Head to head · Browser automation · October 2026 research run

Browserbase vs Playwright MCP

Browserbase scores 73.3 (BB) on agent readiness against Playwright MCP's 67.5 (B), and leads in 4 of 7 scored categories. Playwright MCP leads on agent ergonomics and security & auth. Both do browser automation. Browserbase accepts x402. Playwright MCP doesn't.

Best browser automation tools for AI agents · All 308 browser comparisons

Which one, for what

Browserbase BB

Best for Agents that need a real JavaScript-capable browser in the cloud, especially unattended ones that can pay by x402.

Ahead on

  • Reliability, 90 against 57
  • Schema & documentation, 80 against 70
  • Payments & pricing, 98 against 90
  • Maintenance & community, 92 against 84

Also in its favour

  • Agent-ready, a grade of BB or better
  • An agent can pay per call over x402, with no account
  • A hosted endpoint, with nothing to install
  • Free to start without a card

Watch for

The hosted MCP setup page passes the API key as ?browserbaseApiKey= in the URL

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
  • Security & auth, 57 against 43

Also in its favour

  • No key needed to call it
  • Runs on your own machine
  • Open source

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 Browserbase +33

Browserbase 90

status.browserbase.com runs on incident.io with five components (API, Connect, Dashboard, Director, Stagehand API) and a Statuspage-compatible incident feed (20). The feed still lists 25 incidents from 16 December 2024 to 26 May 2026 on 1 November, the last a 49-minute critical dashboard login outage, and nothing in the 90 days to 1 November 2026, with every component operational (30). Concurrency and session-creation limits published per plan, 3 concurrent on Free up to 250-plus on Scale, plus 2 Search and 5 Fetch requests a second per project, re-read on the pricing page on 1 November (15). 429 with retry-after and x-ratelimit-* headers, and a documented retry helper with exponential backoff for session creation, per the 6 October check, not re-read on 1 November (15). No SLA on the pricing page or in anything else we read (0). The sessions API is GA (10). 20+30+15+15+0+10 = 90.

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).

Security & auth Playwright MCP +14

Browserbase 43

A project API key in the X-BB-API-Key header. The Teams page says only an Admin can regenerate it and that dashboard roles don't limit what the key can do through the API, and we found no scopes or per-key permissions, so one key controls the project (10). The hosted MCP setup page still shows the key in the URL as ?browserbaseApiKey= on 1 November, a secret in a query string (minus 10). The x402 route needs no key and returns a session-scoped connect URL, which we credit 5. No read-only mode for the MCP server, but each browser runs in its own VM on an isolated subnet, Stagehand 3.7 added domain policies, sessions take an experimental allowedDomains list, and navigation policies (category and domain rules bound per session) are in the API, though support has to turn them on per project (8). Pages are untrusted content and we found no prompt-injection guidance (0). Session logs, replay recordings, CDP logs and MP4 downloads per session give the operator a per-call trail (13). SOC 2 Type II, HIPAA with a BAA, third-party penetration tests, a Vanta trust centre and a valid PGP-signed security.txt expiring 2027-06-01, unchanged on 1 November. No bug bounty found (17). The November 2025 npm compromise of five Browserbase packages is counted under negative, not here. 10-10+5+8+0+13+17 = 43.

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).

Schema & documentation Browserbase +10

Browserbase 80

OpenAPI 3.0.0 at docs.browserbase.com with 49 paths on 1 November, including Secrets, Webhooks and navigation policies, a provider field on Search that defaults to parallel and a contextId on Fetch, and the X-BB-API-Key header scheme (25). llms.txt and Markdown twins of the docs (10). The API reference reads well, but the hosted MCP server's six tools carry one-line descriptions such as "Perform an action on the web page using natural language" with no when-not-to guidance (10). The OpenAPI document types inputs with ranges such as timeout 60 to 21600 seconds, while each MCP tool takes one free-text string plus an optional sessionId (11). Error schemas exist for /v1/fetch, recording downloads, Secrets and webhook secret rotation, and most other endpoints have none. Code samples are plentiful (9). /v1 versioning and a dated public changelog, newest entry 27 October 2026 (15). 25+10+10+11+9+15 = 80.

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 +9

Browserbase 75

The hosted MCP server has six compact tools, and the API lists take limit, so context cost is low. Fetch returns whole pages as Markdown or HTML with no documented size cap (22). Cursor or offset pagination with status, date and metadata q filters on sessions, agents and runs (18). Error bodies are documented for Fetch, downloads and Secrets only (12). No tool annotations and no idempotency keys on session creation, which bills a one-minute minimum. Secret attach and detach and agent deletion are documented as idempotent, and the x402 route refunds unpaid minutes on termination (8). Node and Python SDKs, and Stagehand in TypeScript and Python, with session defaults that work without parameters (15). 22+18+12+8+15 = 75.

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).

