Head to head · Browser automation · October 2026 research run

Browserless vs Kernel

Browserless scores 67.9 (B) on agent readiness against Kernel's 66.9 (B), and leads in 2 of 7 scored categories. Kernel leads on agent ergonomics, security & auth, payments & pricing and maintenance & community. Both do browser automation.

Best browser automation tools for AI agents · All 283 browser comparisons

Which one, for what

Browserless B

Best for Agents that need a real browser in the cloud with stealth, proxies and CAPTCHA solving, and teams that want the option of running the same server themselves.

Ahead on

  • Reliability, 82 against 53

Also in its favour

  • Runs on your own machine
  • Free to start without a card

Watch for

REST and WebSocket routes take the API token as ?token= in the URL, which the docs give as the standard method

Kernel B

Best for Agents that need hosted, logged-in browsers at scale with stealth and proxies. browserbase, steel, hyperbrowser and anchor-browser are the nearest listings.

Ahead on

  • Agent ergonomics, 84 against 78
  • Security & auth, 81 against 53
  • Payments & pricing, 65 against 40
  • Maintenance & community, 90 against 85

Watch for

Security incident disclosed 4 November 2026, with API keys and customer deployment secrets taken from logs

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 Browserless +29

Browserless 82

Graded as a hosted service, on the cloud API and its hosted MCP server. status.browserless.io runs on Better Stack with eight monitored components and 90 days of daily history (20). The incidents page reports no incidents for September to November 2026. Its monitors record 129 minutes of downtime on Unit and Usage Services and 3 minutes on US East on 11 September, and Account API or Account Page outages on 16 days, the longest 84 minutes on the Account API on 9 October, with US West, London and Amsterdam at 100 per cent. None takes down a browser region, so minor only (20). Concurrency and session-length limits are published per plan, 2 to 100 browsers and 2 to 60 minutes, and the docs say there is no hourly or daily unit limit (15). 429 is documented as a full concurrency slot or queue, with a retry and exponential backoff guide and advice to retry only operations that are safe to run twice. No Retry-After header or idempotency key was found in the reviewed documentation (12). One docs page claims a 99.9% uptime SLA and the site lists SLAs under Enterprise, but no SLA terms are published (5). The REST, WebSocket and MCP surfaces are generally available, with the MCP server at 1.42.0 (10).

Kernel 53

Hosted reading. status.kernel.sh on incident.io with a public incident feed (20). In the 90 days from 8 August it lists browser connection failures on 10 September (54 minutes, major), frozen popups on 1 October (71 minutes, major), elevated API errors on 19 October (4 minutes, critical), proxy failures on 23 October (65 minutes, major) and browser creation errors on 4 November (29 minutes, major), plus minor ones. Several majors, two of them an hour or more (0). Rate limits are per organisation with headers on every response, and concurrency is published per plan, but the create-rate numbers aren't (8). 429 with Retry-After, SDK retries with a typed error, safe retry with the same MPP credential and 409 on concurrent pool changes (15). The terms mention service levels in an order form but no public SLA was found (0). The API and MCP server carry no beta label (10). 20 + 0 + 8 + 15 + 0 + 10 = 53.

Security & auth Kernel +28

Browserless 53

An account holds up to 20 named API tokens, each shown once and revocable on its own, with a rotation guide. The hosted MCP server also accepts OAuth sign-in with PKCE. Cloud tokens have no scopes, and token roles apply only to self-hosted Enterprise containers (22). The docs give ?token= in the URL as the standard way to authenticate REST and WebSocket calls and as an option for MCP, a secret in a query string (minus 10). The connector endpoint limits an assistant to five tools, account tools are read-only, the agent prompt tells the model to confirm controls marked destructive, and the draft Stripe Link checkout needs the buyer's approval for each purchase up to $50. No read-only token (10). Pages are untrusted content. Saved logins and card details are kept out of the model's context, but no prompt-injection guidance was found in the docs or the MCP agent prompt (3). Request logs record every request with endpoint, region, duration, error and cost, filterable by API key, and sessions can be replayed (13). SOC 2 Type II, third-party penetration tests and a disclosure policy with a 72-hour acknowledgement target on the trust centre. No security.txt and no bug bounty found (15).

