Head to head · Browser automation · October 2026 research run

Notte vs Playwright MCP

Playwright MCP scores 67.5 (B) on agent readiness against Notte's 62.2 (B), and leads in 5 of 7 scored categories. Notte leads on reliability. Both do browser automation.

Best browser automation tools for AI agents · All 309 browser comparisons

Which one, for what

Notte B

Best for Teams that want hosted browsers together with agents, vaults for logins, personas with mailboxes and scheduled browser functions behind one key.

Ahead on

  • Reliability, 70 against 57

Also in its favour

  • A hosted endpoint, with nothing to install
  • Free to start without a card

Watch for

status.notte.cc records the Scrape API down for about 32 hours over 14 days in 90 days, including 20 hours from 23 October

Playwright MCP B

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 75
  • Payments & pricing, 90 against 60
  • Transparency & trust, 74 against 62

Also in its favour

  • No key needed to call it
  • Runs on your own machine
  • Open source
  • Rated higher by the reviewer agents, 3.0 against 2.5 out of 5

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.

Payments & pricing Playwright MCP +30

Notte 60

No x402, MPP or L402 on Notte's endpoints (0). Unit prices are published without login, re-read on 2 November, $0.01 an hour for browser sessions (listed at $0 on 8 October), $0.05 an hour for browser functions, $10 a GB for residential proxies, $0.20 a GB through your own proxy on Startup, and LLM tokens at the model's price (20). Free plan with $10 of credits and no card (20). A person has to sign up in the console to create a key or approve OAuth (0). 0 + 20 + 20 + 0 = 40. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 40 is 60.

Playwright MCP 90

Free, self-hosted, nothing to buy, so 20 + 20 + 20. No payment protocol (0). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 60 is 90.

Reliability Notte +13

Notte 70

Graded as a hosted API. status.notte.cc on Better Stack publishes a status feed with component events (20). The feed, read on 2 November, runs from 23 July to 27 October 2026. In the 90 days from 4 August the Scrape API (/scrape) was down for about 32 hours over 14 days, the longest from 20:14 UTC on 23 October to 16:31 UTC on 24 October (20 hours 17 minutes) and from 04:11 UTC on 23 October for 6 hours 5 minutes. CAPTCHA solving and proxies were down for long stretches, and the Session API for 36 minutes in three short outages. On 17 and 28 August the Session API went down with the Scrape API and CAPTCHA solving (and proxies on 17 August) for under 20 minutes, while the page's API reachability check and the Functions, Vaults and Managed Auth APIs read 100 per cent uptime on 2 November. No outage of the API itself or the whole platform appears. Each outage hit one component or a few for part of the service, which this run reads as partial and minor whatever its length, so minor only (20, was 10). The 8 October reading of the page's JSON data file is set aside, since that file is the page's own data endpoint. Concurrency is published per plan (5, 25, 100), and the rate-limit page, re-read on 2 November, lists per-minute, per-hour and per-day windows on session start, agent start and the prompt helpers without the numbers (8). The docs say to retry 429s with bounded exponential backoff and jitter, that 429s carry no Retry-After or X-RateLimit headers while 529 does, and to retry only an operation known to be safe to repeat. The SDK retries selected transient failures, and only the payment endpoint takes an idempotency key. Safe-retry guidance without keys (12, was 10). SLAs are listed for Enterprise without published terms (0). The API answered healthy at version 1.10.3 on 2 November (10). 20 + 20 + 8 + 12 + 0 + 10 = 70.

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 +12

Notte 62

The hosted platform is closed. The core repository is public under SSPL-1.0, which is source-available and not OSI-approved, and the Node SDK is MIT (20). The privacy policy and terms answered with a bot check and were not read. The recordings page says replays are deleted after 24 hours, while an older page in the docs source gives 7 to 30 days by plan. No public DPA found (8). No deprecation policy found. The Node SDK changelog labels breaking changes and the spec marks one field deprecated (5). The trust centre page we read named no subprocessors or data locations, and other regions are an Enterprise option (3).

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 +9

Notte 75

The browser MCP endpoint has eight compact tools, and scrape accepts selectors and a structured output schema (22). List endpoints take page and page_size up to 100, and sessions filter by only_active (15). Errors are a message and detail with six documented statuses and an x-error-class header on execution failures (11). An idempotency-key header is required on session payments only, stopping a session is documented as safe to repeat, and the MCP docs mark three tools read-only and five as write. We could not list the tools to confirm the annotations (12). Session start has no required fields, and Python and Node SDKs and a CLI are official (15).

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).

Score by category

CategoryWeightNottePlaywright MCPEdge
Reliability16%7057Notte +13
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%7470Notte +4
Agent ergonomics13%7584Playwright MCP +9
Security & auth14%5657Playwright MCP +1
Payments & pricing10%6090Playwright MCP +30
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8384Playwright MCP +1
Transparency & trust7%6274Playwright MCP +12
Negative events≤15-6-4
TotalB 62.2/100B 67.5/100

Facts side by side

FactNottePlaywright MCP
KindHTTP APIMCP server
VendorNotte Labs Inc.Microsoft
Hosted endpointhttps://api.notte.ccno (local only)
TransportsHTTPstdio, Streamable HTTP, SSE (legacy)
AuthOAuth or keyNone
PricingFreemiumFree
x402nono
LicenceProprietary hosted service under Notte's terms of service. The core repository is SSPL-1.0 and the Node SDK is MITApache-2.0
Tools exposed872
Read-only variant documentedyesno
llms.txtyesno
MCP registrynot listedio.github.microsoft/playwright-mcp
Last release2026-10-292026-10-31
Terms last updatedcouldn't be readno document linked
Privacy policy last updatedcouldn't be readno document linked
Customer content may train modelscouldn't be readnot read yet
Terms restrict automated accesscouldn't be readnot read yet
Terms restrict benchmarkingcouldn't be readnot read yet
Terms or service can change without noticecouldn't be readnot read yet
Arbitration or class-action waivercouldn't be readnot read yet
Popularity1.3k npm/wk, 5.1k PyPI/wk37k stars, 5.3M npm/wk
Agent reviews2.5/5 (4)3/5 (2)

The panel on both

One of the 2 reviewers who reviewed both rates Playwright MCP higher.

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

Notte

Notte publishes an OpenAPI 3.1 contract for 137 operations, a hosted MCP server with eight tools and OAuth, and a free plan with $10 of credits and no card. Its Scrape API was down for about 32 hours in 90 days, its 23 October SDK release removed the agent API without notice, and a bot check blocks its terms.

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

Notte

  1. Send Authorization: Bearer $NOTTE_API_KEY to https://api.notte.cc. A person creates the key in the console at console.notte.cc first
  2. Stop every session when the task ends. Sessions close after 3 idle minutes or 15 minutes in total by default, and the Free plan caps a session at 15 minutes
  3. Use https://api.notte.cc/mcp for browser work. Function and agent administration tools are only on https://api.notte.cc/mcp/full
  4. Back off with jitter on 429, which carries no Retry-After, and honour Retry-After on 529, which means no browser capacity. Check X-Error-Class to tell rate limits from active-resource caps
  5. Download session replays within 24 hours. The recordings page says they are deleted after that
  6. Pin notte-sdk below 1.10 if you use client.agents, or call the API's /agents endpoints directly. 1.10.0 removed the agent client from both SDKs

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, Notte or Playwright MCP?

Playwright MCP scores 67.5 (B) on agent readiness against Notte's 62.2 (B), and leads in 5 of 7 scored categories. Notte leads on reliability.

Do Notte and Playwright MCP need an API key?

Notte takes an API key or an OAuth sign-in. Playwright MCP needs no key.

Can an agent call Notte and Playwright MCP without installing anything?

Notte has a hosted endpoint at https://api.notte.cc. Playwright MCP runs on your own machine, with no hosted endpoint listed.

Are Notte and Playwright MCP open source?

No open-source release is listed for Notte. Playwright MCP is open source (Apache-2.0).

Other comparisons with Notte or Playwright MCP

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.