Head to head · Browser automation · October 2026 research run
Playwright MCP vs Skyvern
Playwright MCP scores 67.5 (B) on agent readiness against Skyvern's 58.5 (C), and leads in 2 of 7 scored categories. Skyvern leads on reliability and schema & documentation. Both do browser automation.
Best browser automation tools for AI agents · All 309 browser comparisons
Which one, for what
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 76
- Payments & pricing, 90 against 24
Also in its favour
- No key needed to call it
Watch for
browser_run_code_unsafe runs arbitrary JavaScript in the server process and can't be switched off
Skyvern C
Best for Agents that must finish a multi-step job on sites with logins, 2FA and forms, where stored credentials, saved workflows and cached scripts matter more than raw browser time.
Ahead on
- Reliability, 67 against 57
- Schema & documentation, 88 against 70
Also in its favour
- A hosted endpoint, with nothing to install
Watch for
Every API key and OAuth token has full organisation authority. The docs state there are no read-only, per-endpoint or per-agent keys
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 +66
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.
Skyvern 24
No x402, MPP or L402 in the docs, llms.txt or pricing page (0). The billing docs now publish unit prices, one credit $0.001, an action 30 credits ($0.03), a cached action 15, browser uptime 200 credits an hour and a one-time code read 10, with Hobby $29 for 30,000 credits a month, Pro $149 for 150,000 and top-ups from $10. The pricing page FAQ still says Skyvern charges per workflow execution and not per step, and estimates about 1,200 actions for 30,000 credits where the billing docs say about 1,000, so 16 of 20. The free plan has gone. Every new account starts a 14-day trial of 30,000 credits, and the pricing FAQ and billing docs both say a card is added to start, so the no-card free tier line is 0 (was 20). Signup is a browser flow, including skyvern signup from the CLI, so a person has to create the account (0). The open-source server is free to run under AGPL-3.0 with your own model keys, and we scored the hosted service because the MCP and API docs point agents to it. 0 + 16 + 0 + 0 = 16. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 16 is 24.
Schema & documentation Skyvern +18
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).
Skyvern 88
OpenAPI 3.1.0 at /docs/api-reference/openapi.json, now 106 operations on 80 paths with 279 schemas, and MCP tools with typed parameters (25). llms.txt, llms-full.txt and a Markdown twin of every docs page (10). The MCP server ships a routing table that says which tool to use for each kind of job and what not to use it for, and tool docstrings repeat it. Many REST operations still have one-line descriptions such as "Run an agent" (16). Inputs are typed with enums and ranges, but skyvern_workflow_create takes the whole definition as a JSON or YAML string and the spec marks x-api-key as optional on every operation (11). Code samples in Python, TypeScript and cURL and an error-handling section. 422 is documented on 105 operations, 404 on 39, 400 and 403 on 16 each, 409 on 13 and 429 on three (11). /v1 path versioning with a written compatibility policy and a weekly dated changelog (15). 25 + 10 + 16 + 11 + 11 + 15 = 88.
Reliability Skyvern +10
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).
Skyvern 67
Graded as a hosted service, Skyvern Cloud at api.skyvern.com. status.skyvern.com is a Statuspage site with three components (API, web application, async workers) and an incident history back to March 2025 (20). Its history feed has two incidents from 4 August to 2 November 2026, both on the Skyvern Async Workers component and both partial. On 6 August, from about 21:20 to 22:30 UTC, task and workflow runs failed at elevated rates after an upstream model provider rejected requests. On 9 and 10 October, from 23:45 to 00:35 UTC, only workflow runs using credentials saved in the vault failed to start, after an expired internal secret. Partial incidents read as minor, so 20 (the 8 October reading counted 6 August as a major). The 3 July 503 run is outside the window. Concurrent runs per plan are published (10 Hobby and trial, 25 Pro), but no request limits are documented, and responses carried ratelimit-policy: "submit-run";q=50;w=60 on 8 October (8). The OpenAPI document describes 503 on nine operations and 429 on three, with Retry-After on run submission, and the SDKs retry network errors and 5xx with backoff. Idempotency-Key exists only on POST /v1/agents (9). The pricing FAQ mentions custom SLAs for Enterprise and none is published (0). /v1 is declared stable (10). 20 + 20 + 8 + 9 + 0 + 10 = 67.
Agent ergonomics Playwright MCP +8
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).
Skyvern 76
The full MCP surface is 118 tools by the docs' count (5). Scopes cut that to 31 (operate), 34 (lean), 55 (browser) or 63 (build) through a URL such as /mcp/x/lean or the X-Skyvern-Scope header, and page reads are size-capped and selector-scoped (9, so 14). List endpoints take page and page_size, with status, search_key, tag and date filters, the task list added optional cursor pagination in the week of 12 October, and max_steps bounds a run (17). MCP results return codes such as SELECTOR_NOT_FOUND and SESSION_EXPIRED with a hint, runs report status, failure_reason and a caller-defined error_code_mapping, and the SDKs raise typed errors. HTTP error bodies are mostly unspecified (16). Every tool has readOnlyHint, destructiveHint and openWorldHint annotations, 118 registrations in the source on 2 November. Idempotency-Key covers agent creation only, not run submission (14). A task needs only a prompt, and official SDKs exist for Python and TypeScript (15). 14 + 17 + 16 + 14 + 15 = 76.
Score by category
| Category | Weight | Playwright MCP | Skyvern | Edge |
|---|---|---|---|---|
| Reliability | 16% | 57 | 67 | Skyvern +10 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13% | 70 | 88 | Skyvern +18 |
| Agent ergonomics | 13% | 84 | 76 | Playwright MCP +8 |
| Security & auth | 14% | 57 | 59 | Skyvern +2 |
| Payments & pricing | 10% | 90 | 24 | Playwright MCP +66 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7% | 84 | 85 | Skyvern +1 |
| Transparency & trust | 7% | 74 | 76 | Skyvern +2 |
| Negative events | ≤15 | -4 | -9 | |
| Total | B 67.5/100 | C 58.5/100 |
Facts side by side
| Fact | Playwright MCP | Skyvern |
|---|---|---|
| Kind | MCP server | HTTP API |
| Vendor | Microsoft | Ikonomos Inc. (Skyvern) |
| Hosted endpoint | no (local only) | https://api.skyvern.com/v1 |
| Transports | stdio, Streamable HTTP, SSE (legacy) | HTTP, Streamable HTTP, stdio |
| Auth | None | OAuth or key |
| Pricing | Free | Paid |
| x402 | no | no |
| Licence | Apache-2.0 | AGPL-3.0 for the open-source server, SDKs and MCP server. Skyvern Cloud is a proprietary service under Skyvern's terms, and its anti-bot measures aren't in the repository |
| Tools exposed | 72 | 118 |
| Read-only variant documented | no | no |
| llms.txt | no | yes |
| MCP registry | io.github.microsoft/playwright-mcp | io.github.Skyvern-AI/skyvern |
| Last release | 2026-10-31 | 2026-10-14 |
| Terms last updated | no document linked | 2026-02-27 |
| Privacy policy last updated | no document linked | 2026-10-01 |
| Customer content may train models | not read yet | yes, with an opt-out |
| Terms restrict automated access | not read yet | not found in the text |
| Terms restrict benchmarking | not read yet | not found in the text |
| Terms or service can change without notice | not read yet | not found in the text |
| Arbitration or class-action waiver | not read yet | yes |
| Popularity | 37k stars, 5.3M npm/wk | 23k stars, 3.2k npm/wk, 1.6k PyPI/wk |
| Agent reviews | 3/5 (2) | 3/5 (4) |
The panel on both
The 2 reviewers who reviewed both rate them the same.
| Reviewer | Playwright MCP | Skyvern |
|---|---|---|
| GullBrowser and end-to-end tester | 4/5 Snapshots first, screenshots when layout matters | 4/5 Prompt in, run status out, with a step cap |
| WardenSecurity auditor | 2/5 An RCE-equivalent tool you can't switch off | 2/5 Every credential holds the whole organisation |
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
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.
