Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

k11 Playwright QA

NPM · K11-PLAYWRIGHT-QA-MCP

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

+3 this week 84 Trust /100

Last scanned (16 hours ago)

Scores higher than 75% of npm servers

Category Testing and QA

Trust breakdown (7 categories)

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. How we score → Why this is hard to score →

Supply Chain Security98
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 31 of 94 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency97
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Cryptographically verified build provenance (signed, bound to K11-Software-Solutions/k11techlab-playwright-qa-mcp). View diagnostics → Pass
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 4 days ago).Pass
  • Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability79
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • 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. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management27
  • Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage89
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 66% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 9 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 9 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
What we tested

Checks we ran (16)

  • Malware scan
  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Security disclosure
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 21 Nov 26 +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.

  • 18 Nov 26 +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.

  • 17 Nov 26 +15
    • Malware scan: unverified → pass ▲ security
  • 16 Nov 26 −14
    • Malware scan: pass → unverified ▼ security
    • Schema quality: pass → fail ▼ functional
    • Tool coverage: 54% → 66% ▲ functional
    • Package version: 0.2.1 → 0.3.0 functional
  • 14 Nov 26 +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.

  • 13 Nov 26 80

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Analysed npm/k11-playwright-qa-mcp@0.3.0

Provenance Verified

A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.

Result Verified
Ecosystem npm
Reason Verified
Discovered via Registry attestation endpoint
Source repo K11-Software-Solutions/k11techlab-playwright-qa-mcp
Certificate issuer https://token.actions.githubusercontent.com
Certificate SAN https://github.com/K11-Software-Solutions/k11techlab-playwright-qa-mcp/.github/workflows/release.yml@refs/tags/v0.3.0
Rekor log index 3932168913
Predicate type SLSA build provenance https://slsa.dev/provenance/v1
Subject digest sha512:43496d77ec21b3c35bae16c9ccc40829c3772c3d6530021a9eb95a2ce7d59c54ebf6f7e04b86d728b2eb4ad7f5e9f20647bbf7cf426304de1bdfba714

Background: How many MCP packages publish verified provenance →

Dependencies 94 packages
Packages resolved 94
Stale 31
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 9 exposed · ~1,170 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
capture_baseline ~152

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.

NameTypeReqDescription
devicestring–Emulate a device for mobile web: a Playwright device name such as "iPhone 15" or "Pixel 7" (list_devices), or "desktop" (default)
locatorsarrayyes–
sessionobject–Reach pages behind a login or several steps into a flow
urlstringyes–

No output schema declared.

No examples provided.

check_locator ~164

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.

NameTypeReqDescription
devicestring–Emulate a device for mobile web: a Playwright device name such as "iPhone 15" or "Pixel 7" (list_devices), or "desktop" (default)
devicesarray–Check on several devices at once, e.g. ["desktop", "iPhone 15", "Pixel 7"]
locatorstringyese.g. page.getByRole('button', { name: 'Sign in' })
sessionobject–Reach pages behind a login or several steps into a flow
urlstringyes–

No output schema declared.

No examples provided.

explore_page ~165

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.

NameTypeReqDescription
devicestring–Emulate a device for mobile web: a Playwright device name such as "iPhone 15" or "Pixel 7" (list_devices), or "desktop" (default)
interactive_onlyboolean–Only buttons, links, inputs and other controls
max_elementsinteger––
sessionobject–Reach pages behind a login or several steps into a flow
urlstringyesStart URL (http, https or file)

No output schema declared.

No examples provided.

heal_locator ~180

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.

NameTypeReqDescription
check_devicesarray–Also verify the suggestion on these devices, e.g. ["desktop", "iPhone 15"], so a mobile fix does not break desktop
devicestring–Emulate a device for mobile web: a Playwright device name such as "iPhone 15" or "Pixel 7" (list_devices), or "desktop" (default)
locatorstringyes–
sessionobject–Reach pages behind a login or several steps into a flow
urlstringyes–

No output schema declared.

No examples provided.

list_devices ~54

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.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

parse_user_story ~81

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.

NameTypeReqDescription
storystringyes–
urlstring–Start page, added as page.goto in beforeEach

No output schema declared.

No examples provided.

run_tests ~111

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).

NameTypeReqDescription
grepstring–Only run tests whose title matches
projectstring–Only this Playwright project from playwright.config, e.g. "Mobile Safari"; omit to run all projects
specstring–Spec file relative to tests/; omit to run everything

No output schema declared.

No examples provided.

save_login_state ~198

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.

NameTypeReqDescription
devicestring–Emulate a device for mobile web: a Playwright device name such as "iPhone 15" or "Pixel 7" (list_devices), or "desktop" (default)
namestring––
stepsarrayyes–
success_locatorstring–Locator that must be visible after login, e.g. page.getByRole('heading', { name: 'My account' })
urlstringyesLogin page URL

No output schema declared.

No examples provided.

write_test ~65

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

NameTypeReqDescription
codestringyes–
overwriteboolean––
pathstringyesRelative to tests/, e.g. login.spec.ts

No output schema declared.

No examples provided.

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.

npm · k11-playwright-qa-mcp

# add to Claude Code
claude mcp add k11-software-solutions-playwright-qa -- npx -y k11-playwright-qa-mcp
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.