claude-playwright (smartlabsAT/claude-playwright) is an MCP server listed on the M8ven Trust Index. It scores 25 out of 100, grade F. It declares 26 tools. No publisher has claimed this listing.
Enables browser automation and web interaction control through Playwright, allowing Claude Code to navigate, click, fill forms, take screenshots, and manage sessions.
Warning. Serious findings were identified. Review the full report before connecting. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
smartlabsAT
Source: Glama
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
browser_console_messagesGet all console messages from the browser
browser_network_requestsGet network requests made by the page
browser_evaluateExecute JavaScript in the browser context
browser_wait_forWait for an element or condition
browser_hoverHover over an element
browser_select_optionSelect option(s) in a dropdown
browser_press_keyPress a keyboard key
browser_fill_formFill multiple form fields at once
browser_session_restoreRestore a saved browser session with cookies and localStorage
browser_session_saveSave current browser session with cookies and localStorage
browser_session_listList all saved browser sessions
browser_navigateNavigate to a URL with automatic BASE_URL injection
browser_clickClick an element on the page
browser_typeType text into an input field
browser_snapshotGet accessibility tree snapshot of the current page
browser_screenshotTake a screenshot of the current page
browser_cache_statusGet enhanced cache statistics and debug information
browser_closeClose the browser
browser_save_testSave current interaction sequence as reusable test scenario
browser_find_similar_testsFind similar test scenarios based on intent and context
browser_run_testExecute a saved test scenario with intelligent adaptation
browser_test_libraryShow comprehensive test library with statistics and filtering
browser_suggest_actionsGet intelligent action suggestions based on current context and learned patterns
browser_adapt_testIntelligently adapt an existing test scenario to current context
browser_delete_testDelete test scenarios with flexible options
protocol_validation_statusGet protocol validation statistics and debug information
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse
Anthropic's MCP TypeScript SDK has a ReDoS vulnerability
Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default
Playwright downloads and installs browsers without verifying the authenticity of the SSL certificate
Zod denial of service vulnerability
BASE_URLApplication base URLPLAYWRIGHT_ACTION_TIMEOUTPLAYWRIGHT_ACTIVE_PROFILEPLAYWRIGHT_ACTIVE_SESSIONPLAYWRIGHT_BASE_URLPLAYWRIGHT_BROWSER_TIMEOUTPLAYWRIGHT_LAST_URLPLAYWRIGHT_NAVIGATION_TIMEOUTPLAYWRIGHT_SELECTOR_TIMEOUTPLAYWRIGHT_SESSION_STORAGE_STATEPLAYWRIGHT_USER_AGENTPLAYWRIGHT_VIEWPORTTool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
26/26 tools missing one or more hints — browser_console_messages (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); browser_network_requests (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); browser_evaluate (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +23 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Descriptions match behaviour
2 tools describe read intent but their handlers mutate — browser_session_list (line 124: fs.mkdirSync(SESSIONS_DIR, { recursive: true })); browser_snapshot (line 124: fs.mkdirSync(SESSIONS_DIR, { recursive: true }))
Rename the tool, rewrite the description, or move the side-effect into a separate clearly-named tool.
Tool inputs are validated
18/26 tool handlers declare input schemas (69%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Tool test coverage
12/26 tools referenced in tests (46%)
Write tests that reference each tool by name so every tool has at least one test.
No arbitrary install scripts
Has postinstall/preinstall script — runs arbitrary code on npm install
Remove postinstall/preinstall hooks unless they’re essential.
Production dependencies are patched
0 critical, 4 high severity in production deps — @modelcontextprotocol/sdk@1.17.4 (high), @modelcontextprotocol/sdk@1.17.4 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Dependency freshness
1/11 production deps stale: readline@2022-06-26 (4.2y)
Tool description accuracy
browser_session_list: description implies read-only but handler writes/deletes/executes; browser_snapshot: description implies read-only but handler writes/deletes/executes
Update tool descriptions to accurately reflect all capabilities — especially write, delete, or execute operations.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/smartlabsat/claude-playwright)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check