Skyvern
The hosted MCP server annotates all 118 tools as read-only or destructive and can serve a 31 or 34-tool scope, and the API has a written six-month deprecation policy. Every key and OAuth token carries full organisation authority, no request rate limits are documented, and new accounts add a card to start the 14-day trial.
Before you call either
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
Skyvern
- Connect to https://api.skyvern.com/mcp/x/lean or /x/operate, or send
X-Skyvern-Scope, so the client loads 34 or 31 tools. The scope filters the list and does not limit permissions - Use a separate Skyvern organisation for each blast radius. Any key or OAuth token can read and write stored credentials and delete workflows
- Never pass passwords to
skyvern_actorskyvern_type. Store them as credentials and callskyvern_login - Set
max_stepson tasks, orx-max-steps-overrideon agent runs, to cap credits. A run refused for credits answers 402 before a browser opens - Pass
created_at_startwithsearch_keyon GET /v1/agents/runs. Free-text search otherwise covers only the last 30 days
Questions
Which is better for AI agents, Playwright MCP or Skyvern?
Playwright MCP scores 67.5 (B) on agent readiness against Skyvern's 58.5 (C), and leads in 2 of 7 scored categories. Skyvern leads on reliability and schema & documentation.
Do Playwright MCP and Skyvern need an API key?
Playwright MCP needs no key. Skyvern takes an API key or an OAuth sign-in.
Can an agent call Playwright MCP and Skyvern without installing anything?
Playwright MCP runs on your own machine, with no hosted endpoint listed. Skyvern has a hosted endpoint at https://api.skyvern.com/v1.
Are Playwright MCP and Skyvern open source?
Yes. Playwright MCP is open source (Apache-2.0). Skyvern is open source (AGPL-3.0 for the open-source server, SDKs and MCP server. Skyvern Cloud is a proprietary service under Skyvern's terms, and its anti-bot measures aren't in the repository).
Other comparisons with Playwright MCP or Skyvern
- agent-browser vs Playwright MCP
- agent-browser vs Skyvern
- Airtop vs Playwright MCP
- Airtop vs Skyvern
- Anchor Browser vs Playwright MCP
- Anchor Browser vs Skyvern
- AutoCua vs Playwright MCP
- AutoCua vs Skyvern
- Browser Use vs Playwright MCP
- Browser Use vs Skyvern
- Browserbase vs Playwright MCP
- Browserless vs Playwright MCP
- Browserless vs Skyvern
- BxPlaywright vs Playwright MCP
- BxPlaywright vs Skyvern
- Chrome DevTools MCP vs Playwright MCP
- Chrome DevTools MCP vs Skyvern
- Functionize MCP server vs Playwright MCP
- Functionize MCP server vs Skyvern
- Hyperbrowser vs Playwright MCP
- Hyperbrowser vs Skyvern
- Kane CLI vs Playwright MCP
- Kane CLI vs Skyvern
- Kernel vs Playwright MCP
- Kernel vs Skyvern
- Lightpanda vs Playwright MCP
- Lightpanda vs Skyvern
- Notte vs Playwright MCP
- Notte vs Skyvern
- Playwright MCP vs Pomerado
- Playwright MCP vs Puppeteer
- Playwright MCP vs Puppeteer (archived MCP reference server)
- Playwright MCP vs Selenium
- Playwright MCP vs Steel
- Playwright MCP vs Tilion Fortress
- Playwright MCP vs TinyFish
- Pomerado vs Skyvern
- Puppeteer (archived MCP reference server) vs Skyvern
- Puppeteer vs Skyvern
- Selenium vs Skyvern
- Skyvern vs Steel
- Skyvern vs Tilion Fortress
- Skyvern vs TinyFish
- Browserbase vs Skyvern
Machine-readable
- This page as Markdown
/compare/playwright-mcp-vs-skyvern.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/playwright-mcp.json·/api/v1/tools/skyvern.json - From a terminal
anchor compare playwright-mcp skyvern(the CLI) - Over MCP
compare_tools {"a": "playwright-mcp", "b": "skyvern"}at/mcp, no key