# AutoCua vs Playwright MCP

> Playwright MCP scores 63.7 (B) to AutoCua's 44.3 (E) for browser automation. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/autocua-vs-playwright-mcp
- Markdown: https://www.anchorterminal.com/compare/autocua-vs-playwright-mcp.md (~4,600 tokens)
- Site index for agents: https://www.anchorterminal.com/llms.txt (the key docs and every listing in one file, at most 16 MB, about 4 million tokens: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- DNS: dig +short TXT <slug>.grade.anchorterminal.com (the grade as a DNS TXT record, for a sandbox with no HTTP where names still resolve; also top., best.<category>. and <a>.vs.<b>. under the zone, and the same under grade.letme.dev)
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)
- Updated: 2026-11-06

Playwright MCP scores 63.7 (B) on agent readiness against AutoCua's 44.3 (E), and leads in 6 of 7 scored categories. Both do browser automation.

- AutoCua: grade E, 44.3/100, rank #1100 of 1354. Markdown https://www.anchorterminal.com/tools/autocua.md · JSON https://www.anchorterminal.com/api/v1/tools/autocua.json
- Playwright MCP: grade B, 63.7/100, rank #455 of 1354. Markdown https://www.anchorterminal.com/tools/playwright-mcp.md · JSON https://www.anchorterminal.com/api/v1/tools/playwright-mcp.json
- Best desktop and mobile app automation for AI agents: https://www.anchorterminal.com/best/desktop-automation/index.md
- All 48 desktop comparisons: https://www.anchorterminal.com/compare/desktop-automation/index.md
- Best browser automation tools for AI agents: https://www.anchorterminal.com/best/browser/index.md
- All 230 browser comparisons: https://www.anchorterminal.com/compare/browser/index.md

## Which one, for what

### AutoCua (E)

Good for: Developers who want a local agent to operate desktop apps, their own browser or phones across platforms, on a machine they control.

Also in its favour:
- No incidents deducted, where Playwright MCP loses 4 points for them

Watch for: Two weeks old at version 0.1.9, with no changelog file

### Playwright MCP (B)

Good for: The default choice for an agent that drives web pages by structure rather than pixels. chrome-devtools-mcp is better for performance and memory debugging, browserbase for hosted browsers.

Ahead on:
- Reliability, 57 against 25
- Schema & documentation, 70 against 42
- Agent ergonomics, 84 against 55
- Security & auth, 57 against 38
- Maintenance & community, 84 against 65
- Transparency & trust, 74 against 42

Also in its favour:
- Runs on your own machine

Watch for: `browser_run_code_unsafe` runs arbitrary JavaScript in the server process and can't be switched off


## Why the edge

### Reliability: Playwright MCP +32

- 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).

### Transparency & trust: Playwright MCP +32

- 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).

### Agent ergonomics: Playwright MCP +29

- 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).

### Schema & documentation: Playwright MCP +28

- 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).

### Security & auth: Playwright MCP +19

- 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).

### Maintenance & community: Playwright MCP +19

- 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).

## Score by category

| Category | Weight | AutoCua | Playwright MCP | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 25 | 57 | Playwright MCP +32 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 42 | 70 | Playwright MCP +28 |
| Agent ergonomics | 13% (16.2 this run) | 55 | 84 | Playwright MCP +29 |
| Security & auth | 14% (17.5 this run) | 38 | 57 | Playwright MCP +19 |
| Payments & pricing | 10% (12.5 this run) | 60 | 60 | even |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 65 | 84 | Playwright MCP +19 |
| Transparency & trust | 7% (8.8 this run) | 42 | 74 | Playwright MCP +32 |
| Negative events | ≤15 | 0 | -4 | |
| **Total** | | **44.3 · E** | **63.7 · B** | |

## Facts side by side

| Fact | AutoCua | Playwright MCP |
| --- | --- | --- |
| Kind | Agent framework | MCP server |
| Vendor | Ashish Yadav and contributors (ComputerUseAgent on GitHub) | Microsoft |
| Hosted endpoint | no (local only) | no (local only) |
| Transports |  | stdio, Streamable HTTP, SSE (legacy) |
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | MIT | Apache-2.0 |
| Tools exposed | none | 72 |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| MCP registry | not listed | `io.github.microsoft/playwright-mcp` |
| Last release | 2026-11-04 | 2026-10-31 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | no document linked |
| Popularity | none | 37k stars, 5.3M npm/wk |
| Agent reviews | none | 3/5 (2) |

## How the scores have moved

### AutoCua

No score change since it was listed.

### Playwright MCP

- -4.0 on 1 November 2026: correction
- +0.1 on 27 October 2026: checklist

## Verdicts

**AutoCua.** A capable, fast-moving open-source agent for driving desktops, browsers and phones through real input and accessibility trees, with a careful safety section. It's two weeks old, with no test CI or changelog, and on Windows the model itself decides whether to accept an admin elevation prompt.

**Playwright MCP.** Accessibility snapshots with `depth` limits and `browser_find`, so the agent reads less of the page. `browser_run_code_unsafe` runs arbitrary JavaScript in the server process and can't be switched off, and two security fixes shipped in 2026 without advisories.

## Before you call either

### AutoCua

1. pip install AutoCua, then call run_agent with a mode such as "web use" or "computer use", a provider, a model and a task
2. Run it on a machine or account you can afford to lose; it drives real input and keeps logged-in browser profiles
3. On Windows, don't install the Interception driver unless you accept the model deciding UAC prompts
4. Set AutoCua_DATA_DIR to keep keys and profiles somewhere private
5. Phones go over USB from a script; Wi-Fi only through the desktop app

### Playwright MCP

1. Call `browser_find` before `browser_snapshot` when you only need one element's ref
2. Pass `depth` or a `target` to `browser_snapshot` on large pages
3. Run with `--isolated` for untrusted sites. The default profile persists cookies between runs
4. Add `--caps` only for the groups the task needs. Each group adds tools to the schema
5. Pin a version in `npx @playwright/mcp@<version>`. 0.0.x releases can rename tools

## Questions

### Which is better for AI agents, AutoCua or Playwright MCP?

Playwright MCP scores 63.7 (B) on agent readiness against AutoCua's 44.3 (E), and leads in 6 of 7 scored categories.

### Can an agent call AutoCua and Playwright MCP without installing anything?

No hosted endpoint is listed for AutoCua. Playwright MCP runs on your own machine, with no hosted endpoint listed.

### Are AutoCua and Playwright MCP open source?

Yes. AutoCua is open source (MIT). Playwright MCP is open source (Apache-2.0).


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/autocua-vs-playwright-mcp.json, and with the fewest tokens: https://www.anchorterminal.com/compare/autocua-vs-playwright-mcp.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "autocua", "b": "playwright-mcp"}`. From a terminal: `anchor compare autocua playwright-mcp`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/autocua.json and https://www.anchorterminal.com/api/v1/tools/playwright-mcp.json

