Skip to content
MCP server

PlaywrightGen

Playwright tests written from the live page, proven by your editor AI, approved by people

Pricing
Freemium
Platforms
Web, API, vscode
Runs
Remotely
Version
1.0.0
Listing updated
1 day ago

About PlaywrightGen

PlaywrightGen is a freemium MCP server for developer tools. It runs as a hosted remote server, so there is nothing to install locally.

PlaywrightGen separates writing a test from deciding it counts. An assistant in Copilot, Cursor or Claude Code opens the real page in a remote browser, drafts a test from its actual buttons, fields and test attributes, replays it step by step and repairs failing locators until it passes. It then proposes the test with a signed receipt of the passing run, and only a person on the team can approve it.

The MCP server has sixteen tools covering requirements, test cases, approved automation, recent CI failures and release readiness. It can propose and submit code but has no ability to approve, accept, share or delete, and an agent gets exactly the rights of the person whose token it uses. The README adds that repairs may not weaken a test, and validators refuse focused tests, fixed sleeps and embedded credentials.

Free tools need no account, and the Workspace is in preview. A Team plan is listed at $19 per workspace per month with 60 AI operations a day. Approved code can open as a pull request, and daily checks can alert via Slack or Discord.

Install

Run in a terminal

claude mcp add --transport http playwrightgen https://playwrightgen.com/api/mcp

Add to Settings → Connectors → Add custom connector

https://playwrightgen.com/api/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "playwrightgen": {
      "url": "https://playwrightgen.com/api/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "playwrightgen": {
      "type": "http",
      "url": "https://playwrightgen.com/api/mcp"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "playwrightgen": {
      "serverUrl": "https://playwrightgen.com/api/mcp"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "playwrightgen": {
      "type": "http",
      "url": "https://playwrightgen.com/api/mcp"
    }
  }
}

Tools this server provides (16)

Taken from the project documentation; the running server may differ.

prove_playwright_test
Writes, runs and fixes a test until it passes or fixes run out.
plan_page_coverage
Proposes the tests a whole page needs for approval.
prove_page_coverage
Proves each approved test on the live page.
generate_playwright_test
Writes a draft from a described flow and the real page.
run_playwright_test
Replays a test on the live page and reports each step.
propose_requirement
Drafts a requirement for review.
propose_test_case
Creates a draft test case for review.
submit_playwright_code
Sends code for an existing test case.
list_requirements
Lists requirements with review status and verdicts.
get_requirement
Returns a requirement with its approved tests.
list_test_cases
Lists test cases with review status and version.
get_test_case
Returns approved steps and expected results.
list_approved_automation
Lists reviewed Playwright automation.
get_approved_automation
Returns the approved code.
list_recent_failures
Lists recent CI failures with output.
project_overview
Summarises coverage, regressions and blockers.

What it does

Tests from the real page
Builds locators from actual page elements instead of guessing.
Prove loop
Runs, fixes and reruns a test until it passes or fixes run out.
Human approval
Only a person can approve a proposed test; the agent cannot.
Requirement traceability
Links requirements to approved tests with review status and verdicts.
CI failure view
Lists recent CI failures with output.
Signed run evidence
Shares results as proof links or downloadable files.

Good for

  • Have an assistant write and verify a Playwright test for a page
  • Plan the full set of tests a page needs
  • Find requirements with no passing test
  • Collect release evidence for an audit

Pricing

Freemium, from $19 a month

Free tools; Team $19 per workspace per month

Prices change. Check playwrightgen.com before you buy.

PlaywrightGen FAQ

Does the agent approve tests?

No, the server can propose and send code but cannot approve, accept, share or delete.

What does the Team plan cost?

$19 per workspace per month, with 60 AI operations a day.

Do I need an account to try it?

The free tools need none; the MCP server uses a personal editor token from a workspace.

How many tools are there?

Sixteen.

Is PlaywrightGen free?

PlaywrightGen has a free plan, with paid plans for more usage or features. Paid plans start at $19 a month.

How do I add PlaywrightGen to Claude Code?

Run this command in your terminal: claude mcp add --transport http playwrightgen https://playwrightgen.com/api/mcp

What are the best alternatives to PlaywrightGen?

The closest alternatives to PlaywrightGen are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to PlaywrightGen

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ouroboros

    MCP server

    Spec-first layer that pins requirements and verifies results of AI coding agent work

    Runs locally
    • Open source
    • 6.4K GitHub stars
    • Developer tools