Skip to content
plugmcp
DirectorySkillsCategoriesBlog
EN/中文
Sign inSign up
Directory/com.playwrightgen
MCP serverOfficial registry

PlaywrightGen

Prompt → Playwright test generation. Component → Playwright test generation. Component → unit test generation

by com.playwrightgenv1.0.0GitHubWebsite
Power your agent

Add this server

The publisher's own URL. Not a PlugMCP endpoint.

Server URL
https://playwrightgen.com/api/mcp
Provider
Claude Code
claude mcp add --transport http com.playwrightgen-playwrightgen https://playwrightgen.com/api/mcp

Run in a terminal.

Claude Desktop
{
  "mcpServers": {
    "com.playwrightgen-playwrightgen": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://playwrightgen.com/api/mcp"
      ]
    }
  }
}

claude_desktop_config.json

Step-by-step: add this in Claude

Remote URL or a command on your machine? How the two installs differ

Run on PlugMCP

Host a copy with our keys and logs.

A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.

Launch
Related MCP

More like this

View more

  • Firecrawl

    firecrawl

    🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.

    7.6k starsRemotebatch-processingclaude
  • N

    Notion

    Official
    io.github.awkoy
plugmcp

Plug any tool into any agent. MCP servers for people who do not write servers. Gateway for volume, n8n for apps.

PlugMCP, 2026

Product
  • Browse
  • Install
  • Host your own
  • Voice mode
  • Browser
Directory
  • All MCP servers
  • Agent skills
  • Categories
  • New
  • Voice
  • Submit a server
Developers
  • Docs
  • Blog
  • What is MCP
  • What is WebMCP
  • Status
Company
  • About
  • Contact
  • Terms
  • Privacy
  • DPA
  • [email protected]

Token-auth Notion MCP: pages, databases, blocks, comments, files. Runs headless in CI and agents.

175 starsLocal

  • Context7

    upstash

    Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors

    63k starsRemotevibe-coding

    • Prompt → Playwright test generation. Component → Playwright test generation. Component → unit test generation

    Key features

    1. 01Prompt → Playwright test generation
    2. 02Component → Playwright test generation
    3. 03Component → unit test generation
    4. 04HTML / JSX → Playwright test generation
    5. 05API test generation
    6. 06URL analysis for more realistic browser flows

    Use cases

    1. 01Generate tests faster while building modern web applications
    2. 02Turn manual test ideas into automated Playwright coverage faster
    3. 03Create stable locators, reusable flows, and production-ready test suites
    Suggested
    • Firecrawl🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.
    • N
      NotionToken-auth Notion MCP: pages, databases, blocks, comments, files. Runs headless in CI and agents.
    • Context7Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors

    PlaywrightGen

    AI-powered Playwright test generation platform for developers, automation engineers, and SDETs.

    PlaywrightGen helps teams generate production-ready Playwright tests from prompts, components, HTML snippets, API descriptions, and page URLs.

    Features

    • Prompt → Playwright test generation
    • Component → Playwright test generation
    • Component → unit test generation
    • HTML / JSX → Playwright test generation
    • API test generation
    • URL analysis for more realistic browser flows
    • Multiple output styles: Fast, Clean, Production
    • Free / Pro product structure
    • Copy code and download output
    • Built with Next.js + OpenAI

    Example Use Cases

    Developers

    • Generate tests faster while building modern web applications

    Automation Engineers

    • Turn manual test ideas into automated Playwright coverage faster

    SDETs

    • Create stable locators, reusable flows, and production-ready test suites

    Tech Stack

    • Next.js
    • TypeScript
    • OpenAI API
    • TailwindCSS
    • Playwright
    • Cheerio

    Getting Started

    Install dependencies:

    npm install

    Phase 1A workspace foundation

    Checkpoint 2 adds the PostgreSQL schema and initial Prisma migration for the tenant-safe workspace. Checkpoint 4 synchronizes Clerk users, organizations, and organization memberships into those existing PostgreSQL models. Checkpoint 5 adds the server-only tenant authorization boundary, Checkpoint 6 adds tenant-scoped project and project-membership services with transactional Activity, and Checkpoint 7 adds the real database-backed workspace project list, creation, and overview experience.

    Suggested
    • Firecrawl🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.
    • N
      NotionToken-auth Notion MCP: pages, databases, blocks, comments, files. Runs headless in CI and agents.
    • Context7Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors

    No FAQ yet. Enrichment fills this from the README on the next crawl.

    Suggested
    • Firecrawl🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.
    • N
      NotionToken-auth Notion MCP: pages, databases, blocks, comments, files. Runs headless in CI and agents.
    • Context7Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors

    No tool list yet. Remote servers get one after the first health check.

    Suggested
    • Firecrawl🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.
    • N
      NotionToken-auth Notion MCP: pages, databases, blocks, comments, files. Runs headless in CI and agents.
    • Context7Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors

    The first V1 slice adds project-scoped Requirements, immutable RequirementVersion snapshots, explicit draft/review/approve/archive workflow, and real permission-aware Requirements routes inside each project.

    AI Requirement Review stores advisory, evidence-linked suggestions against one immutable version. Suggestions can be accepted or dismissed but never mutate Requirement content. OPENAI_REQUIREMENT_REVIEW_MODEL optionally overrides the default review model; OPENAI_API_KEY remains server-only.

    V1.3 adds versioned Test Cases with objective, preconditions, structured steps and expected results, review/approval, and direct Requirement traceability. Automation status is separate so future Playwright browser, API, and integration engines can create reviewable artifacts from approved versions.

    V1.4 adds Test Runs pinned to an approved TestCaseVersion. Manual, Playwright Browser, and API modes store environment/browser metadata and append immutable attempts with overall/per-step results, duration, failure details, and evidence links. Retrying creates another attempt instead of overwriting history.

    V1.5 adds advisory AI Failure Intelligence for failed and blocked attempts. It uses the OpenAI Responses API with Structured Outputs, validates every cited quote against immutable stored evidence, records model/prompt/schema/token metadata, and requires a Lead or Owner/Admin to confirm or dismiss findings. OPENAI_FAILURE_ANALYSIS_MODEL optionally overrides the default analysis model.

    Phase 1A uses these environment variable names:

    • DATABASE_URL: the PostgreSQL connection used by the application at runtime and by local development migration work when no direct connection is configured.
    • DIRECT_URL: the optional direct PostgreSQL connection preferred by Prisma migration commands when a pooled runtime connection is unsuitable.
    • TEST_DATABASE_URL: a physically separate PostgreSQL database used only by integration tests. It must identify a dedicated test database and never falls back to either development variable.
    • NEXT_PUBLIC_CLERK_PUBLISHABLE_KEY
    • CLERK_SECRET_KEY
    • CLERK_WEBHOOK_SIGNING_SECRET

    V1.8 GitHub setup additionally requires separate development/Preview values:

    • GITHUB_APP_ID, GITHUB_APP_PRIVATE_KEY
    • GITHUB_APP_SLUG, GITHUB_APP_CLIENT_ID, GITHUB_APP_CLIENT_SECRET
    • GITHUB_WEBHOOK_SECRET
    • GITHUB_SETUP_STATE_SECRET (at least 32 characters and distinct from every other secret)
    • NEXT_PUBLIC_APP_URL (the exact application origin used by the GitHub callback)

    The GitHub App is read-only during repository import: metadata and contents read, with only installation and installation_repositories webhook events. User and installation access tokens are transient and must never be logged or stored.

    Configure a Clerk Dashboard webhook endpoint at /api/webhooks/clerk and set CLERK_WEBHOOK_SIGNING_SECRET locally and in the deployment environment. Subscribe it to:

    • user.created, user.updated, user.deleted
    • organization.created, organization.updated, organization.deleted
    • organizationMembership.created, organizationMembership.updated, organizationMembership.deleted

    Local webhook delivery requires a secure tunnel to the local application. Do not place webhook secret values in documentation or source control.

    Reconcile one Clerk organization without writing by default:

    npm run clerk:reconcile -- --organization-id org_example
# or
npm run clerk:reconcile -- --slug workspace-slug

    After reviewing the dry-run counts, explicitly add --apply to write the scoped reconciliation. The command never sweeps all organizations by default.

    Database commands:

    npm run prisma:format
npm run prisma:validate
npm run prisma:generate
npm run prisma:migrate:dev
npm run test:database

    Never commit credentials, secrets, .env, or .env.local. Never run development migration or database reset commands against production from a developer laptop.