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.
A service that enables rapid deployment of HTML content to EdgeOne Pages and automatically generates publicly accessible URLs for the deployed content.
This read-only MCP Server allows you to connect to OneNote data from Claude Desktop through CData JDBC Drivers. Free (beta) read/write servers available at https://www.cdata.com/solutions/mcp
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.
MCP server that parses web pages into clean markdown via Crawl4AI's HTTP API, exposing parse_page and health-check tools with configurable proxy and timeout.
Provides a local MCP server that exposes the check_prompt_injection tool to MCP clients, letting agents scan untrusted text (web pages, documents, tool outputs, emails) for prompt injection before passing it to another LLM.
Enables browser automation through Surfsky's cloud-based antidetect browser, allowing users to scrape pages, navigate and interact with websites, run JavaScript, take screenshots, and manage isolated sessions with custom profiles, proxies, and fingerprint settings.
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.
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.
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 that keeps raw tool output out of the context window by sandboxing and compressing results (about 98% reduction), persisting file edits, git operations, tasks and decisions in SQLite with BM25 retrieval so the agent resumes after compaction, and enforcing routing across 17 platforms via MCP and hooks. It also encourages the model to write scripts that compute answers and log only results instead of reading large data into context.
MCP server that exposes pre-extracted facts about code behavior, design decisions, and assumptions to AI agents, saving time and tokens by avoiding direct source file reading.
MCP server for the Tecof Developer API that reads theme components from disk, converts agent-written sections into editor documents, and manages draft pages (create, update, delete, preview) with validation and multi-language support.
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.
A hardened, self-hosted MCP server that lets AI agents query and govern an Infraveil control plane in-loop, reading state and filing deploy/remediation requests that require human approval.
Enables AI tools to publish HTML pages and get shareable URLs instantly, with optional account features for persistence, in-place updates, and visibility control.
Enables converting web pages to clean Markdown via MCP, compressing token usage by roughly 95% in under 150ms to support LLM context windows and RAG pipelines.
Public Facebook & Instagram data for AI agents: pages, groups, posts, comments, search, Meta Ads Library, Marketplace, media downloads, Instagram profiles, posts, reels and locations. 12 read-only tools, 51 operations. Hosted at mcp.socialapis.io/mcp or npx @socialapis/mcp. Free tier with 200 requests/month, plans from $4.99/month.
Enables coding agents to independently verify web changes by scanning pages, inspecting UI structure, generating Playwright reproductions, and executing tests with structured QA evidence.
Enables AI assistants to capture website screenshots and record videos of web pages by providing tools for taking screenshots, recording videos, and checking video status.
AutomateLab AI-SEO audits, scores, and rewrites web pages for AI citation eligibility, AEO and GEO. No API keys or registration. Works with Claude, Cursor, Codex, and other MCP clients. Product and documentation: https://automatelab.tech/products/mcp/ai-seo/
A stdio proxy to Jober's remote MCP server that enables AI tools to turn pasted text into KakaoTalk AlimTalk or email campaign drafts, attach custom links or survey landing pages, register recipients, and send or schedule messages while tracking delivery results. It also reports send readiness such as channel connection, quotas, and quiet-hours rules before sending.
Enables AI agents in Claude Code, Claude Desktop, Cursor, VS Code, Windsurf, Gemini CLI and Codex to scrape web pages into Markdown, text, HTML, JSON or PDF, extract structured data with selectors or autoparse, capture screenshots and PDFs the model can see, drive pages with typed browser actions, keep logged-in persistent browser sessions, and batch-scrape thousands of URLs as async jobs. It also exposes usage, request-log and documentation tools so agents can check costs, diagnose failures and look up parameters without leaving the chat.
Scans live web pages and single-page apps across multiple viewports to detect WCAG 2.1 AA accessibility violations and returns concrete, browser-verified fixes grounded in WCAG success criteria and techniques.
MCP server that enables Claude Code to drive the Konsulto cybersecurity audit platform from the CLI, including reading and writing findings, managing evidence, and handling scope and assets.
Enables assistants such as Claude Code, Codex, and Gemini CLI to drive a real browser over MCP — navigating, clicking, typing, and reading live pages from plain-English instructions. Supports optional proxy routing, persistent profiles for surviving logins, and reproducible browser identities via seeds.
