AutoCua vs Playwright MCP

AutoCua 25

Local package. Installs from PyPI as AutoCua with Python 3.10 or later and the supported platforms stated (20). No CI runs the tests; the only workflow, use_case_label.yml, labels issues (0). GitHub issues weren't read, so the open-issue line is scored absent (0). Four tags in a week with no changelog file (5). Version 0.1.9 (0). 20 + 0 + 0 + 5 + 0 = 25.

Playwright MCP 57

Scored as a local stdio package (it also serves HTTP with --port). Official npm package @playwright/mcp with Node 18 or later stated. It pins alpha builds of Playwright (1.65.0-alpha-2026-10-30 in v0.0.84) as dependencies (20). CI runs lint, tests on Ubuntu, macOS and Windows and a Docker test on every push and pull request. Most MCP tests live in the main Playwright repository. We didn't see the run status, so 20 of 25. Issues have been redirected to microsoft/playwright since 29 June 2026, and GitHub's robots rules blocked our search there, so we couldn't count open crash reports (12). Versions run 0.0.x with release notes on GitHub but no semver meaning (5). Not 1.0 and not declared stable (0).

AutoCua 42

MIT (30). Says it sends data only to the chosen model provider and keeps everything else locally, and the source agrees (20 of 30). No deprecation policy (0). States no telemetry, and none was found (20). 30 + 20 + 0 + 20 = 70.

Playwright MCP 74

Apache-2.0 (30). Local software. There's no written data statement, but we found no telemetry or remote calls beyond the pages it's asked to open in the MCP code (20). No deprecation policy, and 0.0.x versioning gives no notice of tool renames (5). No telemetry in the source we read (20).

AutoCua 55

Framework reading. One call with a mode, provider, model and task runs a whole agent (20 of 25). A separate compression agent splices handoff summaries in, and runs are capped and stoppable (15 of 20). Permission and blocked-input errors are reported specifically, with no error reference (8 of 20). No resume or retry semantics described (2 of 20). Sensible defaults (simulators unless device is set), Python only (10 of 15). 20 + 15 + 8 + 2 + 10 = 55.

Playwright MCP 84

72 tools in the README across ten groups. Only core and tabs load by default, 25 tools (15). --caps adds network, storage, devtools, vision, PDF, testing and config groups only when asked, and --snapshot-mode none and --image-responses omit trim each response (plus 10). browser_find searches the snapshot instead of returning it and takes maxResults since v0.0.84, snapshots take depth, and most read tools can write to a file instead of the response (17). Modal-state errors name the tool that clears them (14). Every tool carries readOnlyHint, destructiveHint and openWorldHint, 29 marked read-only. Every other tool is marked destructive, hover included, which blunts the signal (18). Few required parameters and defaults that work. npm and Docker only (10).

AutoCua 42

Framework reading. No API reference or typed interface beyond run_agent's documented arguments (5 of 25). No llms.txt (0). The README says what each mode drives and where it runs, and agent_capabilities.md lists what it can do (16 of 20). Modes and device are documented strings (6 of 15). Many examples, no documented errors (10 of 15). Tags without a changelog (5 of 15). 5 + 0 + 16 + 6 + 10 + 5 = 42.

Playwright MCP 70

Every tool's input is a Zod schema turned into JSON Schema (25). The README's tool list is generated from the source. No llms.txt (5). Descriptions are mostly one line, "Perform click on a web page" or "Returns all console messages". browser_find and browser_snapshot explain when they're cheaper, and the README says when to prefer the CLI over MCP (10). Enums for mouse buttons, modifiers and console levels, depth on snapshots, and a free-form MIME map on browser_drop (13). Few examples beyond browser_run_code_unsafe and browser_find, and no documented error list (7). GitHub release notes for each 0.0.x version (10).

AutoCua 38

Framework reading (telemetry, approvals, guardrails, sandboxing). Provider keys stored in a local folder with Chrome profiles (10 of 30). The worker tools are an allow-list with no write tool, unseen ids are refused, downloads need a yes, but on Windows the model answers UAC elevation prompts itself through a kernel driver, with no person asked (6 of 20). The scraping ruleset has a prompt-injection instruction to log page text that gives instructions (10 of 15). Runs are logged in the app, with no audit log (7 of 15). No security policy, disclosure route or advisories found (5 of 20, for the vault and certificate handling). 10 + 6 + 10 + 7 + 5 = 38.

Playwright MCP 57

No credentials to leak and nothing to scope, so the middle band (20). The HTTP transport binds localhost by default, accepts only loopback hosts and the --host value unless --allowed-hosts widens it, and has no authentication. File access is limited to workspace roots unless --allow-unrestricted-file-access, with symlinks resolved since v0.0.81, and --secrets and --redact-url-params mask values in responses. --isolated is off by default, the allowed and blocked origin lists say they aren't a security boundary, browser_run_code_unsafe, described in its own text as RCE-equivalent in the server process, sits in the core set that can't be switched off, and on Linux the downloaded Chromium builds (--browser chromium, and since v0.0.81 a config naming chromium with no channel) launch without the Chromium sandbox unless --sandbox is set, while the default Chrome channel keeps it (10). Page content is untrusted and we found no prompt-injection guidance beyond a README line that the server isn't a security boundary and a release note to treat WebMCP tools as untrusted input (0). --save-session, traces, video and generated Playwright code for each action give the operator a record (12). Microsoft's MSRC reporting policy in SECURITY.md, and one advisory published, CVE-2025-9611 (High, fixed in v0.0.40) (15).

AutoCua 65

v0.1.9 tagged on 4 November 2026 (30). Four tags in 90 days (20). Issues and pull requests weren't read (0 of 25). The PyPI wheel is current (15). No CI; dependencies pinned per OS in requirements files (0 of 10). 30 + 20 + 0 + 15 + 0 = 65.

Playwright MCP 84

v0.0.84 on 2026-10-31 (30). Six releases since 3 August, v0.0.79 to v0.0.84 (20). Issues moved to microsoft/playwright on 29 June 2026 with a pinned notice. We couldn't read the MCP issues there, and Dependabot pull requests here merge within days (12). Published to the official MCP registry as io.github.microsoft/playwright-mcp by an OIDC workflow on each release, and the registry lists 0.0.84 as latest, published 31 October 2026 (15). Pinned actions and Dependabot, but the package tracks alpha Playwright builds, 1.65.0-alpha-2026-10-30 in v0.0.84 (7).