"Scraping Public Documents" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Search over 1.85 million captioned images using text, a reference image, or both. Upload a JPEG, PNG, or WebP image as base64, or provide a public HTTPS image URL. Find similar images from a Lightdrift asset ID and retrieve hosted file URLs, source licenses, and attribution. Connect with OAuth or an API key. Searches cost $0.005 ($5 per 1,000); image details are free. Setup: https://docs.lightdrift.ai/guides/images-mcp
Korean public procurement law: rule-engine rulings, statutes search, live court precedents
Federated commerce search across independent WooCommerce merchants. Keyless, read-only MCP server.
Public TikTok profiles, videos, comments and keyword search as JSON. No developer account.
Delivery Assurance: compares supplier claims with public observations, keeping unknowns.
Web scraping for agents. Point it at a URL and it returns the page as clean markdown, JavaScript-rendered pages included. Point it at a site and it maps the URLs or crawls the section you need in the background, a few pages at a time so results fit in the conversation. Search the web and read full pages, extract fields with a JSON schema you define (validated, never invented), read a store's catalogue or a blog's posts from the platform's own feed, and check whether a page has changed. Failed requests cost nothing. The free plan includes 1,500 credits a month.
Search apps and games and get short AppAgg summaries with links to full pages.
Turn any public website into an MCP server for agents to search, read and navigate.
Search Signed's public angel investor directory by sector, check size, or keyword. No login needed.
Search Vascue's public healthcare-operations, insurance-claims and clinic-booking documentation. Public content only; never send patient data, credentials or booking requests.
Give your agent collective memory. Bring one real MCP or API integration problem. Call try_remnant with that problem, then inspect_memory on the returned memory before using it. Try the relevant advice in your task, then report what happened through Candy. Failures and partial results are useful. If you learned something reusable, leave a lesson with its evidence and limits for the next agent. Free public search. No human signup required. Remote MCP: https://remnant.dedale-bi.com/mcp. Connect: https://remnant.dedale-bi.com/connect. Connection examples: https://github.com/Dedale-Project/remnant-connect. Candy: https://remnant.dedale-bi.com/agent-candy. Search reusable knowledge, discover agents and inspect Trust Passports. Small operator-published bootstrap collection; no claimed independent validation. Evidence and cryptographic integrity do not guarantee truth or safety. Candy uses a temporary bearer token on each request; REST is available when clients cannot update headers. Candy grants no canonical reputation or verified identity. If no test ran, do not submit an outcome.
Built for companies. Ready for AI agents. PaperOffice is the headless DMS your agent can actually operate: one MCP endpoint to search, read, upload, extract and sign business documents — no UI, no glue code. What the tools do: full-text and semantic search across workspaces · read existing OCR text without a new job · three-step upload with presigned URLs · AI-OCR (text, line boxes, tables) · structured extraction for invoices and 60+ document types (IDP) · PDF generation from Markdown/HTML · e
The first low-latency wire service purpose-built for AI agents. Ingests 54+ public APIs and 71k RSS feeds across 232 countries, outputs CWF (Cognitive Wire Format) – 80% shorter than JSON, sub-second WebSocket delivery. 9 MCP tools: get_latest_signals, search_signals, get_fused_signal, scope_signals, get_facet_manifest, list_facets, get_related_signals, list_data_sources, get_billing_profile. 26 citable fusion products with verifiable formulas – no black-box scores.
Onchain Diary exposes its full knowledge base — 96 Web3 security articles and 220 glossary terms, in English and Chinese — through the Model Context Protocol. Any MCP-capable assistant can search it and read complete articles without scraping HTML.
Search otwarteAPI.pl — a catalog of 53 official public Polish and EU APIs (VAT white list, KRS, GUS, NBP, ECB, Eurostat, VIES and more), curated for AI agents. One tool: find the right API by natural-language query. No API key, no signup.
Search 30,000+ decided U.S. security-clearance (DOHA) decisions: cases, outcomes, statistics, and timelines, with a citable link for every answer. CASE is the searchable public record of DOHA industrial security-clearance decisions from 1996 to the present, refreshed nightly.
Query a live PrestaShop e-commerce store: search the catalog, get product details, real-time prices and stock. Fondouk is an open-source module (MIT) that makes any PrestaShop store speak MCP and UCP — this connector is its public demo store. Read-only, public data only.
Search U.S. cell phone plans from major carriers and MVNOs, compare supported service costs and billing conditions, find consumer wireless news, and get switching guidance. Public read-only access with no authentication. Results retain original source dates and unknown costs. Carrier affiliate links are disclosed. Documentation: https://saveonphone.com/developers/
**ColdState Knowledge Search MCP Server** https://github.com/daniel-coldstate/coldstate-mcp Semantic search over 64.6M knowledge entries — the structured alternative to web search APIs and web scraping for LLM agents. No crawling, no rate limits, sub-3s responses. Cloud-hosted at services.coldstate.ai
Search disc golf discs, compare Speed/Glide/Turn/Fade flight ratings, and find similar alternatives across brands. Free, public, read-only.
