteAI documents by entering a keyword to find documents with matching titles.MITDestructive
- Retrieve a list of recently published documents from PasteAI. Quickly see shared documents and access them.MITDestructive
- Search for documents in Shortcut by title, filter by archived status, creator, or followers, with pagination support.MIT
- Generate critical instructions for web scraping tools to handle proxy rotation and bypass anti-bot measures when extracting data from websites.ISC
- Add documents to a Meilisearch index using the MCP server. Specify indexUid and documents array to manage data efficiently for search and retrieval.MIT
- Retrieve documents from a specified Meilisearch index using indexUid, with optional offset and limit parameters for precise data extraction.MIT