Enables AI assistants to retrieve WOP integration guides and API details, fetch documentation pages, and generate RSA2048 or SM2 key pairs while keeping private keys safely on disk and never exposing them in conversation.
EU-native web scraping for AI agents & developers.
scrape web pages into markdown, screenshots, metadata, and links, map sites, run asynchronous scrape jobs, and check usage, with EU-hosted, GDPR-aligned processing.
Enables AI agents to browse web pages, see a compact semantic digest and typed diff after each action, and verify changes with assertions over that diff.
Official MCP server for ScreenshotAPI: capture website screenshots, convert URLs and HTML to PDF, record scrolling videos, scrape JavaScript-rendered pages as Markdown, text, or HTML, and run bulk captures.
Enables MCP clients to read local PDFs as markdown, plain text, tables, or positioned blocks; inspect metadata; search documents; list and fill form fields into new files; and identify pages needing vision, while keeping documents on-machine and limiting access to allowed directories.
Enables AI agents to read any web page as clean Markdown, pull title/description/preview metadata, capture desktop, mobile, or full-page screenshots, and list every link or image on a URL. JavaScript-heavy pages are rendered in a real browser and blocked requests retried through a proxy, so agents can reach content they'd otherwise miss.
Enables reading and writing the rollekino.fi film archive, including search, film details, stats, and reviews with personal 1-10 ratings alongside IMDb and Metascore.
Enables AI agents to take part in a timed compliance challenge by reading corpus resources through a Trust Layer proxy that returns signed receipts, then submitting assertions paired with the receipts that back them. It also creates and stores the agent's identity keys locally, enrolls it in the season, and after closing returns the published report with computed overclaim and success rates.
Enables AI coding agents to audit web pages for WCAG accessibility and color-contrast issues, and file dev-ready issues directly into OverlayQA projects.
Lets AI assistants crawl sites or load exported crawl data, then query SEO issues, inspect individual pages, and trace broken internal links from real crawl results. It supports live same-origin crawls up to 200 pages and exported datasets for deeper analysis.
Enables AI agents to fetch bot-protected web pages, run structured Google searches, and check domain authority through UnblockingAPI's anti-detection engine and residential proxies.
Enables an AI agent to host a shared folder or join an invite link as a participant in a collaborative editing session, reading, editing, and writing the files the room shares. Runs the same sync engine and wire protocol as editor clients, so an agent and a person or another agent converge on the same documents and see each other's changes.
Lets an AI assistant drive a self-hosted Sn1per install over local stdio, launching orchestrated scans and reading back structured findings, ports, subdomains and technologies. Enforces configured target scope, redacts secrets, and writes an audit log of every scan, cancel, delete and export request.
Enables AI assistants to list a user's connected sites and pages, check whether URLs are indexed by Google, queue Request indexing clicks through the user's own Search Console, follow and cancel those requests, and submit URLs to Bing and other IndexNow engines.
Cold plunge, sauna and contrast-therapy venues across 23 US metros (548 venues). Every published water temperature and price is read from the venue's own pages and returned with its source URL, capture date and verbatim quote; every record carries the date it was last checked. Absent fields mean "not published", never zero. Five read-only tools: search_venues, get_venue, list_cities, get_city_stat
Statistics of Russian texts as tools for LLM agents, built on the ruTS library: readability with school grade and reader age, officialese, SEO metrics, verse meter and rhyme, lexical diversity, morphology, syntax, keywords, concordance, collocations and stylometric comparison. Every value comes with a description, a scale reading and warnings when it is unreliable for the text
Local-first personal wiki and memory server for AI agents. MCP clients can capture knowledge, retrieve context, read and maintain source-backed wiki pages, and carry project context between sessions.
Agent-native MCP server for Carly, the AI scheduling assistant. Exposes 11 tools to read and manage booking pages, event types, calendars, bookings, and available slots. Allows you to manage and create booking pages from the command line.
Enables an LLM to search and read a self-hosted media library over its HTTP API — videos and captions, archived web pages, ebooks and documents, Zim encyclopedias, maps, tags, inventories, and the download queue. It runs read-only on your own computer and returns links back into the web app.
Enables read-only search across EKKE course repositories, GitHub Discussions, and official university pages, returning source links and dates where available. Supports Hungarian-English query expansion and configurable response labels without restricting searches to one language.
Enables LLM agents to read and navigate web pages efficiently with token budgets, extract structured data, and optionally control a browser with explicit user consent, remaining read-only by default.