"Understanding Web Scrubbing Techniques" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
SnapRender gives AI agents eyes on the web through a hosted MCP server. Send a public URL and get the page back as an image, a PDF or clean markdown, with no browser to run or maintain. Capture the viewport or the full page as PNG, JPEG, WebP or PDF, at desktop size or with a phone, tablet or laptop preset, in light or dark mode. Ads and cookie banners are removed by default, and you can hide elements or click one before the capture. extract_content reads the same page as markdown, text, article, links or metadata, so an agent can see a page and read it in one session. Made for monitoring and client work: batch up to 50 URLs in one job, check the cache for free before spending a capture, share signed links that render without an API key, and get webhooks when a batch finishes or a scheduled capture spots a change. Track competitors' pricing and landing pages, or send clients current screenshots of their sites. Connect with OAuth (Google, GitHub or email) or an API key. Works with Claude, ChatGPT, Cursor, VS Code and any MCP client. Free plan: 200 screenshots a month, no credit card. Paid plans from $9 a month for 2,000 up to $199 a month for 200,000. Home: https://snap-render.com Docs: https://snap-render.com/ai-agents
Pay-per-use APIs for agents: web research, data lookups, and metered endpoints billed to credits.
Das Stellen-Radar bündelt den Stellenmarkt in Deutschland an einem Ort: über 260.000 aktuelle Stellen, davon über 60.000 Führungspositionen. Dafür beobachtet das Stellen-Radar über 2.500 Personalberatungen, über 90 Jobportale und die Karriereseiten von über 6.300 Unternehmen. Viele Stellen, die über Personalberater besetzt werden, finden sich auf keinem Portal. Über das MCP können Sie: * Ihre 100 passendsten Stellen mit Kurzfassung, Stichworten, Punktzahl und Link in Claude laden, zusammen mit Ihren eigenen Markierungen und Notizen, sie dort näher analysieren und vergleichen und sich mit Claude passende Bewerbungsunterlagen erstellen, * sehen, wie viele Stellen es für Ihre Zielposition in Ihrer Region gibt, und die besten Treffer ansehen, * Ihr Suchprofil verbessern und jede Änderung vorher mit echten Vorher- und Nachher-Zahlen durchrechnen, * Stellen merken, ausblenden oder als beworben markieren, Notizen zu Stellen festhalten und den Stellen-Agenten einstellen, der Ihnen neue passende Stellen per E-Mail schickt. Alles, was Sie über das MCP markieren oder notieren, finden Sie auch im Stellen-Radar im Web wieder. Übertragen werden nur strukturierte Eckdaten wie Zielposition, Ebene, Branche und Region, nie Ihr Lebenslauf. Werkzeuge und Antworten sind auf Deutsch. Find jobs in Germany from executive search firms, job portals and company career pages.
Agentic Finance: 500+ agent tools, multi-chain USDC over x402 or MPP, or free via proof-of-work
Engram is a persistent, long-term memory layer for AI agents and assistants. Claude, ChatGPT, Grok, Cursor and any MCP client share one memory, stored as plain markdown notes: your knowledge base, second brain and AI context in one place. No extraction step: the memory is the note itself, so you can read exactly what your AI remembers and fix it. Edit your memory in Obsidian (real-time sync), the web app, or on your phone. Hybrid keyword + semantic search (RAG over your notes) finds exact strings like error messages, config keys and IDs. Remote MCP server over Streamable HTTP with OAuth 2.1; notes encrypted at rest. Https://engram.page https://youtu.be/rwnPeZ-8Lqo?is=NI-N7BduydGAiZlF https://github.com/engram-app/Engram
Strips 85-97% of HTML/DOM boilerplate into clean Markdown, skeletons, or BM25-ranked RAG chunks.
41Machine-exclusive web distillation MCP server for AI agents. Deterministically strips 85-97% of HTML/DOM/JS/CSS token bloat into clean Markdown, structured JSON tables/JSON-LD, <200-token structural skeletons, or BM25 budget-capped context with native HTTP 402 (x402 Base USDC & L402) micropayments.
Build 3D web apps: physics, audio, music, Blender import. Live edits, undo, versions, publishing.
Connect Chatway, an AI-powered website live chat and customer support platform, to ChatGPT, Claude, Gemini, Cursor, and other AI assistants using MCP. Chatway helps businesses communicate with website visitors, manage customer conversations, and deliver faster support across multiple channels, including website live chat, email, WhatsApp, Instagram, and Facebook Messenger. Native mobile apps for iOS and Android let support teams manage conversations and respond to customers on the go. With Chatway's MCP server, AI agents can access and manage customer support operations. Search and read conversations, send replies, add private notes, resolve and assign chats, manage contacts, retrieve customer information, and search knowledge base articles. Chatway also includes a built-in AI Support Agent for automated customer service, a shared team inbox, support ticket management, a customizable website chat widget, a help center, team management, automated workflows, visitor tracking, and integrations with popular platforms, including WordPress and Shopify. Connect external AI agents to automate customer support, answer customer questions, access conversation history, and streamline support workflows without building custom integrations. Manage your customer support from anywhere using Chatway's web dashboard or mobile apps. The hosted MCP server supports Streamable HTTP and secure OAuth 2.1 authentication with scoped permissions. Available on all Chatway plans, including the Free plan. Conversation limits apply. Website: https://chatway.app Documentation: https://developers.chatway.app/mcp/guides.mcp_overview
Agent intake desk for property renovation. Read only, CORS open, fail closed, receipts recompute.
Vigilia watches your live app, explains every problem in plain language and writes the fix prompt. Your AI fixes it; Vigilia confirms with real traffic. Vigilia watches web apps that are live with real users, including apps built with Lovable, Bolt, v0, Cursor and Claude Code. It catches errors, failed requests and downtime, explains each problem in plain language, and writes a fix prompt for it. Connect Vigilia to Claude and ask what's broken. Claude lists your open incidents worst first. For each one it reads the plain-language diagnosis, who it affects, the technical evidence (error, page, failing request, stack frames and what the visitor did right before) and Vigilia's fix prompt. In Claude Code or another coding agent, Claude can then fix the cause in your own codebase. Once you've deployed, it marks the incident fixed, and Vigilia watches real traffic to confirm the error stayed away. If it comes back, the incident reopens as a regression. You can also ask how an app is doing (uptime, open incidents, today's traffic), get the exact install snippet for a new project, and check that a live site is running Vigilia. Vigilia never reads or changes your code: the fixing happens in your session, by your AI, in front of you. The only tool that changes anything is marking an incident fixed (the install check just records its result on the app), and you can connect with read-only access. Your data is stored in the EU. Emails, tokens and card numbers are stripped from what visitors' browsers send, and only that scrubbed error context is sent to Anthropic to write the diagnosis. Requires a Vigilia account. The free plan covers one app; reporting backend errors (Supabase, Next.js routes, Workers) is part of Pro.
K2 annual reports for Swedish limited companies (aktiebolag). Your AI uploads the SIE file, reviews the figures, reads the tax calculation and INK2, and fills in the annual report step by step in the same guided flow as the web app, while you watch in AI mode. Payment, signing and digital filing with Bolagsverket are always done by you.
Scans untrusted web pages, emails, MCP responses, or A2A payloads for hidden prompt injections an.
Marketplace and work network for AI agents and swarms: discover paid jobs, specialist services, digital products and collaborators. Messaging and collaboration are free. Weekly Most Active shares 3 / 1.50 / 0.50 USDC prizes under live eligibility rules. Paid flows accept USDC on their advertised Base or Arc network; Web Intelligence costs 0.01 USDC on Base or Arc. Optional Pro costs 10 USDC once. Lost keys can be recovered with a previously verified wallet at https://speedbot.dev/recover. Compact MCP has 23 entry tools; speedbot_action reaches specialized tools. Current instructions: https://speedbot.dev/docs and https://speedbot.dev/release.json.
Executes live Google News RSS + HackerNews Algolia search queries and returns clean, token-pruned.
Convert docs and web pages to clean Markdown: PDF, DOCX, XLSX, EPUB, scans, URLs. Batch of 10.
Fetch any public web page through managed proxies, with optional JS rendering and extraction rules.
fivebar’s MCP server lets Claude, ChatGPT, Cursor and other MCP clients read your cookieless, privacy-friendly web analytics and explain what changed, where traffic and signups came from, and which pages are slow. It can also install and verify the tracking tag from your coding agent, and connects with OAuth, read-only by default, with no API key needed.
Turn any web page URL or HTML into clean Markdown or plain text for an LLM to read.
Test a web app in a real browser from plain English. Passed, failed or cannot verify, with evidence.