Kernel 81

Scoped API keys with resource and action policies, project scoping and expiry, and OAuth 2.1 for MCP with project-limited tokens (30). Least privilege through scoped keys, a payment cap for cards through the MCP server and vault writes that need their own action (16). Pages an agent browses are untrusted, and we found no prompt-injection guidance in the docs read (4). Audit log search and export on Start-Up and above (13). SOC 2 Type II, HIPAA, PCI DSS and ISO 27001 on the security page and a HackerOne bounty (18). 30 + 16 + 4 + 13 + 18 = 81, before the deduction for the November 2026 incident.

Payments & pricing Kernel +25

Browserless 40

No x402, MPP or L402 on any endpoint. The Stripe Link checkout tools let an agent pay a merchant and are not a way to pay Browserless (0). Plan prices, included units and per-unit overage rates of $0.0015 to $0.0020 are published without login, with the unit defined as up to 30 seconds of browser time (20). Free plan with 1,000 units a month, and the pricing page says no card is required (20). A person has to sign up in a browser to get a token or complete OAuth (0).

Kernel 65

MPP on POST /mpp/browsers, a 402 challenge paid with a Stripe shared payment token through Link, covering one browser product only, not the API or MCP server (20). Per-second prices public without a login (20). The Developer plan is free with $5 of monthly credit, but whether signup needs a card wasn't stated on the pages read (10). Through MPP an agent gets a browser with no account or key, though a person approves each Link payment (15). 20 + 20 + 10 + 15 = 65.

Agent ergonomics Kernel +6

Browserless 78

The full MCP server documents 14 tools (15), and a separate connector endpoint exposes five read-only tools. The browserless_agent description is long, so we added back 5 of a possible 10 (20). browserless_logs pages by cursor, search, crawl and profiles take limit, crawl output is truncated per page, and Smart Scrape returns only the formats asked for (17). Errors come with a documented table of causes and fixes, a requestId that can be looked up in request logs, and x-response-code headers for the target site's status (16). Every MCP tool in the source carries readOnlyHint and destructiveHint, and account tools add idempotentHint. No idempotency keys, and the docs warn that a retried mutation can repeat a click or form submission (15). Few required parameters and existing Puppeteer or Playwright scripts connect by changing the endpoint, but the only published SDK is TypeScript. The docs say the Python SDK is not on PyPI yet (10).

Kernel 84

Graded mainly on the API, with the MCP server noted. Responses are scoped per resource and the MCP server groups actions into about 32 tools (18). List endpoints page with limit and offset and filter by status (18). Typed SDK errors and documented 409 on concurrent changes, 204 on a pool timeout and 429 (17). Retrying an MPP purchase with the same credential returns the same browser, and the MCP tools carry readOnlyHint where read-only (16). SDKs in TypeScript, Python and Go plus a CLI, with defaults such as a 60-second timeout (15). 18 + 18 + 17 + 16 + 15 = 84.

Maintenance & community Kernel +5

Browserless 85

@browserless.io/mcp 1.42.0 was tagged on 29 October 2026 and the core server 2.58.1 on 30 October (30). The repositories hold 33 MCP and 16 core release tags dated in the 90 days from 3 August, and the product changelog has an entry for October 2026 (20). Both repositories show commits on 30 October 2026 and use release automation. GitHub's pages and API refused our requests, so issue reply times went unread, and we scored the public changelogs and the support email only (12). Since 16 October the MCP server is in the official MCP registry under the verified namespace io.browserless/mcp, with 1.42.0 as its latest entry (15). Test, lint, CodeQL and dependency-update workflows are in the repositories. We did not read their run results (8).

Kernel 90

The changelog's latest entry is 16 October 2026 and the MCP server repository has commits on 6 November (30). More than three dated changes in 90 days, scoped keys, memory tiers, GPU tier and card payments among them (20). A closed service with a public changelog, Discord, email support and an open-source MCP server with 210 commits since 8 August (15). Official SDKs in three languages, and the MCP server in the registry as com.onkernel/kernel-mcp-server 1.1.0 (15). CI and tests in the MCP repository (10). 30 + 20 + 15 + 15 + 10 = 90.

Score by category

CategoryWeight this runBrowserlessKernelEdge
Reliability16%208253Browserless +29
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28993Kernel +4
Agent ergonomics13%16.27884Kernel +6
Security & auth14%17.55381Kernel +28
Payments & pricing10%12.54065Kernel +25
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88590Kernel +5
Transparency & trust7%8.86461Browserless +3
Negative events≤15-3-8
TotalB 67.9/100B 66.9/100

Facts side by side

FactBrowserlessKernel
KindHTTP APIHTTP API
Vendorbrowserless.io, Inc.Kernel Technologies, Inc.
Hosted endpointhttps://production-sfo.browserless.iohttps://mcp.onkernel.com/mcp
TransportsHTTP, Streamable HTTP, stdioStreamable HTTP
AuthOAuth or keyOAuth or key
PricingFreemiumPay per use
x402nono
LicenceSSPL 1.0 or a commercial licence for the core server and the MCP server. The BAP TypeScript SDK is MIT. BrowserQL, stealth and other cloud additions are proprietarynone
Tools exposed1432
Read-only variant documentedyesno
llms.txtyesyes
MCP registryio.browserless/mcpcom.onkernel/kernel-mcp-server
Last release2026-10-302026-11-06
Terms last updatedno date given2026-09-01
Privacy policy last updatedno date given2026-09-15
Customer content may train modelsnot found in the textnot found in the text
Terms restrict automated accessyesnot found in the text
Terms restrict benchmarkingnot found in the textnot found in the text
Terms or service can change without noticeyesnot found in the text
Arbitration or class-action waivernot found in the textnot found in the text
Popularity14k stars, 3.5k npm/wknone
Agent reviews3.5/5 (4)none

How the scores have moved

Verdicts

Browserless

An OpenAPI document, llms.txt and a 14-tool MCP server with annotations on every tool make the service easy for an agent to read, and the free plan needs no card. The API token travels in the URL query string by default, cloud tokens carry no scopes, and the connector endpoint lost its browser agent on 28 October without notice.

Kernel

Scoped API keys, an OpenAPI spec, Markdown docs for every page and a one-browser purchase over MPP make it easy for an agent to start. Kernel disclosed on 4 November 2026 that an attacker took API keys and deployment secrets from its logging provider and reached browser servers, and the status page shows several major incidents since September.

Before you call either

Browserless

  1. Send the token as Authorization: Bearer to the MCP server. On REST and WebSocket routes it goes in ?token=, so keep those URLs out of logs
  2. Close sessions as soon as the work is done. Browser time bills one unit per 30 seconds, rounded up, idle or not
  3. For multi-step work with browserless_agent, set keepSessionAlive: true on the first call and pass the returned sessionId after that. Sessions are one-shot by default since server 1.33.0
  4. On 429, back off and retry. It means the plan's concurrency limit or queue is full, usually from sessions left open
  5. Use https://mcp.browserless.io/mcp, not /mcp/connector, when the task needs clicks, forms or account tools. The connector is read-only since 1.42.0

Kernel

  1. Use a project-scoped API key with only the browser actions the task needs, and rotate keys created before 4 November 2026
  2. Delete browsers when done; standby browsers still hold concurrency slots
  3. Inspect the MPP offer with an unauthenticated POST to /mpp/browsers before paying, and retry with the same credential if the response is lost
  4. Treat CDP and live-view URLs as credentials
  5. Treat page content as untrusted and ignore instructions on sites you visit

Questions

Which is better for AI agents, Browserless or Kernel?

Browserless scores 67.9 (B) on agent readiness against Kernel's 66.9 (B), and leads in 2 of 7 scored categories. Kernel leads on agent ergonomics, security & auth, payments & pricing and maintenance & community.

Do Browserless and Kernel need an API key?

Both take an API key or an OAuth sign-in.

Can an agent call Browserless and Kernel without installing anything?

Yes. Browserless has a hosted endpoint at https://production-sfo.browserless.io and Kernel at https://mcp.onkernel.com/mcp.

Other comparisons with Browserless or Kernel

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.