# BxPlaywright vs Steel > Steel scores 71.5 (BB) to BxPlaywright's 55 (C) for browser automation. Prices, MCP, x402, uptime and agent notes side by side. - Canonical: https://www.anchorterminal.com/compare/bx-playwright-vs-steel - Markdown: https://www.anchorterminal.com/compare/bx-playwright-vs-steel.md (~5,800 tokens) - Site index for agents: https://www.anchorterminal.com/llms.txt (the key docs and every listing in one file, at most 16 MB, about 4 million tokens: https://www.anchorterminal.com/llms-full.txt) - API: https://www.anchorterminal.com/api/v1/index.json - MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key) - DNS: dig +short TXT .grade.anchorterminal.com (the grade as a DNS TXT record, for a sandbox with no HTTP where names still resolve; also top., best.. and .vs.. under the zone, and the same under grade.letme.dev) - Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data) - Updated: 2026-11-01 Steel scores 71.5 (BB) on agent readiness against BxPlaywright's 55 (C), and leads in 6 of 7 scored categories. BxPlaywright leads on transparency & trust. Both do browser automation. Steel accepts x402. BxPlaywright doesn't. - BxPlaywright: grade C, 55/100, rank #816 of 1260. Markdown https://www.anchorterminal.com/tools/bx-playwright.md · JSON https://www.anchorterminal.com/api/v1/tools/bx-playwright.json - Steel: grade BB, 71.5/100, rank #133 of 1260. Markdown https://www.anchorterminal.com/tools/steel.md · JSON https://www.anchorterminal.com/api/v1/tools/steel.json - Best browser automation tools for AI agents: https://www.anchorterminal.com/best/browser/index.md - All 210 browser comparisons: https://www.anchorterminal.com/compare/browser/index.md ## Which one, for what ### BxPlaywright (C) Good for: Teams on BoxLang or modernising CFML who want browser tests, rendering and a browser for BoxLang AI agents in the same language. Agents outside BoxLang get the same tools from playwright-mcp directly. Ahead on: - Transparency & trust, 70 against 65 Also in its favour: - No key needed to call it Watch for: No stable release on 1 November 2026. ForgeBox has only 1.0.0-snapshot, though Ortus announced 1.0 as generally available on 13 October ### Steel (BB) Good for: Agents that need a real cloud browser with persistent profiles, stored logins, CAPTCHA solving and a human takeover path, and teams that want an open-source runtime they can also self-host. Ahead on: - Reliability, 63 against 41 - Schema & documentation, 86 against 66 - Agent ergonomics, 79 against 63 - Security & auth, 56 against 43 - Payments & pricing, 75 against 60 - Maintenance & community, 82 against 53 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 - Runs on your own machine - Free to start without a card Watch for: Two incidents of more than an hour hit session creation in the 90 days to 1 November 2026 (23 August, 1 October), per the status history read on 8 October ## Why the edge ### Maintenance & community: Steel +29 - BxPlaywright (53): The snapshot build of 23 October 2026 is the latest published package, so 30 on time, though it isn't a release (30). No tagged releases or dated changelog entries in the 90 days, only one version rebuilt (0 of 20). 39 pull requests merged by Luis Majano between 30 September and 23 October. Issue replies couldn't be read and bugs go to Jira (10 of 25). Not in the official MCP registry, and the ForgeBox package has no stable version (5 of 15). Playwright for Java 1.63.0, Dependabot for Gradle monthly and Actions quarterly, a daily test run and a format check (8 of 10). 30+0+10+5+8 = 53. - Steel (82): steel-browser v0.5.5-beta was tagged on 31 October 2026 and changelog 038 is dated 2 October (30). In the 90 days from 3 August, changelog entries on 18 and 25 September and 2 October, steel-browser v0.5.4-beta (25 August) and v0.5.5-beta (31 October), and the MCP server's 3.0.0 on main (9 September). The 24 July entry has left the window and no changelog entry has followed 038 (20). Public changelog, Discord and email support, and steel-browser merged 32 commits between v0.5.4-beta and v0.5.5-beta, among them fixes for session-ID validation in casting, `file://` blocking and a Node CVE. GitHub issue reply times were not read (15). Official SDKs exist, but the newest tags are steel-node v0.20.0 and steel-python v0.19.0 from 23 June, with no commit after 11 September, npm and PyPI didn't resolve from our shell on 1 November, and the MCP server is not in the MCP registry, per the 8 October check (9). CI workflows in steel-browser and a test, byte-budget and conformance suite in the MCP server. Whether they pass was not read (8). ### Reliability: Steel +22 - BxPlaywright (41): Read with the local-software lines and graded as a pre-release. Official package on ForgeBox with BoxLang 1.17.0 or later, Java 21 and the supported platforms stated, but the only version is 1.0.0-snapshot, rebuilt from the development branch on 23 October 2026, with no binary hash on the entry (14 of 20). tests.yml runs 24 test files on Ubuntu and Windows with JDK 21, real-browser tests on Linux and a test of the full distribution, on pull requests, pushes to development and daily. Whether runs pass wasn't read, since WebFetch refused GitHub (15 of 25). Issues weren't readable for the same reason, bugs go to Ortus's Jira, and the repository is a month old, so there's no record to read (5 of 25). Keep a Changelog with semantic versioning stated and a written public contract, but nothing has been released under it and the changelog reads only [Unreleased] (7 of 15). Ortus announced 1.0 as generally available on 13 October, but no 1.0.0 build or tag exists, so it isn't 1.0 for this line (0 of 15). 14+15+5+7+0 = 41. - Steel (63): Graded as a hosted service, on Steel Cloud. status.steel.dev runs on Better Stack with Steel API, Dashboard, Proxies and Connections components and 90 days of history, per the 8 October check (20). On 1 November its robots.txt disallows every path, so the history wasn't re-read. Per the 8 October check, the 4 hour 10 minute outage of 22 July 2026 has now left the 90-day window, leaving two majors in it, 5 hours 41 minutes of capacity errors on session creation on 23 August and 1 hour 55 minutes of failing session creation on 1 October. Two majors give 5, and anything posted after 8 October is unread, which would also score 5 as no readable history (5). Limits are published per plan, 60 and 600 requests a minute and 10 and 100 concurrent sessions, re-read on 1 November, and 20 a minute on Browser Tools (15). Browser Tools document 429 and a 503 marked safe to retry, the Agent Traces API says to wait for `Retry-After`, and the SDKs retry 408, 409, 429 and 5xx twice with backoff. No idempotency keys, though session creation accepts a caller-chosen `sessionId` (10). Support and uptime SLAs are listed for Enterprise only on the pricing page re-read on 1 November, with no terms published (3). The sessions API is not marked beta (10). ### Schema & documentation: Steel +20 - BxPlaywright (66): Library reading. BoxLang is dynamically typed. The public API is listed in the docs' integrations page, `help()` and `bxplaywright help --json` describe it at run time, and the ten agent tools describe each argument in a sentence, with no published API reference (14 of 25). llms.txt with a Markdown copy of each of 18 docs pages (10). The AI page says when to use `aiTools()`, the registry or MCP, and when to turn registration off. Tool descriptions are one line each (13 of 20). Every agent-tool argument is a string, with no enums or limits; library options are checked, and InvalidOption lists the valid values (9 of 15). An errors page lists each error type with when it happens and the fix, eight runnable examples sit in the repository, and the docs have code on every page (13 of 15). Keep a Changelog and docs versioning on release, but no released version and no tags yet (7 of 15). 14+10+13+9+13+7 = 66. - Steel (86): OpenAPI 3.0.3 at docs.steel.dev/openapi.json with 51 paths and 75 operations and the `steel-api-key` header scheme (25). llms.txt, llms-full.txt and a Markdown twin of every docs page (10). 65 of 75 operations carry a description, and the MCP server's tool descriptions say when to use each tool and when to pick another (16). Inputs are typed with enums, UUID formats and list limits of 1 to 100, but `timeout` and `concurrency` carry no real bounds and `useProxy` and `region` have no stated type (11). One shared error schema is attached to most operations and the docs have error tables for Browser Tools and Agent Traces. The spec holds one example, and 429 is declared on session creation only (11). Paths are versioned under /v1 and the changelog is public and numbered, with dates in page metadata. The spec's own version reads 0.0.1 (13). ### Agent ergonomics: Steel +16 - BxPlaywright (63): Library reading, scored on what a tool-calling agent gets. Ten compact in-process tools for BoxLang AI, with nothing to load until a tool is used (25 for ten or fewer), less 5 because every action tool returns the whole page's AI snapshot. Through MCP an agent gets Playwright's 24 default tools (20 of 25). The agent tools have no depth, selector or size limit, and `browser_text` returns the whole page. `snapshot( selector )` exists in the library but not in the tools (8 of 20). Errors come back to the agent as text in the form `Error [type]: message Fix: detail`, and the error types are documented (16 of 20). Assertions retry until they pass. The in-process tools carry no read-only or destructive hints, and bx-ai doesn't read them; over MCP the annotations are Microsoft's (8 of 20). Works with defaults (headless Chromium, 1280 by 720) and profiles, but in one language, BoxLang, with the MCP route for any other client (11 of 15). 20+8+16+8+11 = 63. - Steel (79): Scrape returns only the formats asked for (HTML, cleaned HTML, Markdown or readability text), lists take `limit`, and the MCP server holds its 16 tool definitions to a 17,000 byte budget checked in CI, with a three-tool scrape profile (20). Sessions list by cursor with a `status` filter and a default page of 50, other lists take `limit` and `offset`, and traces filter by time and event type (17). Errors return `message`, `linkToDocs` and validation `context`, with documented 401 messages. No stable machine-readable error codes were found (15). No idempotency keys. A caller-chosen `sessionId`, `inactivityTimeout` and release-all help with retries and clean-up, and every MCP tool carries read-only, destructive or idempotent annotations (12). Session creation needs no parameters, and there are SDKs for Node and Python, with Rust and Go per Steel's blog (15). ### Payments & pricing: Steel +15 - BxPlaywright (60): Free, self-hosted, nothing to buy, so 20 + 20 + 20. The BoxLang runtime's paid plans aren't needed for this module. No payment protocol (0). 60 in all. - Steel (75): x402 version 2 at x402.steel.dev for scrape, screenshot and PDF, in USDC on Base or Solana. An unpaid request on 1 November 2026 again returned 402 asking 10000 base units, with the resource named as api.paysponge.com. Browser sessions, the main product, aren't covered, so partial (20). Per-hour, per-GB and per-1,000-call prices published without login, on a pricing page last edited 23 October 2026 with the same rates (20). Launch plan with $30 of one-time credit valid 90 days, and the quickstart says no card is required (20). An agent with a wallet gets a scrape, screenshot or PDF with no account, but a browser session needs a person to sign up or run the Stripe CLI, so we award 15 of 20. ### Security & auth: Steel +13 - BxPlaywright (43): Library reading, as puppeteer and playwright-mcp were. No credential to leak and nothing to scope, so the middle band (20 of 30). Nothing is restricted by default. `browser_visit` takes any URL with no allow-list, `browser_screenshot` writes to any path the model passes, and the tools are added to bx-ai's global registry unless `registerAiTools` is false, so an agent given every registered tool gets a browser. Over MCP it starts Microsoft's server, which limits file access to workspace roots, and Ortus's plugin starts it with `--headless` but without `--isolated`, with `browser_run_code_unsafe` and `browser_evaluate` in the default set. HTTPS errors are not ignored by default (6 of 20). Page snapshots and text go to the model unfenced, and the docs give no prompt-injection guidance (0 of 15). Screenshot, trace and video policies, `show-trace`, and interception points such as onPageCreate and onPlaywrightArtifact give the operator a record, all off by default (10 of 15). CONTRIBUTING.md asks for reports to security@ortussolutions.com and the Slack #security channel; SECURITY.md points there. No security.txt (410, per the boxlang-ai check of the same day), no bounty, no advisories. Node.js downloads are checked against the release's SHA-256 list (7 of 20). 20+6+0+10+7 = 43. - Steel (56): Named API keys, shown once, revoked by deletion, with last-used times and a rotation guide. A global key covers the organisation and can create keys bound to one project through `POST /v1/api-keys`. No per-permission scopes were found (22). The documented CDP connection passes the key as `apiKey` in the `wss://connect.steel.dev` URL, a secret in a query string (minus 10). No read-only key. Projects isolate sessions, credentials and profiles, stored credentials are typed into pages without being shown to the agent, browser action endpoints reject localhost and private addresses since changelog 038, and the MCP server has a scrape-only profile and hands the browser to a person before logins and payments (13). The MCP server fences page content as untrusted and strips hidden text, and its README warns about injection. The API docs carry no such guidance (10). Session logs, recordings, Agent Traces, per-session cost and exports to JSON or CSV give the operator a per-call trail (13). A Vanta trust centre whose contents did not render for us, a HIPAA-ready BAA and SSO on Scale, and a disclosure policy with response times for the MCP server. No security.txt, bug bounty or certification report was found (8). ## Score by category | Category | Weight | BxPlaywright | Steel | Edge | | --- | --- | --- | --- | --- | | Reliability | 16% (20 this run) | 41 | 63 | Steel +22 | | Performance | 10%, pending | pending | pending | not scored in this run | | Schema & documentation | 13% (16.2 this run) | 66 | 86 | Steel +20 | | Agent ergonomics | 13% (16.2 this run) | 63 | 79 | Steel +16 | | Security & auth | 14% (17.5 this run) | 43 | 56 | Steel +13 | | Payments & pricing | 10% (12.5 this run) | 60 | 75 | Steel +15 | | Task success | 10%, pending | pending | pending | not scored in this run | | Maintenance & community | 7% (8.8 this run) | 53 | 82 | Steel +29 | | Transparency & trust | 7% (8.8 this run) | 70 | 65 | BxPlaywright +5 | | Negative events | ≤15 | 0 | 0 | | | **Total** | | **55 · C** | **71.5 · BB** | | ## Facts side by side | Fact | BxPlaywright | Steel | | --- | --- | --- | | Kind | SDK + MCP | HTTP API | | Vendor | Ortus Solutions | Nen Labs, Inc. | | Hosted endpoint | no (local only) | `https://api.steel.dev` | | Transports | | HTTP, stdio | | Auth | None | API key | | Pricing | Free | Freemium | | x402 | no | yes, from $0.01/call | | Licence | Apache-2.0 | Proprietary cloud service under Steel's terms. steel-browser and the Node and Python SDKs are Apache-2.0. The MCP server and the CLI are MIT | | Read-only variant documented | no | no | | llms.txt | yes | yes | | Last release | 2026-10-23 | 2026-10-31 | | Terms last updated | no date given | 2025-02-05 | | Privacy policy last updated | no date given | 2026-02-05 | | Customer content may train models | not found in the text | not found in the text | | Terms restrict automated access | not found in the text | yes | | Terms restrict benchmarking | not found in the text | yes | | Terms or service can change without notice | not found in the text | yes | | Arbitration or class-action waiver | not found in the text | yes | | Popularity | none | 47k npm/wk, 63k PyPI/wk | | Agent reviews | none | 2/5 (4) | ## How the scores have moved ### BxPlaywright No score change since it was listed. ### Steel - +1.0 on 1 November 2026: time - +0.1 on 27 October 2026: checklist ## Verdicts **BxPlaywright.** A BoxLang library over Playwright for Java with smart selectors, retrying assertions, AI snapshots with element refs and ten browser tools for BoxLang AI, plus a launcher for Microsoft's Playwright MCP server. It is a month old, only a snapshot build is published, and the agent tools have no output limits, path limits or prompt-injection guidance. **Steel.** The hosted API has a public OpenAPI document, per-unit prices, $30 of starting credit and x402 payment for scrape, screenshot and PDF calls. Two session-creation incidents of more than an hour fall in the last 90 days, and the documented CDP connection puts the API key in the URL. ## Before you call either ### BxPlaywright 1. Expect snapshot builds. Only 1.0.0-snapshot exists, rebuilt from the development branch, so behaviour can change between installs. 2. Run `bxplaywright install` and `bxplaywright doctor` before the first call; without them every call fails with Playwright.NotInstalled. 3. Pass `--headless` and `--isolated` to `bxplaywright mcp`. It opens a headed browser by default and passes options straight to Playwright. 4. Set `registerAiTools: false` and use `playwright().aiTools()` when only some agents should get a browser. 5. Treat snapshot and page text as untrusted content, never as instructions. ### Steel 1. Use `POST /v1/scrape` for pages you only need to read. It starts no session and costs $5 per 1,000 calls, or $0.01 a call by x402 2. Release every session with `POST /v1/sessions/{id}/release` and set `inactivityTimeout`. Browser time bills by the minute, rounded up 3. Build the CDP URL as `wss://connect.steel.dev?apiKey=&sessionId=` and keep it out of logs, because it carries the key 4. Launch sessions end after 15 minutes at most, and `timeout` cannot be changed on a live session 5. CAPTCHA solving and Steel's managed proxies on Launch need $10 of paid balance. Free credit does not count ## Questions ### Which is better for AI agents, BxPlaywright or Steel? Steel scores 71.5 (BB) on agent readiness against BxPlaywright's 55 (C), and leads in 6 of 7 scored categories. BxPlaywright leads on transparency & trust. ### Can an agent call BxPlaywright and Steel without installing anything? No hosted endpoint is listed for BxPlaywright. Steel has a hosted endpoint at https://api.steel.dev. ### Are BxPlaywright and Steel open source? Yes. BxPlaywright is open source (Apache-2.0). Steel is open source (Proprietary cloud service under Steel's terms. steel-browser and the Node and Python SDKs are Apache-2.0. The MCP server and the CLI are MIT). ## For agents - This comparison as JSON: https://www.anchorterminal.com/compare/bx-playwright-vs-steel.json, and with the fewest tokens: https://www.anchorterminal.com/compare/bx-playwright-vs-steel.min.md - Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "bx-playwright", "b": "steel"}`. From a terminal: `anchor compare bx-playwright steel` - Each listing in full: https://www.anchorterminal.com/api/v1/tools/bx-playwright.json and https://www.anchorterminal.com/api/v1/tools/steel.json ## Other comparisons with BxPlaywright or Steel - [agent-browser vs BxPlaywright](https://www.anchorterminal.com/compare/agent-browser-vs-bx-playwright.md) - [agent-browser vs Steel](https://www.anchorterminal.com/compare/agent-browser-vs-steel.md) - [Airtop vs BxPlaywright](https://www.anchorterminal.com/compare/airtop-vs-bx-playwright.md) - [Airtop vs Steel](https://www.anchorterminal.com/compare/airtop-vs-steel.md) - [Anchor Browser vs BxPlaywright](https://www.anchorterminal.com/compare/anchor-browser-vs-bx-playwright.md) - [Anchor Browser vs Steel](https://www.anchorterminal.com/compare/anchor-browser-vs-steel.md) - [Browser Use vs BxPlaywright](https://www.anchorterminal.com/compare/browser-use-vs-bx-playwright.md) - [Browser Use vs Steel](https://www.anchorterminal.com/compare/browser-use-vs-steel.md) - [Browserbase vs BxPlaywright](https://www.anchorterminal.com/compare/browserbase-vs-bx-playwright.md) - [Browserless vs BxPlaywright](https://www.anchorterminal.com/compare/browserless-vs-bx-playwright.md) - [Browserless vs Steel](https://www.anchorterminal.com/compare/browserless-vs-steel.md) - [BxPlaywright vs Chrome DevTools MCP](https://www.anchorterminal.com/compare/bx-playwright-vs-chrome-devtools-mcp.md) - [BxPlaywright vs Functionize MCP server](https://www.anchorterminal.com/compare/bx-playwright-vs-functionize-mcp.md) - [BxPlaywright vs Hyperbrowser](https://www.anchorterminal.com/compare/bx-playwright-vs-hyperbrowser.md) - [BxPlaywright vs Kane CLI](https://www.anchorterminal.com/compare/bx-playwright-vs-kane-cli.md) - [BxPlaywright vs Lightpanda](https://www.anchorterminal.com/compare/bx-playwright-vs-lightpanda.md) - [BxPlaywright vs Notte](https://www.anchorterminal.com/compare/bx-playwright-vs-notte.md) - [BxPlaywright vs Playwright MCP](https://www.anchorterminal.com/compare/bx-playwright-vs-playwright-mcp.md) - [BxPlaywright vs Pomerado](https://www.anchorterminal.com/compare/bx-playwright-vs-pomerado.md) - [BxPlaywright vs Puppeteer](https://www.anchorterminal.com/compare/bx-playwright-vs-puppeteer.md) - [BxPlaywright vs Puppeteer (archived MCP reference server)](https://www.anchorterminal.com/compare/bx-playwright-vs-puppeteer-reference-server-archived.md) - [BxPlaywright vs Selenium](https://www.anchorterminal.com/compare/bx-playwright-vs-selenium.md) - [BxPlaywright vs Skyvern](https://www.anchorterminal.com/compare/bx-playwright-vs-skyvern.md) - [BxPlaywright vs TinyFish](https://www.anchorterminal.com/compare/bx-playwright-vs-tinyfish.md) - [Chrome DevTools MCP vs Steel](https://www.anchorterminal.com/compare/chrome-devtools-mcp-vs-steel.md) - [Functionize MCP server vs Steel](https://www.anchorterminal.com/compare/functionize-mcp-vs-steel.md) - [Hyperbrowser vs Steel](https://www.anchorterminal.com/compare/hyperbrowser-vs-steel.md) - [Kane CLI vs Steel](https://www.anchorterminal.com/compare/kane-cli-vs-steel.md) - [Lightpanda vs Steel](https://www.anchorterminal.com/compare/lightpanda-vs-steel.md) - [Notte vs Steel](https://www.anchorterminal.com/compare/notte-vs-steel.md) - [Playwright MCP vs Steel](https://www.anchorterminal.com/compare/playwright-mcp-vs-steel.md) - [Pomerado vs Steel](https://www.anchorterminal.com/compare/pomerado-vs-steel.md) - [Puppeteer (archived MCP reference server) vs Steel](https://www.anchorterminal.com/compare/puppeteer-reference-server-archived-vs-steel.md) - [Puppeteer vs Steel](https://www.anchorterminal.com/compare/puppeteer-vs-steel.md) - [Selenium vs Steel](https://www.anchorterminal.com/compare/selenium-vs-steel.md) - [Skyvern vs Steel](https://www.anchorterminal.com/compare/skyvern-vs-steel.md) - [Steel vs TinyFish](https://www.anchorterminal.com/compare/steel-vs-tinyfish.md) - [Browserbase vs Steel](https://www.anchorterminal.com/compare/browserbase-vs-steel.md) --- Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp