"Sage" matching MCP servers:

An MCP server that uses headless Chromium (Puppeteer) to capture pixel-perfect screenshots and extract DOM from URLs, with LLM-friendly step-based workflows.

Given a company domain, finds specified page types (like pricing or careers) on the company's own website and returns the URL, discovery method, and confidence score, optionally extracting structured data from the page.

Enables monitoring web pages for changes using Playwright, storing snapshots in SQLite, and optionally analyzing changes with an LLM for business impact assessment.

A Model Context Protocol server that enables LLMs to retrieve web content and save it to local files for permanent storage and later access.

Enables an AI agent to read and operate the Chrome or Edge tabs you are already using — titles, URLs, text, HTML, screenshots, clicks, typing, scrolling, and tab management — via a browser extension and native messaging, without restarting the browser, switching profiles, or opening a debug port. It exposes these capabilities as 19 MCP tools, with access limited to explicitly shared tabs and hardened by per-tab, origin-bound grants plus domain allow/deny lists.

Enables coding agents to scan a public URL in passive or authorized mode and receive only bounded, sanitized structured findings (severity, confidence, standard, evidence, remediation) with quarantined evidence instead of raw page dumps. A second tool lets agents inspect the scanner's safety boundaries and coverage without making any network request.

A lightweight MCP server for parsing HTML, fetching URLs, rendering terminal-style screenshots, and executing JavaScript on static HTML without external dependencies.

Provides Claude plan usage data (session and weekly percentages) as an MCP tool by reading through a logged-in browser, enabling Claude to check its own remaining usage.

Enables AI assistants to monitor web pages for content changes and receive alerts when changes occur.

Fetches any public web page and provides SEO foundation snapshots and prose readability analysis.

MCP server that fetches and renders dynamic web pages (SPA) using Chromium, returning content as Markdown or text. It uses lightweight HTTP first with automatic fallback to a browser for JS-heavy sites, and includes SSRF protection, login session support, and batch fetching.

Enables read-only retrieval of public web pages through MCP, with SSRF protection, no cookies or login state, and specialized anonymous parsing for Xiaohongshu, plus an opt-in Jina Reader fallback.

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.

Reads website pages and generates one cohesive image per page, with no text and no recognizable human faces.

Enables browser-based web page fetching with automatic cookie management and CSS selector extraction, supporting JavaScript rendering and authenticated sessions through a Chrome extension.

A content fetcher that sanitizes, size-caps, and caches fetched content, protecting against injection attacks via the Model Context Protocol.

An MCP server that automatically generates TypeScript Page Object classes and comprehensive Cypress test suites for any web page, supporting element interactions, workflow tests, and both positive and negative testing scenarios.

Enables rapid analysis of landing pages for SEO compliance, conversion structure, color contrast accessibility, and performance metrics with automated optimization suggestions and code snippets.

A local stdio MCP server that lets AI assistants run audits of generic HTML and Shopify product pages, gathering reproducible evidence on identity, structured data, images, links, specifications, and optional browser or link checks. It returns JSON and Markdown reports that the client can interpret, while keeping automated findings separate from checks requiring human judgment.