Skip to content
Agentmart
Submit a tool

PlaywrightGen

Approved test intent, reviewed Playwright automation and run evidence, inside your editor.

Connector by playwrightgen.comOfficial · Domain verified by the MCP Registry

IndexedLicense unknownRemote (HTTP)
Write a review

Install

Works with Claude Code, VS Code, Cursor, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install connector/playwrightgen-com-playwrightgen

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Remote endpoint

  • https://playwrightgen.com/api/mcp Remote (HTTP)

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Approved test intent, reviewed Playwright automation and run evidence, inside your editor.

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools
10 read · 6 write · 0 delete
Secrets
1 (API keys, tokens or passwords)
Install scripts
Nothing to install (hosted)
Runs as
Hosted (remote endpoint)

Tools by what they do 16

Read from the source code; the running server may list different tools.

Read 10 · Look things up without changing anything.

  • generate_playwright_test
  • get_approved_automation
  • get_requirement
  • get_test_case
  • list_approved_automation
  • list_recent_failures
  • list_requirements
  • list_test_cases
  • prove_playwright_test
  • run_playwright_test

Write 6 · Create, change, send or run things.

  • plan_page_coverage
  • project_overview
  • propose_requirement
  • propose_test_case
  • prove_page_coverage
  • submit_playwright_code

Secrets and settings it asks for

Secrets: values you paste in that let it act as you.

  • Authorization

Network hosts it talks to 1

  • playwrightgen.com · found in remote endpoint, install command

Tools (16)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • generate_playwright_testGenerate a Playwright testread-only

    Write a Playwright test draft for described behaviour. When pageUrl is a public page, PlaywrightGen opens it and builds locators from its real accessibility tree. Returns the code, the plan, and which locators could not be confirmed on the page. Uses one request from the workspace's daily AI allowance. Next, check it with run_playwright_test.

  • get_approved_automationGet approved automation

    The approved Playwright code for one automation artifact, ready to save into the repository unchanged, with any configuration and dependencies it needs.

  • get_requirementGet a requirement and its evidenceread-only

    One requirement: its review status, its verdict, why, and every approved test that verifies it with how that test last ran. Use it before writing a test, so the new one covers what is missing rather than what is already proven. Reads only; spends no AI allowance.

  • get_test_caseGet a test case

    The current version of one test case: objective, preconditions, steps, expected results, linked requirements, and the version marker to put in the Playwright test title.

  • list_approved_automationList approved automation

    Playwright automation in this project that a person has reviewed and approved, with the test case each one covers.

  • list_recent_failuresList recent failures

    The most recent failed or blocked test attempts in this project, with the failure output, so a broken test can be fixed against what actually happened.

  • list_requirementsList requirements and what verifies themread-only

    Every requirement in this project that is not archived -- approved ones and drafts alike, each with its review status -- and a verdict derived from stored records only: VERIFIED (an approved test last ran and passed), FAILING (one last ran and did not pass), or UNVERIFIED (nothing approved covers it, or nothing has run). Use verdict: "UNVERIFIED" to find what still needs a test. Reads only; spends no AI allowance.

  • list_test_casesList test cases

    Test cases in this project with their review status, current version and automation status. Approved ones are the agreed behaviour to test against.

  • plan_page_coveragePlan the tests a page needs

    Reads a public page (signed in, when env carries E2E_USERNAME and E2E_PASSWORD) and proposes up to six tests covering what a user can do there, leaving out risky actions such as payments. Returns the plan and a link: a person approves which tests to prove in PlaywrightGen, then prove_page_coverage proves them. Takes about a minute. Uses one request from the workspace's daily AI allowance.

  • project_overviewProject overview

    Release readiness for this project: whether any blocking condition was found in the recorded evidence, coverage counts, how old that evidence is, and every blocker and caution with its reason. It reports what the records show; it is not a judgement that the project is safe to ship.

  • propose_requirementPropose a requirement

    Creates a draft requirement in this project: what the product should do, and how somebody would know it works. Use it when the behaviour you are about to test has no requirement yet -- check list_requirements first. Write only what your source supports; do not invent behaviour to fill a gap, and say what is unsettled in the description instead. A person reviews and approves it; until then it counts as nothing.

  • propose_test_casePropose a test case

    Create a draft test case in PlaywrightGen for behaviour that has none yet, optionally with the Playwright code you wrote for it and optionally submitted for review. A person on the team reviews and approves it; nothing proposed here counts as approved coverage until then.

  • prove_page_coverageProve a page's approved tests

    For a plan a person has approved in PlaywrightGen: writes each approved test from the live page, runs it in a remote browser, fixes a failing step and runs again, and keeps each result on a draft Test Case for review. Proves as many as fit in about two to four minutes; call again until the status is DONE, which returns the proven suite. Before approval it only reports the status. Uses up to three requests from the daily AI allowance per test.

  • prove_playwright_testWrite a Playwright test and make it passread-only

    The whole loop in one call: write a test for described behaviour from the real page, run it in a remote browser, fix the failing step from the page as it was, and run again until it passes or the fix budget runs out. Returns the code, what happened in each round, and a runReceipt when it passed, which propose_test_case accepts as evidence. Uses one request from the workspace's daily AI allowance, plus one per fix.

  • run_playwright_testRun a Playwright test on the live pageread-only

    Replay a Playwright test step by step in a real remote browser against a public page, and report which step failed, why, and the page's accessibility tree at that moment so the locator can be fixed. The code is read into safe Playwright steps, never executed as code. Pass env for process.env values the test reads, such as a test account; they are used for this run only. A passing run returns a runReceipt to give submit_playwright_code. Uses one request from the workspace's daily AI allowance.

Show 1 more tools
  • submit_playwright_codeSubmit Playwright code for a test case

    Attach the Playwright test you wrote for an existing test case. It waits on the test case in PlaywrightGen until a person turns it into a reviewed automation version; it replaces code sent earlier that has not been used yet. Keep the test case's version marker in the test title.

Signals

Stars
0
Forks
0
Open issues
0
Last commit
Oct 19, 2026 (9 days ago)
Last release
Sep 20, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

Registry name
com.playwrightgen/playwrightgen
Version
1.0.0
Auth
Bearer token
License
License unknown
Repository
github.com/hmamut39/playwrightgen
Website
playwrightgen.com/mcp
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
Official MCP Registrygithub-graphql
Cite this page

PlaywrightGen MCP server. Agent Mart. https://agentmart.dev/connectors/playwrightgen-com-playwrightgen (last updated 2026-10-24)