# k11 Playwright QA (npm · k11-playwright-qa-mcp)

User stories to verified Playwright tests, and self-healing locators with an audit trail.

- Trust score: 84/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- npm · `k11-playwright-qa-mcp`: 84/100 (this document), [markdown](https://verifymcp.io/servers/k11-software-solutions-playwright-qa/k11-playwright-qa-mcp.md), [page](https://verifymcp.io/servers/k11-software-solutions-playwright-qa/k11-playwright-qa-mcp)

## Channel facts

- Registry: `npm`
- Package: `k11-playwright-qa-mcp`
- Version: `0.3.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 31 of 94 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to K11-Software-Solutions/k11techlab-playwright-qa-mcp).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 4 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 79/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1170 tokens (~130/item across 9 items; 9 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 89/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 66% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 9 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 9 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the k11 Playwright QA MCP server?

k11 Playwright QA runs locally as an npm package, launched with npx -y k11-playwright-qa-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add k11-software-solutions-playwright-qa -- npx -y k11-playwright-qa-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "k11-software-solutions-playwright-qa": {
      "command": "npx",
      "args": [
        "-y",
        "k11-playwright-qa-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "k11-software-solutions-playwright-qa": {
      "command": "npx",
      "args": [
        "-y",
        "k11-playwright-qa-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add k11-software-solutions-playwright-qa -- npx -y k11-playwright-qa-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "k11-software-solutions-playwright-qa": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "k11-playwright-qa-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add k11-software-solutions-playwright-qa --command npx --arg -y --arg k11-playwright-qa-mcp
```

### Hermes

```yaml
mcp_servers:
  k11-software-solutions-playwright-qa:
    command: "npx"
    args: ["-y", "k11-playwright-qa-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "k11-software-solutions-playwright-qa": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "k11-playwright-qa-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add k11-software-solutions-playwright-qa -t stdio -c npx -a -y k11-playwright-qa-mcp
```

### Other

```json
{
  "mcpServers": {
    "k11-software-solutions-playwright-qa": {
      "command": "npx",
      "args": [
        "-y",
        "k11-playwright-qa-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-21 (score 84, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-18 (score 83, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-17 (score 82, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-16 (score 67, −14)

- [security regression] Malware scan: pass → unverified
- [functional regression] Schema quality: pass → fail
- [functional improvement] Tool coverage: 54% → 66%
- [functional] Package version: 0.2.1 → 0.3.0

### 2026-11-14 (score 81, +1)

No change was recorded against any check on this day. Stability & Change Management went from 0 to 3. That category is still filling its 30-day observation window: 0 days of observed history at the previous scan, 1 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-13 (score 80)

First indexed and scored.

## MCP tools (9)

### `explore_page` (~165 tokens)

Explore page

Open a URL in a headless browser (optionally with a saved login and/or steps to reach a deeper page) and list its meaningful elements with locators verified to match exactly one element, most stable first. Use these locators when writing tests instead of guessing selectors.

Input parameters:

- `device` (string): Emulate a device for mobile web: a Playwright device name such as "iPhone 15" or "Pixel 7" (list_devices), or "desktop" (default)
- `interactive_only` (boolean): Only buttons, links, inputs and other controls
- `max_elements` (integer)
- `session` (object): Reach pages behind a login or several steps into a flow
- `url` (string, required): Start URL (http, https or file)

### `check_locator` (~164 tokens)

Check locator

Check how many elements a Playwright locator matches on a page (1 = good) and whether the match is visible. Accepts the same session as explore_page.

Input parameters:

- `device` (string): Emulate a device for mobile web: a Playwright device name such as "iPhone 15" or "Pixel 7" (list_devices), or "desktop" (default)
- `devices` (array): Check on several devices at once, e.g. ["desktop", "iPhone 15", "Pixel 7"]
- `locator` (string, required): e.g. page.getByRole('button', { name: 'Sign in' })
- `session` (object): Reach pages behind a login or several steps into a flow
- `url` (string, required)

### `save_login_state` (~198 tokens)

Save login state

Log in once by running steps on a login page, then save the browser's cookies and storage to .qa-mcp/auth/<name>.json. Pass that file as session.storage_state to other tools, or to Playwright's storageState in tests. Put passwords in environment variables and reference them as ${ENV:NAME}; never pass them literally. The saved file contains session tokens: keep .qa-mcp/auth out of version control.

Input parameters:

- `device` (string): Emulate a device for mobile web: a Playwright device name such as "iPhone 15" or "Pixel 7" (list_devices), or "desktop" (default)
- `name` (string)
- `steps` (array, required)
- `success_locator` (string): Locator that must be visible after login, e.g. page.getByRole('heading', { name: 'My account' })
- `url` (string, required): Login page URL

### `parse_user_story` (~81 tokens)

Parse user story

Turn a user story (As a.../I want.../so that..., Gherkin scenarios, or acceptance-criteria bullets) into structured scenarios and a Playwright Test skeleton with one test per scenario and one test.step per step.

