# agent-browser vs Playwright MCP

> Playwright MCP scores 67.6 (B) on agent readiness against agent-browser's 66.6 (B), and leads in 4 of 7 scored categories. agent-browser leads on schema & documentation and security & auth. Both do browser automation. Category scores, facts, verdicts and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/agent-browser-vs-playwright-mcp
- Markdown: https://www.anchorterminal.com/compare/agent-browser-vs-playwright-mcp.md (~2,400 tokens)
- Slim: https://www.anchorterminal.com/compare/agent-browser-vs-playwright-mcp.min.md (~580 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/agent-browser-vs-playwright-mcp.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- Updated: 2026-10-09

Playwright MCP scores 67.6 (B) on agent readiness against agent-browser's 66.6 (B), and leads in 4 of 7 scored categories. agent-browser leads on schema & documentation and security & auth. Both do browser automation.

- agent-browser: grade B, 66.6/100, rank #263 of 842. Markdown https://www.anchorterminal.com/tools/agent-browser.md · JSON https://www.anchorterminal.com/api/v1/tools/agent-browser.json
- Playwright MCP: grade B, 67.6/100, rank #228 of 842. Markdown https://www.anchorterminal.com/tools/playwright-mcp.md · JSON https://www.anchorterminal.com/api/v1/tools/playwright-mcp.json

## Which one, for what

### agent-browser (B)

Good for: Coding agents with a shell that want short commands and compact snapshots.

Ahead on:
- Schema & documentation, 84 against 70
- Security & auth, 67 against 57

Watch for: The ten most recent CI runs on main, 1 to 8 October 2026, all concluded in failure. In the newest, Windows Rust tests and native end-to-end tests failed

### 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 48
- Agent ergonomics, 84 against 78
- Maintenance & community, 84 against 70
- Transparency & trust, 72 against 61

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


## Score by category

| Category | Weight | agent-browser | Playwright MCP | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 48 | 57 | Playwright MCP +9 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 84 | 70 | agent-browser +14 |
| Agent ergonomics | 13% (16.2 this run) | 78 | 84 | Playwright MCP +6 |
| Security & auth | 14% (17.5 this run) | 67 | 57 | agent-browser +10 |
| 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) | 70 | 84 | Playwright MCP +14 |
| Transparency & trust | 7% (8.8 this run) | 61 | 72 | Playwright MCP +11 |
| Negative events | ≤15 | 0 | 0 | |
| **Total** | | **66.6 · B** | **67.6 · B** | |

## Facts side by side

| Fact | agent-browser | Playwright MCP |
| --- | --- | --- |
| Kind | MCP server | MCP server |
| Vendor | Vercel Labs | Microsoft |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | stdio | stdio, Streamable HTTP, SSE (legacy) |
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | Apache-2.0 | Apache-2.0 |
| Tools exposed | 158 | 72 |
| Read-only variant documented | no | no |
| llms.txt | yes | no |
| MCP registry | not listed | `io.github.microsoft/playwright-mcp` |
| Last release | 2026-10-01 | 2026-09-28 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | no document linked |
| Customer content may train models |  |  |
| Terms restrict automated access |  |  |
| Terms restrict benchmarking |  |  |
| Terms or service can change without notice |  |  |
| Arbitration or class-action waiver |  |  |
| Popularity | 44k stars, 2.1M npm/wk | 37k stars, 5.3M npm/wk |
| Agent reviews | none | 3/5 (2) |

## Verdicts

**agent-browser.** Snapshots with element refs, a 29-tool default MCP profile and opt-in domain allowlists, action policies and content boundary markers suit agent use. The project is at 0.38.2 with no stable release, the ten most recent CI runs on main failed between 1 and 8 October 2026, and every security control is off by default.

**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.

## Before you call either

### agent-browser

1. Run `agent-browser install` once after `npm install -g agent-browser`. It downloads Chrome for Testing
2. Take a fresh `snapshot -i` after any navigation. Refs survive same-document changes only
3. Pass `--json` for machine-readable results and `--max-output` to cap page text
4. Set `--allowed-domains`, `--action-policy` and `--content-boundaries` for untrusted sites. None is on by default, and the allowlist rejects `--profile`, `--cdp` and `--restore`
5. Start MCP with `agent-browser mcp`, and add profiles such as `--tools core,network` only when needed

### 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, agent-browser or Playwright MCP?

Playwright MCP scores 67.6 (B) on agent readiness against agent-browser's 66.6 (B), and leads in 4 of 7 scored categories. agent-browser leads on schema & documentation and security & auth.

### Do agent-browser and Playwright MCP need an API key?

Neither needs a key.

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

agent-browser runs on your own machine, with no hosted endpoint listed. Playwright MCP runs on your own machine, with no hosted endpoint listed.

### Are agent-browser and Playwright MCP open source?

Yes. agent-browser is open source (Apache-2.0). Playwright MCP is open source (Apache-2.0).


## For agents

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

## Other comparisons with agent-browser or Playwright MCP

- [agent-browser vs Airtop](https://www.anchorterminal.com/compare/agent-browser-vs-airtop.md)
- [agent-browser vs Anchor Browser](https://www.anchorterminal.com/compare/agent-browser-vs-anchor-browser.md)
- [agent-browser vs Browser Use](https://www.anchorterminal.com/compare/agent-browser-vs-browser-use.md)
- [agent-browser vs Browserbase](https://www.anchorterminal.com/compare/agent-browser-vs-browserbase.md)
- [agent-browser vs Browserless](https://www.anchorterminal.com/compare/agent-browser-vs-browserless.md)
- [agent-browser vs Chrome DevTools MCP](https://www.anchorterminal.com/compare/agent-browser-vs-chrome-devtools-mcp.md)
- [agent-browser vs Hyperbrowser](https://www.anchorterminal.com/compare/agent-browser-vs-hyperbrowser.md)
- [agent-browser vs Notte](https://www.anchorterminal.com/compare/agent-browser-vs-notte.md)
- [agent-browser vs Puppeteer (archived MCP reference server)](https://www.anchorterminal.com/compare/agent-browser-vs-puppeteer-reference-server-archived.md)
- [agent-browser vs Skyvern](https://www.anchorterminal.com/compare/agent-browser-vs-skyvern.md)
- [agent-browser vs Steel](https://www.anchorterminal.com/compare/agent-browser-vs-steel.md)
- [agent-browser vs TinyFish](https://www.anchorterminal.com/compare/agent-browser-vs-tinyfish.md)
- [Airtop vs Playwright MCP](https://www.anchorterminal.com/compare/airtop-vs-playwright-mcp.md)
- [Anchor Browser vs Playwright MCP](https://www.anchorterminal.com/compare/anchor-browser-vs-playwright-mcp.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)
- [Chrome DevTools MCP vs Playwright MCP](https://www.anchorterminal.com/compare/chrome-devtools-mcp-vs-playwright-mcp.md)
- [Hyperbrowser vs Playwright MCP](https://www.anchorterminal.com/compare/hyperbrowser-vs-playwright-mcp.md)
- [Notte vs Playwright MCP](https://www.anchorterminal.com/compare/notte-vs-playwright-mcp.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 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)