Enables agents to inspect web pages for Cloudflare Turnstile challenges without an API key, and clear Turnstile or WAF challenges using a SolveGate API key.
Enables MCP clients to search Yellow Pages local businesses by keyword and location and retrieve full listing details such as phone, hours, services, brands, and payment methods.
Enables AI assistants to manage Cloudflare zones and DNS records through the Model Context Protocol, including listing, fetching, creating, updating, and deleting DNS records.
An MCP server that deterministically scores landing pages on conversion-critical signals and blocks ad spend on low-quality pages to prevent wasted budget.
Enables AI agents to work in a signed-in Systeme.io account by reading sales reports, managing funnels, pages, and email campaigns, and performing approval-gated refunds, invoices, and publishing actions.
MCP server for the Cloudflare API v4, written in Go. Exposes 28 read tools across zones, DNS, WAF/firewall, rate limits, HTTP request logs, Security Center, and threat intelligence.
Pages Native 0.5.0: 36 local MCP tools and a Codex plugin for native Apple Pages on macOS. Guarded text and table edits, structured search, typed model recipes, batches of up to 10 documents, recipe history and restoration, native PDF previews. Uses only the public Pages scripting API; preserves .pages without Word conversion or Accessibility.
Enables accepting USDC payments on Base and Solana via x402, with bring-your-own-wallets and no Coinbase account required, optimized for Cloudflare Workers and PayAI facilitator.
Enables keyword research, listing audits, and shop data from eRank through read-only MCP tools, including keyword metrics, related searches, Etsy tags, top listings, bulk keyword analysis, listing audits, shop info, and connected shops.
Enables querying a Tonal fitness account for workout history with per-set weights, muscle readiness, strength scores, and lifetime stats through a remote MCP endpoint.
Enables MCP clients to query Oura Ring health data, including sleep, readiness, HRV, activity, and SpO2, through OAuth2-authenticated tools running on Cloudflare Workers.
Enables users to search grocery products and stores, manage a cart, sync purchase history, and predict needed items through MCP tools. It also stores food preferences as server instructions so connected agents can respect them automatically.
Checks which .env, .git, keys and source maps Cloudflare Pages, Vercel, Netlify or Firebase would publish, before and after deploy. CLI, live probe, Claude Code hook, MCP server and GitHub Action.
Enables MCP clients to access Chakudya Nutrition Registry data through a stateless Streamable HTTP transport, with bearer token or OAuth authentication.
Cloudflare MCP server with multi-user credential management, full Cloudflare API coverage, and schema discovery tools for safe LLM-driven Cloudflare resource management.
A template for deploying MCP servers on Cloudflare Workers with OAuth authentication, enabling remote access to MCP tools via SSE transport from Claude Desktop and other MCP clients.
Enables finding information online, reading web pages, finding images, capturing screenshots, and performing multi-source research with per-answer confidence.
Provides AI assistants with current Ionic Framework v9 and v8 documentation, including component API references, usage examples for Angular, React, Vue, and vanilla JavaScript, and Ionic blog posts. Enables searching docs, reading pages, listing components, retrieving usage examples, and listing blog posts.
MCP server that verifies scraped web data by re-fetching source pages and returning ed25519-signed pass, fail, or unverifiable verdicts, with x402 in-band payment.
Lets AI agents query, search and read wiki pages and raw transcripts of past coding sessions, so they can look up prior decisions and fixes before redoing work. It also exposes linting, sync, export and dashboard tools over stdio, with path-traversal guards and no SDK dependency.
Read-only MCP server for Grafana Loki: lets AI agents (Claude Code, Cursor, Copilot) discover labels, read bounded LogQL pages, count lines by label or time, and export logs — across several Loki stands
Rust-powered PDF toolkit over MCP: create, read, and analyze PDFs; extract text and entities for RAG; convert to Markdown; split/merge/rotate/reorder pages; manage form fields and annotations; encrypt documents. Runs locally via uvx oxidize-mcp.
Extracts people (names and titles) from a company's team, leadership, or about page given a domain. Uses Apify to crawl and return structured data, with optional filters for seniority and email inclusion.
Enables AI agents to extract clean LLM-ready markdown and readable articles from web pages, parse metadata, tables, links, feeds, and contact info, audit paywalls, SEO, and XSS, and access these tools via Streamable HTTP or a stdio bridge.
Deep Research infrastructure for AI agents. Search the web, read pages incrementally, follow source links, and collect relevant evidence across multiple sources. Web search runs through your own SearXNG instance, while the agent remains in control of research planning and reasoning. Cluefinch runs locally over MCP stdio.
Offline PDF tools from the LaserPDF desktop app: extract and search text, OCR scanned pages (English and Turkish), redact text so it is removed from the file, remove hidden metadata, export tables to Excel, and merge, extract or rotate pages.
Enables AI agents to fetch any public web page as clean Markdown, retrieve page metadata (title, description, canonical URL, OpenGraph/Twitter cards, JSON-LD), and crawl a page plus up to four linked same-site pages. Calls are paid per use in USDC via x402/MPP with no API key or account, and invalid inputs or unfetchable pages are never charged.
PageSift is an open-source Rust MCP server that crawls websites and extracts clean Markdown and structured content from web pages, PDFs, and Office documents. It supports adaptive rendering, query-focused crawling, and batch extraction for AI agents and RAG pipelines.
Provides AI agents with a local, private Markdown-based memory vault and SQLite search. Enables agents to search, read, list, and traverse linked knowledge pages via MCP with zero external runtime dependencies.
Enables users to plan, write and launch WordPress webinars entirely from a chat with any MCP-compatible AI client — including topics, titles, invitation emails, reminders, registration pages, live rooms and evergreen funnels. It works standalone for drafting content, or connected to a WebinarIgnition WordPress site where 71 read, write and destructive tools let an assistant build and run the real webinar with confirmation before anything changes.
Enables users to find brands that have sponsored creators in a niche within a recent date window, returning deduplicated brand rows and evidence-linked sightings from public YouTube descriptions, podcast show notes, newsletters, event sponsor pages, partnership jobs, and creator programs. It also surfaces public contact routes, promo codes, placement types, and pitch angles, with the work run through Apify.
Checks OpenAI, Anthropic and Google model IDs for retirement: status, retirement date, days left and replacement, from the providers' deprecation pages, re-checked daily. Can also scan a project folder for retired or retiring model IDs with file and line, and list what retires in the next N days. No API key needed.
Enables Claude Desktop, Cursor AI, Windsurf, and autonomous LLM agents to scrape, crawl, map, search, and extract validated JSON from live web pages with dynamic rendering, anti-bot bypass, and Markdown conversion.
An MCP server for the Library of Congress that enables searching scanned American newspaper pages, searching catalogue items by media type, reading individual records, and listing digital collections, all without requiring an API key or account.
Discover and invoke AI services on AIMarket with prices and signed receipts. Also fetch public web pages, search the web, and request Metis verification. Five tools over stdio or self-hosted HTTP; marketplace search needs no API key.
Enables AI agents to generate Korea Government Design System components and page templates with KWCAG 2.2 accessibility requirements built in, then validate rendered pages and block task completion until remaining accessibility violations are corrected.
Local, offline-first retrieval for agents over code, PDFs, and Office files. Returns exact citations (source lines, PDF pages, slides, sheet cells), combines BM25 and vector search, and refuses questions the sources cannot answer. CLI, stdio MCP server, and TypeScript API; works with Claude Code, Codex, LangChain, and LlamaIndex.
MCP server for Taiga project management, enabling LLM clients to inspect and manage projects, work items, sprints, comments, attachments, and wiki pages via 6 op-dispatching tools.
Enables natural language queries of the Chrome UX Report API to fetch Core Web Vitals (LCP, INP, CLS, FCP, TTFB), compare form factors, benchmark pages against site averages, and analyze up to 40 weeks of performance trends.
Enables querying GeoIP2, GeoLite2, and custom MMDB databases through the Model Context Protocol for IP lookups, filtered network queries, resumable pages, and MaxMind database downloads.
Uptime monitoring from your AI agent: create and diagnose checks (40 types: HTTP, TCP, DNS, SSL, ICMP, databases, message queues and more), read results and incidents, and manage status pages and maintenance windows. Built into the self-hostable SolidPing server, served over streamable HTTP at /api/v1/mcp.
Enables AI agents to convert files, render web pages to markdown/PDF/screenshots, search the live web, extract structured data, ingest RAG-ready chunks, and monitor pages for changes through a single API key.
Enables AI tools to publish HTML pages and get shareable URLs instantly, with optional account features for persistence, in-place updates, and visibility control.
Folio serves a folder of markdown and data files to the browser as live pages and keeps a model of the whole folder. Its MCP server gives agents read-only tools over that model: documents and their blocks, links, queries over data files, figures checked against their data, folder health, history and digests, and what the reader has read or has yet to catch up on.
Diff and sync configuration between two Shopify stores (metafield and metaobject definitions, metaobjects, collections, pages, menus, redirects, policies, translations) from Claude, ChatGPT, Cursor or any MCP client. Dry-run plans, handle-based ID remapping, never deletes.
Enables any AI agent to call websites and REST APIs as MCP tools through a config-driven, zero-dependency Cloudflare Workers gateway. Connectors map HTTP endpoints into type-checked tools with token-friendly responses, server-side secrets, and optional bearer auth.
Publish Markdown or HTML to a shareable link from your AI assistant, then list, inspect, update or delete your pages. Six tools cover publishing, page management and account usage. Connect through hosted Streamable HTTP with OAuth, or use an API key for headless clients.
Claude thinks, your GPU reads. A local sub-agent on your own GPU that takes the token-heavy work off Claude Code and Codex: browsing in your logged-in Chrome, reading many pages, and coding in your repo, from reading the codebase to fixing it on a new branch until your tests pass. Only the answer and its sources come back.
Enables agents to inspect app status, uptime, response times, incidents, and certificate/domain expiry; set up and manage monitors and status pages; and draft incident updates through authenticated MCP tools.
One MCP server holding a live session with every client's account at once, so one agent can read across a dozen businesses and write inside only the one you name. It forwards each provider's own MCP tools (Cloudflare, Vercel, Resend, Supabase, Linear, Notion, Sentry, Netlify and more) with that client's credentials, and adds deterministic DNS and email checks that never call a model.