Playwright MCP Server (ExecuteAutomation)
Frameworks & Eval · tested 2026-08-14 · by the Hlido desk, not the vendor
In short: A widely-installed Playwright MCP server whose public surface is three marketing sentences and a link to Udemy — the tool may well be good, but almost nothing about it is checkable from outside.
Visit Playwright MCP Server (ExecuteAutomation) → scorecard.json
Quick answer
Playwright MCP Server (ExecuteAutomation) scores 58/100 (FADING) on Hlido’s independent, hands-on test (reviewed 2026-08-14). FADING because the public surface supports almost none of the checks this category demands: no tool inventory, no version or changelog, no security or data-handling statement, and no integration detail beyond 'change the Pricing: Open source (free entry point documented).
This is a case where the review has to be explicit about what it did and did not see. The documentation site is a near-default Docusaurus scaffold: a tagline, three feature cards ('Easy to Use', 'Test UI and APIs', 'Powered by NodeJS'), links to a tutorial and to the maintainer's YouTube and Udemy courses, and a 2025 copyright line. There is no tool list, no configuration reference on the landing surface, no version, no changelog, and no statement about what the server does or does not permit an agent to do against a browser. That matters more for this category than most. A Playwright MCP server hands an LLM control of a real browser; the questions a buyer needs answered are which tools are exposed, whether there is any sandboxing, and how credentials or session state are handled. None of that is answerable from the public surface. The tutorial pages exist and may cover it, but the entry surface — the thing an evaluating agent or a hurried engineer lands on — does not. The low score reflects a thin, unverifiable public surface, not a judgement that the software is bad; a docs pass exposing the tool inventory and a security note would move this substantially.
Why FADING
FADING because the public surface supports almost none of the checks this category demands: no tool inventory, no version or changelog, no security or data-handling statement, and no integration detail beyond 'change the Claude config file'. Not lower, because the docs site does load, a real tutorial path exists, and the product's purpose is stated unambiguously. The confidence on this review is low by design — the score describes what is publicly verifiable, and a documentation update could change it quickly.
What we saw
4 screenshots captured by the Hlido engine during the reviewed run (run-06c430ea5592ee18-executeautomation-github-io). Our own captures — not vendor marketing material.
What it does well
- Purpose is stated in one unambiguous sentence — no ambiguity about what the server is for
- Documentation site is public with no login wall
- A tutorial path exists and is linked from the landing page
- Setup burden is honestly described as a single config-file change
What it fails at
- No tool inventory anywhere on the public surface — a buyer cannot see what the server exposes to an agent
- No version, release or changelog signal; the copyright reads 2025 with no freshness indicator
- No security or sandboxing statement, despite the server granting an LLM control of a real browser
- No credential or session-state handling description
- Primary community links route to paid Udemy courses rather than to reference documentation
Red flags
- A browser-control MCP server with no public security or sandboxing statement is a meaningful gap — this class of tool can navigate, click and read anything the browser session can reach.
- The most prominent community links are to paid courses, not to technical reference material, which shifts evaluation cost onto the buyer.
Best for
- Engineers who already know Playwright and want the fastest path to driving it from an AI client
- Teams doing exploratory UI/API testing where a thin tool surface is acceptable
- Anyone prepared to read the repository directly rather than rely on published docs
Not recommended for
- Buyers who need a published tool inventory or permission model before letting an agent drive a browser
- Regulated or security-reviewed environments — there is no public posture to review
- Agents evaluating autonomously; there is not enough structured public information to decide on
Pricing & access
- ModelOpen source
- Free entry pointYes — a free tier or open-source edition is documented
Derived from Hlido-held evidence only (engine checklist + editorial text); quotes are verbatim from the scorecard; not vendor-supplied; re-derived daily. Verify current prices on the vendor's pricing page. Last verified 2026-08-11.
Compared to
-
Microsoft Playwright MCP
documentation-and-provenance
Microsoft's own Playwright MCP publishes a full tool inventory and is maintained alongside Playwright itself. Unless you specifically want this variant's API-testing framing, the first-party server is the better-documented default.
-
WaveXisMCP
documented-surface
WaveXisMCP documents 220 tools across 13 tiers with a security page and benchmarks; this server documents none of that publicly. Opposite ends of the documentation spectrum for a similar job.
Agent relevance
MCP
Agentic-Commerce Readiness 33/100 · SURFACE-ONLY
Independent readiness for agent delegation & transaction. How it’s scored · check live
An MCP server by definition, installed via a client config change. But with no published tool list, an agent cannot determine its capabilities ahead of connecting — discovery has to happen at runtime, which is the weakest form of agent-addressability.
Agent-friendly score: 4/10
Score over time
The longitudinal record — every point is the score as published on that date. Raw series.
Evidence
- Homepage publicly accessible and value proposition clearly stated — source (2026-08-14) verified
- Pricing page discoverable in 2 clicks from homepage — source (2026-08-14)
- Documentation or live demo accessible without login — source (2026-08-14)
- Integration list or supported frameworks documented — source (2026-08-14)
- Authentication / data handling claims publicly stated — source (2026-08-14)
scorecard.json · transparency passport · registry · methodology
Embed this trust badge
Markdown
[](https://hlido.eu/check/?agent=executeautomation-mcp-playwright)HTML
<a href="https://hlido.eu/check/?agent=executeautomation-mcp-playwright"><img src="https://hlido.eu/badge/executeautomation-mcp-playwright.svg" alt="Hlido trust score"></a>