MCP server · Org-owned · Audited from source

Playwright MCP server

by microsoft/playwright-mcpApache-2.0 licenceAudited 19 Sep 2026 · source 9c99d0c7d411

npm @playwright/mcp 0.0.82stdio★ 37,315
✓SAFEGrade B · 89/100 · 19 Sep 2026 · 9c99d0c
37,315GitHub stars

Is it safe? Yes — SAFE, grade B (89/100). The tool list is built at runtime, so we cannot read it from the source. The audit recorded 5 findings (0 critical, 0 high, 1 medium, 4 low). Maintainer's description: Playwright MCP server

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Playwright MCP server (microsoft/playwright-mcp)”. Retrieved 19 Sep 2026. https://modelsatlas.com/mcp/microsoft/playwright-5

4 MCP servers are called Playwright. This is the one we pick. Compare all 4 →

Trust audit

Audit 0.4.1 · full source read 19 Sep 2026

Trust score89/100✓SAFE B
0 critical0 high1 medium4 low0 info

5 findings, listed below with the file and line each was found on. Grade A needs a sandboxed behavioural run too; this audit read the source only.

What the source does

  • FilesystemDeclared1 observation
  • NetworkDeclared1 observation
  • ShellDeclared3 observations
  • DependenciesNot pinnedSome ranges float
  • SecretsFoundSee the findings

“Declared” means the server says it does this and the source agrees. Browser, file and shell access are expected of some kinds of server.

Five audit layers

LayerWhat we checkResult
L0 ProvenanceRepo owner, licence, archive status, activityPASS
L1 Static sourceSecrets, path traversal, supply chainWARN 3 findings
L2 InstructionsPrompt injection and authority framing in docs and tool descriptionsPASS 1 finding
L3 InventoryDeclared tools match the sourcePASS 1 finding
L4 SandboxRun in isolation and watch behaviourSKIPPED

Provenance & runtime

Who published it, and what the audit could and could not run

Provenance

  • Repository owner microsoftOrganizationAccount type recorded when we read the repository.
  • PackagePublished on npm@playwright/mcp at version 0.0.82
  • LicenceApache-2.0From the repository, as read at the audited commit.
  • Last pushTodayActivity of the repository when we read it.
  • Source commit read9c99d0c7d411The audit covers exactly this commit, read on 19 Sep 2026.

Runtime

  • Sandbox runNot run yetThis audit read the source only; it did not execute the server.
  • Tool inventoryBuilt at runtimeThe source declares no tools; the server lists them when a client connects, so we cannot read them.

Every value here is read from the record's own repository and audit.Suggest a correction

Findings (5)

Sorted by severity

MEDIUMHard-coded secretssecret.private_key · tests/testserver/key.pem:1
F-03 Hard-coded secretsCWE-798 · CWE-321Layer L1

Excerpt withheld: it is a secret, and we never print one.

Why
No further detail recorded for this rule.
Fix
—
LOWFilesystem / pathfs.traversal · utils/docker/publish_docker.sh:18
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
MCP_VERSION=$(node -p "require('../../package.json').version")
Why
No further detail recorded for this rule.
Fix
—
LOWSupply chainsupply.unpinned · package.json
F-08 Supply chainCWE-829 · CWE-1357Layer L1
@modelcontextprotocol/sdk, @types/node
Why
2 dependency range(s) float
Fix
pin exact versions or ship a lockfile
LOWPrompt injectionprompt.authority_framing · README.md:411
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
| --allow-unrestricted-file-access | allow access to files outside of the workspace roots. Also allows unrestricted access to file:// URLs. By default access to file system is restricted to workspace 
Why
No further detail recorded for this rule.
Fix
—
LOWInventory / provenancemcp.no_tools_extracted · server.json
F-13 Inventory / provenanceCWE-1104Layer L3
Why
the tool list is enumerated at runtime by tools/list, not declared in source
Fix
the page says so rather than showing an empty table

Tools it exposes

None declared in source

The tool list is built at runtime, so we cannot read it from the source.

Install

Package version 0.0.82 · audited commit 9c99d0c

claude mcp add mcp -- npx -y @playwright/[email protected]

The command pins the package version recorded in the source (0.0.82); the audit covers commit 9c99d0c7d411. Transport: stdio. No environment variables required.

Audit history

  1. ✓SAFE B 89 / 100

    Source changed, verdict held · 9c99d0c7d411

  2. ✓SAFE B 89 / 100

    First audit · 146dc5a010d0

README badge

For maintainers · updates on every re-audit

ModelsAtlas: SAFE BMODELSATLASSAFE · B
[![ModelsAtlas: SAFE B](https://modelsatlas.com/mcp/microsoft/playwright-5/badge.svg)](https://modelsatlas.com/mcp/microsoft/playwright-5/)

The badge always shows the latest audit; a maintainer cannot pin an old verdict.

Other ratings

Cited, never blended into our score

No third-party security ratings are recorded for this server yet. When they exist they appear here with their source and date, beside, not inside, our grade.

Questions about Playwright MCP server

What is the Playwright MCP server?
Playwright MCP server
Is Playwright safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Playwright need?
No credential environment variables were found in its source, so it appears to need none.
How does Playwright run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as @playwright/mcp at 0.0.82.
How current is this page?
The grade is for one exact copy of the source (9c99d0c7d411), read on 2026-09-19. The repository is watched and re-audited when it changes.
Which Playwright MCP server is the right one?
microsoft/playwright-mcp (this page). 4 servers share the name; see the side-by-side comparison.

Sources

  • microsoft/playwright-mcp on GitHub — the source we read, its licence, stars and activityObserved · 19 Sep 2026
  • ModelsAtlas trust audit — SAFE verdict for commit 9c99d0c7d411Observed · 19 Sep 2026

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.