MCP servers and skills: search, filter by where they run, and compare.
Nothing matches every word exactly, so these are the closest matches.
Writing and run Enterprise-grade E2E tests automatically with claude and Playwright
SkillMIT★ 1Few starsNo key
AI-assisted QA pipeline with traceable test cases, Playwright E2E and Postman/Newman API checks, schema validation, and four human review gates.
SkillMIT★ 1Few starsNo key
Extract any website's complete design system with one command. DTCG tokens, semantic+primitive+composite, MCP server for Claude Code/Cursor/Windsurf, multi-platform emitters (iOS SwiftUI, Android Comp
Node.jsMIT★ 4.3kNo key
Resolve WoRMS marine species names; fetch classifications, synonyms, distributions, traits, and IDs via MCP. STDIO or Streamable HTTP.
Node.jsApache-2.0Few starsNo key
Complete browser tasks with Ego Lite and actively call Jev for semantic target selection, filtering, ranking, classification and text evidence judgments.
SkillMIT★ 2Few starsNo key
AI-native test framework for QA teams — fetch a ticket from Jira or GitHub Issues, generate Gherkin + Playwright spec, run the test, diagnose the failure, and post results back to the tracker. Driven
SkillApache-2.0★ 6No key
FORGE sits between developer intent and an AI coding agent. Instead of making the model spend paid reasoning time rediscovering a repository, FORGE performs repeatable local preparation first: reposit
Node.jsApache-2.0★ 2Few starsNo key
Search and explore 1.8M+ US nonprofits, fetch Form 990 financials, and access IRS filing history via MCP. STDIO or Streamable HTTP.
Node.jsApache-2.0★ 2Few starsNo key
Agent skill + zero-dependency TypeScript CLI for pushing text or HTML notifications to MeoW nicknames (api.chuckfang.com)
SkillMITFew starsNo key
AI-Native Quality Engineering Lab with MCP, Playwright, Open Banking APIs, local LLMs, Golden Dataset, LLM evaluation and CI/CD Quality Gates.
SkillMIT★ 1Few starsNo key
Evaluation-first AI systems for Claude Skills, browser automation, and SEC 10-K extraction.
SkillMIT★ 1Few starsNo key
Local MCP server that drives Adobe Firefly through Playwright browser automation.
Node.jsMIT★ 1Few starsNo key
Evidence-based website scanner for what AI agents can read, answer, and call—validating MCP, WebMCP, APIs, and crawler access.
SkillAGPL-3.0Few starsNo key
Playwright end-to-end testing MCP server — run, debug and inspect E2E tests from any AI agent: failure analysis, live DOM inspection, selector validation, visual diffs, flaky-test diagnosis.
Node.jsMITFew starsNo key
How to use the `@gate` / `@force-gate` test directives instead of `it.skip` or fake-green skip patterns. Use when a test is known-failing under some test-matrix dimension (dev mode, a bundler, an expe
OfficialSkillMIT★ 143k in collectionNo key
Debug LLM applications using the Phoenix CLI. Fetch traces, analyze errors, structure trace review with open coding and axial coding, inspect datasets, review experiments, query annotation configs, an
OfficialSkillApache-2.0★ 40k in collectionNo key
Build and validate experimental WebMCP tools for an existing web page. Use when an agent needs to expose a site's real workflows as page tools, create webmcp.init.js, define deterministic checks, or c
OfficialSkillApache-2.0★ 44k in collectionNo key
Implement, configure, and secure Sign In With Google (SiwG) using Google Identity Services (GIS / `https://accounts.google.com/gsi/client`) across web architectures. Use when creating Google sign-in b
OfficialSkillApache-2.0★ 21k in collectionNo key
MCP server that diagnoses and fixes failing Playwright tests: trace analysis, verified locator fixes, per-test flaky verdicts, GitHub Action.
Node.jsMITFew starsNo key
MCP server for unpacking and analyzing Playwright trace.zip archives
Node.jsMIT★ 1Few starsNo key
Use Hugging Face Hub via MCP server tools. Search models, datasets, Spaces, papers. Get repo details, fetch documentation, run compute jobs, and use Gradio Spaces as AI tools. Available when connected
OfficialSkillApache-2.0★ 11k in collectionNo key
A procedural Agent Skill that teaches custom-provider models how to discover, use, verify, and recover from Claude Desktop/Cowork-style tools and workflows
SkillMIT★ 37No key
Open-source, self-hosted alternative to OpenAI Dots, Grok Bot. Built to be undetectable by anti-bot systems.
SkillMIT★ 32kNo key
AI-driven network-first crawler compiler for authorized workflows
Node.jsMIT★ 2Few starsNo key
Who stands behind it