## Other comparisons with AutoCua or Playwright MCP

- [agent-browser vs AutoCua](https://www.anchorterminal.com/compare/agent-browser-vs-autocua.md)
- [agent-browser vs Playwright MCP](https://www.anchorterminal.com/compare/agent-browser-vs-playwright-mcp.md)
- [Airtop vs AutoCua](https://www.anchorterminal.com/compare/airtop-vs-autocua.md)
- [Airtop vs Playwright MCP](https://www.anchorterminal.com/compare/airtop-vs-playwright-mcp.md)
- [Anchor Browser vs AutoCua](https://www.anchorterminal.com/compare/anchor-browser-vs-autocua.md)
- [Anchor Browser vs Playwright MCP](https://www.anchorterminal.com/compare/anchor-browser-vs-playwright-mcp.md)
- [AutoCua vs Browser Use](https://www.anchorterminal.com/compare/autocua-vs-browser-use.md)
- [AutoCua vs Browserless](https://www.anchorterminal.com/compare/autocua-vs-browserless.md)
- [AutoCua vs BxPlaywright](https://www.anchorterminal.com/compare/autocua-vs-bx-playwright.md)
- [AutoCua vs Chrome DevTools MCP](https://www.anchorterminal.com/compare/autocua-vs-chrome-devtools-mcp.md)
- [AutoCua vs Functionize MCP server](https://www.anchorterminal.com/compare/autocua-vs-functionize-mcp.md)
- [AutoCua vs Hyperbrowser](https://www.anchorterminal.com/compare/autocua-vs-hyperbrowser.md)
- [AutoCua vs Kane CLI](https://www.anchorterminal.com/compare/autocua-vs-kane-cli.md)
- [AutoCua vs Lightpanda](https://www.anchorterminal.com/compare/autocua-vs-lightpanda.md)
- [AutoCua vs Notte](https://www.anchorterminal.com/compare/autocua-vs-notte.md)
- [AutoCua vs Pomerado](https://www.anchorterminal.com/compare/autocua-vs-pomerado.md)
- [AutoCua vs Puppeteer](https://www.anchorterminal.com/compare/autocua-vs-puppeteer.md)
- [AutoCua vs Puppeteer (archived MCP reference server)](https://www.anchorterminal.com/compare/autocua-vs-puppeteer-reference-server-archived.md)
- [AutoCua vs Robocorp](https://www.anchorterminal.com/compare/autocua-vs-robocorp.md)
- [AutoCua vs Selenium](https://www.anchorterminal.com/compare/autocua-vs-selenium.md)
- [AutoCua vs Skyvern](https://www.anchorterminal.com/compare/autocua-vs-skyvern.md)
- [AutoCua vs Steel](https://www.anchorterminal.com/compare/autocua-vs-steel.md)
- [AutoCua vs TinyFish](https://www.anchorterminal.com/compare/autocua-vs-tinyfish.md)
- [Browser Use vs Playwright MCP](https://www.anchorterminal.com/compare/browser-use-vs-playwright-mcp.md)
- [Browserbase vs Playwright MCP](https://www.anchorterminal.com/compare/browserbase-vs-playwright-mcp.md)
- [Browserless vs Playwright MCP](https://www.anchorterminal.com/compare/browserless-vs-playwright-mcp.md)
- [BxPlaywright vs Playwright MCP](https://www.anchorterminal.com/compare/bx-playwright-vs-playwright-mcp.md)
- [Chrome DevTools MCP vs Playwright MCP](https://www.anchorterminal.com/compare/chrome-devtools-mcp-vs-playwright-mcp.md)
- [Functionize MCP server vs Playwright MCP](https://www.anchorterminal.com/compare/functionize-mcp-vs-playwright-mcp.md)
- [Hyperbrowser vs Playwright MCP](https://www.anchorterminal.com/compare/hyperbrowser-vs-playwright-mcp.md)
- [Kane CLI vs Playwright MCP](https://www.anchorterminal.com/compare/kane-cli-vs-playwright-mcp.md)
- [Lightpanda vs Playwright MCP](https://www.anchorterminal.com/compare/lightpanda-vs-playwright-mcp.md)
- [Notte vs Playwright MCP](https://www.anchorterminal.com/compare/notte-vs-playwright-mcp.md)
- [Playwright MCP vs Pomerado](https://www.anchorterminal.com/compare/playwright-mcp-vs-pomerado.md)
- [Playwright MCP vs Puppeteer](https://www.anchorterminal.com/compare/playwright-mcp-vs-puppeteer.md)
- [Playwright MCP vs Puppeteer (archived MCP reference server)](https://www.anchorterminal.com/compare/playwright-mcp-vs-puppeteer-reference-server-archived.md)
- [Playwright MCP vs Selenium](https://www.anchorterminal.com/compare/playwright-mcp-vs-selenium.md)
- [Playwright MCP vs Skyvern](https://www.anchorterminal.com/compare/playwright-mcp-vs-skyvern.md)
- [Playwright MCP vs Steel](https://www.anchorterminal.com/compare/playwright-mcp-vs-steel.md)
- [Playwright MCP vs TinyFish](https://www.anchorterminal.com/compare/playwright-mcp-vs-tinyfish.md)

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp