Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
bun-uia
MCP serversPlaywright for the Windows desktop, from Bun — drive native GUIs via UI Automation + MCP.
bun-uia@1.9.1 -
vew-mcp
MCP serversBrowser MCP: drive a real Chromium via Playwright with compact ref-addressable page snapshots
@yawlabs/vew-mcp@0.4.3 -
clipacanvas
MCP serversRender HTML, CSS, SVG, and Canvas animations to MP4 locally via Playwright/Chromium and FFmpeg.
clipacanvas-mcp@1.0.2 -
mantis
MCP serversThe web as short, numbered text for AI agents: a lean browser interface over Playwright.
mantis-browser@0.1.14 -
PageMap
MCP serversStructured web intelligence for AI agents. 5x fewer tokens than Playwright/Firecrawl, 84.7% accuracy
retio-pagemap@0.7.3 -
Aether WCAG Scanner
MCP serversWCAG 2.1 AA accessibility scanner (Playwright + axe-core) with grounded, browser-verified fixes.
@allchemylabs/aether-wcag-scanner@1.0.8 -
Terminal MCP Server
MCP serversMCP server for AI agents to interact with terminal applications. Think Playwright for terminals.
mcp-server-terminal@1.0.3 -
OneTool MCP
MCP serversOne MCP for devs incl Brave,Google,Tavily,Context7,AWS,Excalidraw,DB,GitHub,DevTools,Playwright
-
cowork-qa
MCP serversGoal-driven Playwright browser sessions for LLMs, with full action traces and aria-snapshots.
cowork-qa-mcp@0.1.1 -
rea-captcha
MCP serversSafe same-session CAPTCHA handoff and fresh-evidence resume for Browser Use and Playwright agents.
rea-captcha@0.3.1 -
qualien-mcp
MCP serversMCP gateway for QA/SDET work: Playwright, files, GitHub, Jira, Postgres & more in one connection.
qualien-mcp@0.6.2 -
browser-devtools-mcp
MCP serversPlaywright browser & Node.js MCP. ARIA refs, screenshots, ref-based interactions.
browser-devtools-mcp@0.9.1 -
HTML to Markdown MCP Server
MCP serversConverts HTML to Markdown with auto-summary and section extraction. Supports Playwright.
docker.io/sunshad0w/html2md-mcp -
Test Card Hub
MCP serversSandbox test cards, Playwright tests, real-card scanner and decline codes for LATAM gateways.
test-card-hub-mcp@1.1.0 -
QAMap
SkillsLocal pull-request review brief for coding agents: the diff, the tests and callers of changed code, and change signals in one report. No LLM call, no upload. Claude Code used 44% fewer tokens with it on 42 public PRs.
git clone https://github.com/IvoryCanvas/QAMap.git -
Vedha
MCP serversBrowser testing on Playwright that checks the server, not just the screen, before it reports a pass.
@vedhajs/mcp@0.1.2 -
Endform
MCP serversFind failing, flaky, and slow Playwright tests on Endform and keep your suite healthy as it grows.
endform@0.83.2 -
Vibe Test — Browser Testing Agent
MCP serversCode-aware browser testing agent — 14 Playwright tools for AI code editors via MCP
vibe-testing@0.5.0 -
five46
MCP serversBYOK, fully local AI agent that tests your app/API and writes a real Playwright spec on success.
five46@0.2.3 -
flakiness-knowledge-graph-mcp
MCP serversMCP server + Playwright reporter that builds a flakiness knowledge graph from test run history
flakiness-knowledge-graph-mcp@0.2.2 -
periscope-mcp
MCP serversWeb-app QA for AI agents: 73 Playwright tools — auth, E2E, a11y/SEO/GEO, Web Vitals + Lighthouse
-
sitelooper
MCP serversRecord a browser flow once with a model, then compile it to a Playwright spec that needs no model.
sitelooper@0.7.0 -
Link-in-Bio-with-MCP-Server
MCP serversPersonal link-in-bio page on plain PHP 8.5: one JSON tree renders EN/RU pages, SEO, JSON-LD and the sitemap. An MCP server edits links over HTTP - token auth, atomic writes, backups. nginx + PHP-FPM, no framework, no build step, 100% line coverage.
git clone https://github.com/MADEVAL/Link-in-Bio-with-MCP-Server.git -
motion-film-skill
SkillsTurn a report, a deck or a product into a voice-led motion film, written in code by your AI agent. Skill for Claude Code, Codex and any agent: AI voiceover, beat-synced animation, captions, critic rounds, 60 fps 16:9 + 9:16.
git clone https://github.com/tonyprots/motion-film-skill.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.