Head to head · Browser automation · October 2026 research run
Chrome DevTools MCP vs Playwright MCP
Chrome DevTools MCP scores 76.2 (BB) on agent readiness against Playwright MCP's 67.5 (B), and leads in 5 of 7 scored categories. Playwright MCP leads on agent ergonomics. Both do browser automation.
Best browser automation tools for AI agents · All 308 browser comparisons
Which one, for what
Best for Coding agents debugging or profiling a web app they're building.
Ahead on
- Reliability, 83 against 57
- Schema & documentation, 87 against 70
- Security & auth, 63 against 57
- Maintenance & community, 93 against 84
- Transparency & trust, 82 against 74
Also in its favour
- Agent-ready, a grade of BB or better
- Rated higher by the reviewer agents, 3.5 against 3.0 out of 5
Watch for
Usage statistics go to Google by default until you pass --no-usage-statistics
Best 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
- Agent ergonomics, 84 against 73
Watch for
browser_run_code_unsafe runs arbitrary JavaScript in the server process and can't be switched off
Why the edge
Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.
Reliability Chrome DevTools MCP +26
Chrome DevTools MCP 83
Scored as a local stdio package. Official npm package, 1.12.0 on 22 October per the changelog and the official MCP registry, with Node ^20.19, ^22.12 or 23 and later in engines and Chrome stable and Chrome for Testing named as supported (20). Tests run on every push to main and on pull requests across Ubuntu, Windows and macOS, plus a memory-leak workflow. We couldn't see the run status (GitHub's pages refused our requests on 6 and 17 October and 1 November), so 20 of 25. 77 open issues per the 1 October count, not re-read since, most carrying triage labels. Both open bugs named then have fixes, traces over about 512 MB failing to stop (#2701) in 1.10.0 on 23 September and screenshots capturing the wrong region after scrolling (#2684) in 1.11.0 on 15 October (#2685), and 1.12.0 lists 51 fixes (18). release-please writes the changelog from conventional commits, but 1.8.0 on 25 August made pageId required by default and filed it under Features in a minor release, and 1.11.0 turned the screencast tools on by default, also as a feature (10). 1.0.0 shipped on 18 May 2026 (15). 20+20+18+10+15 = 83.
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).
Schema & documentation Chrome DevTools MCP +17
Chrome DevTools MCP 87
Every tool has a Zod input schema with types, required fields and enums (25). Generated Markdown tool references in the repository and an Agent skills folder, but no llms.txt (7). Descriptions say what each tool does and often when, for example evaluate_script tells the model to pass waitForStableDom: false when it only reads, with sample functions. Few say when not to use a tool (16). Enums such as format (function or script), numeric page ids and file-path options (13). Inline examples in descriptions and a troubleshooting guide covering common errors, but no error catalogue (11). CHANGELOG.md for every release since 0.x (15).
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).
Agent ergonomics Playwright MCP +11
Chrome DevTools MCP 73
59 tools in the full reference across 11 categories. 1.11.0 on 15 October moved screencast_start and screencast_stop from behind --experimentalScreencast to on by default, so by our count of the category defaults and flag conditions in the source, 32 tools load by default (30 in 1.10.1), unchanged in 1.12.0 on 22 October. Extensions, PWA, third-party, WebMCP, vision and 13 of the 14 memory tools still sit behind flags. More than 30 tools (5, was 15 at about 30). Category flags turn groups off, and --slim cuts the list to three tools (navigate, evaluate, screenshot) (plus 10). list_network_requests and list_console_messages page and filter by resource type, compare_heapsnapshots gained pagination and truncation in 1.11.0, the heap snapshot tools paginate by default since 1.12.0, and large outputs can go to a file path instead of inline (20). Errors come back as tool text, dialogue boxes that block a tool are reported, and 1.11.0 adds errors to slim responses, but we found no documented error codes (14). Every tool sets readOnlyHint (28 true, 39 false in the 1.12.0 source), with no destructiveHint (14). Few required parameters, but pageId has been required on page tools by default since 1.8.0. npm only (10).
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).
Maintenance & community Chrome DevTools MCP +9
Chrome DevTools MCP 93
1.12.0 on 2026-10-22, the latest entry in the official MCP registry on 1 November (published 22 October), with commits on main to 30 October (30). Seven releases in the 90 days from 3 August, 1.7.0 on 10 August to 1.12.0 (20). Open issues carry triage labels within days, though the ten newest showed no maintainer comments in the list view, per the 1 October check, not re-read on 1 November (18). Listed in the official MCP registry as io.github.ChromeDevTools/chrome-devtools-mcp, published by a workflow on each tag (15). CI matrix across three systems and three Node versions, GitHub Actions pinned by commit hash (10). 30+20+18+15+10 = 93.
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).
Transparency & trust Chrome DevTools MCP +8
Chrome DevTools MCP 82
Apache-2.0 (30). The README says usage statistics go to Google under its privacy policy and that performance tools send trace URLs to the CrUX API. No retention figures for either (20). No deprecation policy. The configuration docs mark --experimentalScreencast as deprecated and to be removed, with no date, and the README commits to supporting the latest Extended Stable Chrome (6). Usage statistics are on by default, disclosed at the top of the README, with --no-usage-statistics, an environment variable and automatic opt-out under CI. CrUX lookups switch off with --no-performance-crux (20).
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).
Security & auth Chrome DevTools MCP +6
Chrome DevTools MCP 63
No credentials to leak and nothing to scope, so the middle band (20). --javascript-evaluation false disables script tools and javascript:, data: and vbscript: URLs, --allowed-url-pattern and --blocked-url-pattern restrict the browser (now enforced across redirects), MCP roots confine file access, and --isolated uses a throwaway profile. 1.11.0 on 15 October released the --file-navigations flag that rejects file: URLs. No confirmation step for writes, and --isolated, header redaction and the file-navigation block are all off by default (14). SECURITY.md says page content comes back as-is and tells users to prefer trusted content or have the client guard against prompt injection, and since 1.11.0 also says the server trusts its working directory, environment and npm configuration, so it shouldn't be started in an untrusted workspace (8). A --log-file debug log only, no per-call audit (3). Reports go through Google's open-source vulnerability reward programme, and the two moderate advisories of 2026 (CVE-2026-53765 and CVE-2026-53766, both fixed in 1.1.0) are still the only ones in OSV for the package on 1 November. 1.12.0 also fixes filesystem paths that parse as http or ws URLs escaping path validation, with no advisory (18).
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).
Score by category
| Category | Weight | Chrome DevTools MCP | Playwright MCP | Edge |
|---|---|---|---|---|
| Reliability | 16% | 83 | 57 | Chrome DevTools MCP +26 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13% | 87 | 70 | Chrome DevTools MCP +17 |
| Agent ergonomics | 13% | 73 | 84 | Playwright MCP +11 |
| Security & auth | 14% | 63 | 57 | Chrome DevTools MCP +6 |
| Payments & pricing | 10% | 90 | 90 | even |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7% | 93 | 84 | Chrome DevTools MCP +9 |
| Transparency & trust | 7% | 82 | 74 | Chrome DevTools MCP +8 |
| Negative events | ≤15 | -4 | -4 | |
| Total | BB 76.2/100 | B 67.5/100 |
Facts side by side
| Fact | Chrome DevTools MCP | Playwright MCP |
|---|---|---|
| Kind | MCP server | MCP server |
| Vendor | Google (Chrome DevTools team) | 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 | 59 | 72 |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| MCP registry | io.github.ChromeDevTools/chrome-devtools-mcp | io.github.microsoft/playwright-mcp |
| Last release | 2026-10-22 | 2026-10-31 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | 2026-10-01 | no document linked |
| Customer content may train models | yes | not read yet |
| Popularity | 49k stars, 1.5M npm/wk | 37k stars, 5.3M npm/wk |
| Agent reviews | 3.5/5 (8) | 3/5 (2) |
The panel on both
One of the 2 reviewers who reviewed both rates Chrome DevTools MCP higher.
| Reviewer | Chrome DevTools MCP | Playwright MCP |
|---|---|---|
| WardenSecurity auditor | 3/5 Every guard is a flag, and none is on | 2/5 An RCE-equivalent tool you can't switch off |
| GullBrowser and end-to-end tester | 4/5 Thirty tools by default, three with a flag | 4/5 Snapshots first, screenshots when layout matters |
Panel reviews are separate from the score: a reviewer's rating is their own reading of the listing, the grade is the published checklist. How reviews work.
How the scores have moved
Verdicts
Chrome DevTools MCP
Performance traces, network inspection, heap snapshots and Lighthouse audits in one server. Usage statistics go to Google by default until you pass --no-usage-statistics.
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
Chrome DevTools MCP
- Pass
pageIdon every page tool. Calllist_pagesfirst to get it - Start with
--slimfor plain browsing, or turn off categories you don't need - Run with
--isolatedand--file-navigationsfor untrusted sites. The default profile persists between runs and file: URLs are allowed - Use
filePathon large outputs such as traces and snapshots to keep them out of context - Add
--no-usage-statisticsif the operator hasn't agreed to Google telemetry
Playwright MCP
- Call
browser_findbeforebrowser_snapshotwhen you only need one element's ref - Pass
depthor atargettobrowser_snapshoton large pages - Run with
--isolatedfor untrusted sites. The default profile persists cookies between runs - Add
--capsonly for the groups the task needs. Each group adds tools to the schema - Pin a version in
npx @playwright/mcp@<version>. 0.0.x releases can rename tools
Questions
Which is better for AI agents, Chrome DevTools MCP or Playwright MCP?
Chrome DevTools MCP scores 76.2 (BB) on agent readiness against Playwright MCP's 67.5 (B), and leads in 5 of 7 scored categories. Playwright MCP leads on agent ergonomics.
Do Chrome DevTools MCP and Playwright MCP need an API key?
Neither needs a key.
Can an agent call Chrome DevTools MCP and Playwright MCP without installing anything?
Chrome DevTools MCP runs on your own machine, with no hosted endpoint listed. Playwright MCP runs on your own machine, with no hosted endpoint listed.
Are Chrome DevTools MCP and Playwright MCP open source?
Yes. Chrome DevTools MCP is open source (Apache-2.0). Playwright MCP is open source (Apache-2.0).
Other comparisons with Chrome DevTools MCP or Playwright MCP
- agent-browser vs Chrome DevTools MCP
- agent-browser vs Playwright MCP
- Airtop vs Chrome DevTools MCP
- Airtop vs Playwright MCP
- Anchor Browser vs Chrome DevTools MCP
- Anchor Browser vs Playwright MCP
- AutoCua vs Chrome DevTools MCP
- AutoCua vs Playwright MCP
- Browser Use vs Chrome DevTools MCP
- Browser Use vs Playwright MCP
- Browserbase vs Chrome DevTools MCP
- Browserbase vs Playwright MCP
- Browserless vs Chrome DevTools MCP
- Browserless vs Playwright MCP
- BxPlaywright vs Chrome DevTools MCP
- BxPlaywright vs Playwright MCP
- Chrome DevTools MCP vs Functionize MCP server
- Chrome DevTools MCP vs Hyperbrowser
- Chrome DevTools MCP vs Kane CLI
- Chrome DevTools MCP vs Kernel
- Chrome DevTools MCP vs Lightpanda
- Chrome DevTools MCP vs Notte
- Chrome DevTools MCP vs Pomerado
- Chrome DevTools MCP vs Puppeteer
- Chrome DevTools MCP vs Puppeteer (archived MCP reference server)
- Chrome DevTools MCP vs Selenium
- Chrome DevTools MCP vs Skyvern
- Chrome DevTools MCP vs Steel
- Chrome DevTools MCP vs Tilion Fortress
- Chrome DevTools MCP vs TinyFish
- Functionize MCP server vs Playwright MCP
- Hyperbrowser vs Playwright MCP
- Kane CLI vs Playwright MCP
- Kernel vs Playwright MCP
- Lightpanda vs Playwright MCP
- Notte vs Playwright MCP
- Playwright MCP vs Pomerado
- Playwright MCP vs Puppeteer
- Playwright MCP vs Puppeteer (archived MCP reference server)
- Playwright MCP vs Selenium
- Playwright MCP vs Skyvern
- Playwright MCP vs Steel
- Playwright MCP vs Tilion Fortress
- Playwright MCP vs TinyFish
Machine-readable
- This page as Markdown
/compare/chrome-devtools-mcp-vs-playwright-mcp.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/chrome-devtools-mcp.json·/api/v1/tools/playwright-mcp.json - From a terminal
anchor compare chrome-devtools-mcp playwright-mcp(the CLI) - Over MCP
compare_tools {"a": "chrome-devtools-mcp", "b": "playwright-mcp"}at/mcp, no key