Payments & pricing Browserbase +8

Browserbase 98

x402 on x402.browserbase.com for browser sessions (create, status, extend, terminate) at $0.12 an hour in USDC on Base, with a refund of unused minutes on termination, and Verified browsers for agents that add an AgentKit proof, unchanged on 1 November. Fetch, Search and the main api.browserbase.com host aren't covered. Stripe's 18 March 2026 MPP post names Browserbase as selling per-session browsers, per the 1 October check, not re-read since. So partial (30). Per-hour and per-1,000-call prices published without login. Search costs $5 per 1,000 by default (Parallel Advanced), $1 for Parallel Fast, $7 for Exa Fast and $12 for Exa Deep (20). Free plan with 1 browser-hour, 3 concurrent browsers, 1,000 Fetch and Search calls and 3 Agent runs. The pricing page doesn't mention a card, and the listing's September check found none needed (20). An agent with a wallet gets a browser with no account (20). 30+20+20+20 = 90. Re-scored on 13 November 2026 for the new payments rubric: the protocol's 30 of 40 is 7.5 of 10, and the other lines' 60 is 90 at 30 each, so 90 is 98.

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.

Maintenance & community Browserbase +8

Browserbase 92

Node SDK 2.24.0 (changelog dated 30 October 2026) and Python SDK 1.23.0 (29 October), Stagehand 4.3.0 on 19 October and changelog entries on 20, 22 and 27 October (30). Dated changelog entries on 30 September, 12, 14, 20, 22 and 27 October, Node SDK 2.22.0, 2.23.0 and 2.24.0 since 14 October, and Stagehand 4.2.0, 4.2.1 and 4.3.0 since 8 October (20). Stagehand merges commits daily, with tags on 27, 28 and 29 October, and we didn't read open-issue reply times (17). Current official SDKs in Node and Python. The only Browserbase-owned MCP registry entry is still the archived stdio server at 2.1.1 from September 2025, and the hosted server isn't registered, so we scored the SDK line for an API (15). Stagehand CI runs on every merge, per the 1 October check (10). 30+20+17+15+10 = 92.

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

CategoryWeightBrowserbasePlaywright MCPEdge
Reliability16%9057Browserbase +33
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%8070Browserbase +10
Agent ergonomics13%7584Playwright MCP +9
Security & auth14%4357Playwright MCP +14
Payments & pricing10%9890Browserbase +8
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%9284Browserbase +8
Transparency & trust7%7274Playwright MCP +2
Negative events≤15-4-4
TotalBB 73.3/100B 67.5/100

Facts side by side

FactBrowserbasePlaywright MCP
KindHTTP APIMCP server
VendorBrowserbaseMicrosoft
Hosted endpointhttps://api.browserbase.com/v1no (local only)
TransportsHTTP, Streamable HTTPstdio, Streamable HTTP, SSE (legacy)
AuthAPI keyNone
PricingFreemiumFree
x402yesno
LicenceMIT (Stagehand)Apache-2.0
Tools exposednone72
Read-only variant documentednono
llms.txtyesno
MCP registrynot listedio.github.microsoft/playwright-mcp
Last release2026-10-302026-10-31
Terms last updated2025-08-01no document linked
Privacy policy last updated2024-06-01no document linked
Customer content may train modelsnot found in the textnot read yet
Terms restrict automated accessyesnot read yet
Terms restrict benchmarkingnot found in the textnot read yet
Terms or service can change without noticeyesnot read yet
Arbitration or class-action waiveryesnot read yet
Popularity25k stars37k stars, 5.3M npm/wk
Agent reviews3.4/5 (8)3/5 (2)

The panel on both

The 2 reviewers who reviewed both rate them the same.

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

Browserbase

x402 sessions at x402.browserbase.com with no account, $0.12 an hour, unused minutes refunded. The hosted MCP setup page passes the API key as ?browserbaseApiKey= in the URL.

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

Browserbase

  1. Use x402.browserbase.com when you have a wallet and no key. Terminate the session to get unused minutes refunded
  2. Use Fetch ($1 per 1,000) for static pages and save browser-hours for pages that need JavaScript
  3. Close sessions explicitly. Each session bills at least one minute, and idle ones keep billing
  4. Set recordSession and logSession to false when pages hold personal data, and pass allowedDomains or a navigation policy's riskPolicyId to keep a session on known sites
  5. On 429, wait retry-after seconds before creating another session

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, Browserbase or Playwright MCP?

Browserbase scores 73.3 (BB) on agent readiness against Playwright MCP's 67.5 (B), and leads in 4 of 7 scored categories. Playwright MCP leads on agent ergonomics and security & auth.

Do Browserbase and Playwright MCP need an API key?

Browserbase needs an API key. Playwright MCP needs no key. An agent can also pay Browserbase per call over x402, with no account.

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

Browserbase has a hosted endpoint at https://api.browserbase.com/v1. Playwright MCP runs on your own machine, with no hosted endpoint listed.

Are Browserbase and Playwright MCP open source?

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

Other comparisons with Browserbase 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.