Input parameters:

- `story` (string, required)
- `url` (string): Start page, added as page.goto in beforeEach

### `write_test` (~65 tokens)

Write test file

Write a Playwright spec into the project's tests/ folder. Refuses paths outside tests/ and will not overwrite unless overwrite=true.

Input parameters:

- `code` (string, required)
- `overwrite` (boolean)
- `path` (string, required): Relative to tests/, e.g. login.spec.ts

### `run_tests` (~111 tokens)

Run Playwright tests

Run Playwright Test in the project and return per-test results. Failures include the error, its location and, when the cause was a locator, the locator Playwright was waiting for (pass it to heal_locator).

Input parameters:

- `grep` (string): Only run tests whose title matches
- `project` (string): Only this Playwright project from playwright.config, e.g. "Mobile Safari"; omit to run all projects
- `spec` (string): Spec file relative to tests/; omit to run everything

### `capture_baseline` (~152 tokens)

Capture locator baselines

While tests pass, record a fingerprint (role, name, test id, id, classes, text...) of the element each locator matches, saved in .qa-mcp/baselines.json under the page reached. heal_locator uses these after the UI changes. Accepts the same session as explore_page for pages behind a login.

Input parameters:

- `device` (string): Emulate a device for mobile web: a Playwright device name such as "iPhone 15" or "Pixel 7" (list_devices), or "desktop" (default)
- `locators` (array, required)
- `session` (object): Reach pages behind a login or several steps into a flow
- `url` (string, required)

### `heal_locator` (~180 tokens)

Heal locator

For a locator that no longer matches (or matches several elements), find the most likely intended element on the current page and suggest a verified replacement with a confidence score and reasons. Accepts the same session as explore_page. Never edits files: review the suggestion, update the test, then re-run.

Input parameters:

- `check_devices` (array): Also verify the suggestion on these devices, e.g. ["desktop", "iPhone 15"], so a mobile fix does not break desktop
- `device` (string): Emulate a device for mobile web: a Playwright device name such as "iPhone 15" or "Pixel 7" (list_devices), or "desktop" (default)
- `locator` (string, required)
- `session` (object): Reach pages behind a login or several steps into a flow
- `url` (string, required)

### `list_devices` (~54 tokens)

List devices

Device profiles for mobile web testing (Playwright's built-in list): phones and tablets with their screen size, pixel density and touch. Pass a name as device to explore_page, check_locator, capture_baseline and heal_locator.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/k11-software-solutions-playwright-qa/k11-playwright-qa-mcp#diagnostics

## Score history

- 2026-11-21: 84
- 2026-11-20: 83
- 2026-11-19: 83
- 2026-11-18: 83
- 2026-11-17: 82
- 2026-11-16: 67
- 2026-11-15: 81
- 2026-11-14: 81
- 2026-11-13: 80

## Common questions

### What is the k11 Playwright QA MCP server?

k11 Playwright QA is an MCP server listed in the public MCP registry as io.github.K11-Software-Solutions/playwright-qa. User stories to verified Playwright tests, and self-healing locators with an audit trail. This page covers its npm package (k11-playwright-qa-mcp).

### Is the k11 Playwright QA MCP server safe to use?

k11 Playwright QA scores 84 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the k11 Playwright QA MCP server expose?

k11 Playwright QA exposes 9 tools: explore_page, check_locator, save_login_state, parse_user_story, write_test, and 4 more. Their descriptions and schemas cost roughly 1,170 tokens of context every time the server is loaded.

### Is the k11 Playwright QA MCP server still maintained?

k11 Playwright QA is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the k11 Playwright QA MCP server under?

k11 Playwright QA declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

### What did VerifyMCP test on the k11 Playwright QA MCP server?

VerifyMCP ran 16 checks on k11 Playwright QA, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- npm package: https://www.npmjs.com/package/k11-playwright-qa-mcp
- Socket report: https://socket.dev/npm/package/k11-playwright-qa-mcp
- Repository: https://github.com/K11-Software-Solutions/k11techlab-playwright-qa-mcp
- Changelog RSS feed: https://verifymcp.io/servers/k11-software-solutions-playwright-qa/k11-playwright-qa-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/k11-software-solutions-playwright-qa/k11-playwright-qa-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/k11-software-solutions-playwright-qa/k11-playwright-qa-mcp.json
- HTML version of this page: https://verifymcp.io/servers/k11-software-solutions-playwright-qa/k11-playwright-qa-mcp
