playwright-mcp
mcp0.0.78Playwright MCP server
By microsoft | 42 findings | Scanned 7/28/2026 | tooltrust-scanner/v0.3.19 | 35.5k
Risk Summary
Needs ApprovalDep Visibility plus Excessive Permissions raises enough risk that this tool should not be auto-trusted.
Potential impact: This finding indicates the tool should be reviewed before it is trusted.
Recommended action: Keep this tool behind manual approval and avoid unattended runs until the risky capabilities are narrowed or removed.
Suggested policy: keep this tool behind manual approval, do not allow unattended runs, and re-scan after narrowing risky permissions.
Security Findings (42)
browser_run_code_unsafe:tool name or description implies arbitrary script/code execution (evaluate_script, execute javascript, etc.)
Fix: This tool can execute arbitrary code or shell commands on the host system. Remove it unless strictly required. If kept: (1) restrict access to trusted users/agents only, (2) require human approval before each invocation (Claude Desktop: set approval_required: true; other clients: enable equivalent confirmation), (3) use the most restrictive sandbox or read-only mode available, and (4) never expose this tool to untrusted input sources.
tool performs network or execution operations but declares no rate-limit, timeout, or retry configuration
browser_navigatebrowser_network_requestsbrowser_network_requestbrowser_run_code_unsafebrowser_tabsFix: Declare explicit rate-limit, timeout, and retry configuration for all network and execution tools. Implement exponential back-off and surface resource state to the calling agent.
No metadata.dependencies or repo_url were exposed by this MCP server, and no local project manifest could be inferred from the launch command.
browser_closebrowser_resizebrowser_console_messagesbrowser_handle_dialogbrowser_evaluatebrowser_file_uploadbrowser_dropbrowser_findbrowser_fill_formbrowser_press_keybrowser_typebrowser_navigatebrowser_navigate_backbrowser_network_requestsbrowser_network_requestbrowser_run_code_unsafebrowser_take_screenshotbrowser_snapshotbrowser_clickbrowser_dragbrowser_hoverbrowser_select_optionbrowser_tabsbrowser_wait_forFix: Review and remediate the identified issue.
declared capabilities: filesystem access
browser_console_messagesbrowser_evaluatebrowser_file_uploadbrowser_dropbrowser_take_screenshotbrowser_snapshotdeclared capabilities: network access
browser_navigatebrowser_tabsdeclared capabilities: network access, filesystem access
browser_network_requestsbrowser_network_requestdeclared capabilities: code/command execution, filesystem access
browser_run_code_unsafeFix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.
browser_evaluate:tool name or description implies arbitrary script/code execution — capability unconfirmed (no exec permission or code/script/eval input property found)
Fix: This tool can execute arbitrary code or shell commands on the host system. Remove it unless strictly required. If kept: (1) restrict access to trusted users/agents only, (2) require human approval before each invocation (Claude Desktop: set approval_required: true; other clients: enable equivalent confirmation), (3) use the most restrictive sandbox or read-only mode available, and (4) never expose this tool to untrusted input sources.
Scan this tool yourself
Reproduce this audit locally, integrate into CI, or let your agent audit its own tools.
Install once, then scan any MCP server:
$ curl -sfL https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-scanner/main/install.sh | bash$ tooltrust-scanner scan --server "npx -y playwright-mcp"Adjust the package name if your npm registry name differs from the tool ID. View source
Add badge to your README
Copy this Markdown to show your ToolTrust grade on GitHub.
[](https://github.com/AgentSafe-AI/tooltrust-directory)