"MCP servers from GitHub user smriti-AA" matching MCP servers:

Enables AI agents to drive a full Chromium desktop browser over MCP by reading structured accessibility-tree snapshots with stable element refs and token-saving incremental updates, then navigating, clicking, typing, selecting, scrolling, and extracting page text. It also supports tab management, console logs, screenshots, and HTTP traffic capture with request/response bodies and HAR export for API inspection.

Enables end-to-end testing of voice-enabled web applications by simulating a synthetic user with a virtual microphone, virtual speakers, a real browser, and a viewable display, allowing audio injection, speech capture/transcription, and browser automation.

Perplexity AI search, reasoning, research, and compute - MCP server, dashboard, and multi-IDE auto-config for VS Code.

This MCP server provides a unified search experience by integrating and intelligently fusing results from multiple major search engines. It automates complex processes like query language detection, weighted result ranking, and engine failover to deliver robust and high-quality search output.

Enables automated GitHub login through browser automation using Playwright. Provides MCP tools for programmatic authentication to GitHub accounts with credential management.

Enables AI agents to perform web searches and extract full-text content from web pages via standard MCP tools, with fallback search and semantic reranking.

Checks a website or local dev server with axe-core (WCAG 2.0/2.1 A and AA) and returns a fix prompt with real examples from the pages, for the AI tool to fix the source. Automated checks find roughly a third of accessibility problems.

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.

Enables MCP clients to read console logs and network requests from a connected mobile H5 page and, with explicit user authorization, execute JavaScript in that page.

MCP server providing free, IP-direct tools for web search, crawling, anti-detect browsing, and structured data from Wikipedia, Wikidata, GitHub, and YouTube.

Browser acceptance testing for AI agent deliverables: verify agent output in real Chromium from JSON specs, with MCP server, visual regression, multi-browser support and GitHub Actions.

A local-first MCP server for web search and documentation fetching, providing free DuckDuckGo search, URL-to-markdown conversion, and library docs from npm, PyPI, crates.io, Go, and GitHub with caching.

MCP server for internet access across Western and Indian platforms, enabling reading, searching, and hot content retrieval from stocks, news, hackernews, YouTube, GitHub, and more.

An MCP server that audits websites for accessibility (WCAG 2.1 AA/EAA), performance, SEO, design quality, and mobile responsiveness, providing actionable scores, grades, and prioritized fixes.

Enables AI agents to read data from Instagram, TikTok, YouTube, App Store, GitHub, Hacker News, Bluesky, Twitch, and Linktree through the ScrapingIsNotACrime public API.

A powerful Model Context Protocol (MCP) server for scraping Behance.net. Extract projects, user profiles, images, and job listings from Behance's creative community without any API keys or subscriptions.

Enables agents to verify real-world assertions like content being posted or PRs merged by fetching live evidence from URLs and GitHub, returning a verified boolean plus raw evidence.

Audits web pages for WCAG 2.2 AA accessibility aligned with the GOV.UK standard using axe-core and headless Chromium, returning structured JSON, markdown reports, and GDS compliance summaries.

An accessibility audit server that enforces WCAG 2.2 AA standards by running axe-core in a headless browser, providing violation details grouped by impact with fix hints.

Generates timesheets from activity data and automates submission to PSI Project Server (SharePoint-based systems) using browser automation. Works with Activity Collector MCP to fetch data from GitLab, GitHub, and Calendar services.

Enables solo developers to triage bounty and hackathon listings into GO, REVIEW, or SKIP verdicts backed by verbatim quotes from the listing, and to verify whether the opportunity is still open by checking linked GitHub issues or pages through the GitHub API and Tavily. It also maintains a persistent opportunity queue with liveness statuses, comparisons, submission plans, and daily briefings.

Enables searching, reading, and privately archiving news from supported publisher subscriptions, with per-user authentication via human sign-in links and separate tokens, sessions, and archives.

A Twitter/X MCP server powered by patchright (stealth Playwright fork) and a persistent Chrome user profile. It enables posting, engaging, searching, and managing tweets, threads, media, and user interactions via natural language.

WCAG 2.2 AA accessibility checks for a URL or for HTML the agent just wrote, run locally in headless Chrome. 31 checks with CSS selectors, snippets and fix guidance; the same engine as the A11yScope Chrome extension.

Deploys AI user personas to validate user journeys at scale, surfacing UX friction before real users encounter it.

Provides web search and content retrieval optimized for AI coding assistants, returning full conversations and structured content from StackOverflow, GitHub Issues, arXiv, and Wikipedia in a single call.

Enables AI agents to drive a real Chrome instance over the Chrome DevTools Protocol — opening and navigating tabs, reading compact YAML page outlines with refs, clicking, typing, scrolling, screenshotting, and evaluating scripts — with no browser extension or installed dependencies. It also audits pages for horizontal overflow and WCAG AA contrast, available both as an MCP tool and as a CI-friendly CLI.

Lets an MCP client list and read pages a user has explicitly shared from a running Firefox session, including visible job listings and recruiter conversations, and search for text within those pages. Access is read-only, granted per page for 30 minutes from the toolbar, and ends on navigation, reload, tab closure, revocation, or client disconnect.

A lightweight MCP server that enables LLMs to search the web via DuckDuckGo, search GitHub code repositories, and extract clean content from web pages in LLM-friendly formats.

Enables an external AI client to discover tender portal APIs, collect and verify tender listings, combine sections, and select relevant lots from a user request through local MCP tools.