"How to obtain an API key" matching MCP servers:

MyChart MCP Server

Enables free web searches using DuckDuckGo results without requiring API keys or authentication, returning structured titles, URLs, and descriptions with a configurable result limit.

A local-first, no-API-key MCP server that enables LLMs to search the web, fetch pages, and read documents using multiple engines and smart fallbacks.

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.

Fetches a URL and returns the main content as clean Markdown, using plain HTTP when possible and headless Chromium for JavaScript-rendered or bot-protected pages.

Enables AI agents to check a list of websites by running an Apify Actor through one tool, returning per-site tech stack, on-page SEO issues and score, robots.txt rules for AI crawlers, sitemap, llms.txt presence, and an AI-readiness score. Supports local stdio operation with an Apify token for tool calls.

An MCP server that provides web search powered by DeepSeek's native search API, returning AI-generated answers with source links. Integrates with MCP-compatible clients like Claude Code and Cursor.

Screen-reader navigation cost analyzer. Measures how hard it is for assistive-technology users to discover, reach, and operate interactive targets on the web.

Enables web searches through DuckDuckGo without an API key and extracts readable main content from web pages.

Provides web access tools (fetch, search, sitemap crawl) through String AI's API, automatically handling anti-bot bypass, CAPTCHA, and JavaScript rendering.

MCP server that converts web page URLs to Markdown via the Zyla API.

Enables any MCP-compatible LLM to perform AI-powered web research using Google's AI Mode, returning synthesized and cited answers instead of raw search results.

MCP server for publishing articles to Toutiao (今日头条) via browser automation, featuring QR code login and no API key required.

Audits AI-bot visibility: robots.txt per-bot for 22 AI user-agents (GPTBot/ClaudeBot/PerplexityBot/etc), Cloudflare flags, JSON-LD, sitemap, llms.txt, SPA shell, plus cross-model brand mentions via Perplexity + OpenRouter. 0-100 score. SSRF-guarded, spend-capped.

Gives MCP-capable agents live web access: search the web, scrape pages into Markdown (including JavaScript-heavy and bot-protected sites), and extract named fields as JSON, with job polling, token-aware content offloading, and built-in research guidance. Ships as a self-hostable stdio or HTTP service with spend caps and per-request key support.

Provides agent-friendly web search via MCP with zero-config free engines, region-aware failover, freshness filtering, and a one-call research tool that searches, fetches, and summarizes pages.

Connects AI assistants to Querit for live web search and clean webpage content retrieval, supporting both anonymous access and bring-your-own-key authentication.

Give it a product and a country and it searches Google for manufacturers, wholesalers, and distributors, reads each candidate company's own website, and returns only the ones whose pages back up the claim, with quoted evidence, the domain, and a confidence score. Directories, marketplaces, and social networks are filtered out, and a free summary row reports how many sites were found and checked when nothing qualifies.

Model Context Protocol server exposing the SCOUTS-AI web search API as a single web_search tool for AI agents. No API key required.

Turns any web page into structured data without an LLM or API key: reads the JSON-LD, microdata, RDFa, OpenGraph and other data a page declares, with where each value came from, and returns clean markdown or extractors learnt from examples. Obeys robots.txt.

Enables terminal AI coding assistants to interact with web AI chat services through browser automation, supporting multiple platforms like Doubao and ChatGPT.

Fetches and analyzes website content to provide business context to AI agents, designed for Voice AI in GoHighLevel.

Free open-source CLI and read-only MCP tool from Advisors AI (advisorsai.ai): give it one public URL and it lists which machine-readable basics are present or missing (title, meta description, structured data, one h1, canonical, robots policy for AI crawlers, llms.txt, sitemap). No API key, no account, nothing stored.

Enables AI assistants to search Perplexity.ai through browser automation without an API key, returning answers with cited sources.

AI-native web scraper: scrape, crawl and map any site to clean markdown over stdio. MIT-licensed.

MCP server for DuckDuckGo web search, enabling AI agents to perform real-time text, news, and image searches without an API key.

Provides TinyFish's free web, news, and academic search plus URL-to-markdown content fetching via a lightweight API-key-secured MCP server with no OAuth flow.

Enables MCP clients to search the web through DuckDuckGo, Google News, and Wikipedia, and to fetch readable text or pretty-printed JSON from web pages without API keys, accounts, or configuration.

Zero-Config, Fully AI-Managed End-to-End Testing for all code gen platforms.

Exposes three read-only MCP tools that let an assistant check whether specified AI crawlers are allowed by a site's robots.txt and how a URL responds when fetched with each bot's user-agent, fetch a page as a single named bot, and generate a robots.txt that welcomes AI crawlers.

An MCP server for web content extraction, providing tools to fetch clean text, extract links, query by CSS selector, and search the web via DuckDuckGo.

Reads a small-business website like a customer would and shows where they get stuck. Every AI answer has to quote the page, and the server checks the quote before it counts.

MCP server for scraping images from DuckDuckGo and Google Maps place photos without API key.

An MCP server that orchestrates structured multi-round debates between ChatGPT Web and Gemini Web in the same Chrome browser via CDP, requiring no API keys.

Enables agent runtimes to look up, classify, and fetch Hermai schemas as MCP tools, including read-only data retrieval via hosted endpoints (with optional API key).

Enables web search, page fetching, and search statistics for Claude Code and any MCP client without requiring an API key, using automatic provider fallback and caching.

Enables read-only buyer-side searches of live Avito listings for used PC components, inspection of full listing cards, and side-by-side comparison of exact offers, defaulting to Yekaterinburg without an Avito account or API key.

Connects AI assistants to web page content and Google search results, enabling them to retrieve HTML, Markdown, or screenshots from a URL, run Google queries, and check account plan and token usage. It supports hosted OAuth sign-in as well as local and self-hosted deployments with an API key.

An MCP server that gives an agent a remote browser:

Enables AI assistants to check Proxy302 account usage, browse countries, regions and plans, obtain rotating residential proxy URLs, list dynamic proxies and static IPs, and fetch web pages through a chosen country's exit. It is read-only and spend-free, handing proxy credentials to browsers or Playwright for JavaScript-heavy sites.