{
  "listings": [
    {
      "slug": "agent-browser",
      "name": "agent-browser",
      "company": "Vercel Inc.",
      "grade": "B",
      "fit": "yes",
      "why": "snapshot -i, -c and -d cap the tree, --max-output truncates page text, screenshot writes a path and console reads errors. acc-48 and acc-40 use it for precisely this; acc-72 reports flaky refs on dynamic pages.",
      "source": "https://agent-browser.dev/snapshots.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/agent-browser"
    },
    {
      "slug": "browserbase",
      "name": "Browserbase",
      "company": "Browserbase, Inc.",
      "grade": "BB",
      "fit": "yes",
      "why": "The Browse CLI runs a managed local browser (--local) or a remote session, prints accessibility snapshots with cached refs, and the ui-test skill reports passed, failed and skipped tests with failure screenshots under .context/. Remote sessions still cannot reach localhost.",
      "source": "https://docs.browserbase.com/integrations/skills/browse-cli",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/browserbase"
    },
    {
      "slug": "chrome-devtools-mcp",
      "name": "Chrome DevTools MCP",
      "company": "Google LLC",
      "grade": "BB",
      "fit": "yes",
      "why": "take_snapshot returns a filtered tree by default (verbose false) or writes to filePath, actions default includeSnapshot to false, take_screenshot writes a file, and a local Chrome reaches localhost. acc-72 puts the tool definitions at about 17k tokens; --slim trims them.",
      "source": "https://github.com/ChromeDevTools/chrome-devtools-mcp/blob/main/docs/tool-reference.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/chrome-devtools-mcp"
    },
    {
      "slug": "kane-cli",
      "name": "Kane CLI",
      "company": "TestMu AI (formerly LambdaTest)",
      "grade": "C",
      "fit": "yes",
      "why": "A plain-English objective runs in local Chrome, so localhost works, and every run seals an evidence pack with per-step screenshots, annotated copies, console and network logs and a pass or fail result card; saved test.md files replay cached steps. Runs spend account credits.",
      "source": "https://github.com/LambdaTest/kane-cli/blob/main/docs/user-guide/agents.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/kane-cli"
    },
    {
      "slug": "airtop",
      "name": "Airtop",
      "company": "Switchboard Visual Technologies, Inc. (dba Airtop)",
      "grade": "C",
      "fit": "caveat",
      "why": "A cloud browser driven by page-query, click and type calls over Puppeteer or Playwright, with recordings per window. It cannot reach localhost without a tunnel, and there is no accessibility snapshot or ref tool, so each step check is an AI call billed in credits.",
      "source": "https://docs.airtop.ai/guides/how-to/ai/page-interactions.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/airtop"
    },
    {
      "slug": "anchor-browser",
      "name": "Anchor Browser",
      "company": "Anchor Forge Inc.",
      "grade": "B",
      "fit": "caveat",
      "why": "The hosted MCP's anchor_* tools give navigate, snapshot with accessibility refs, click, type, screenshot, console and network logs, and sessions record MP4 by default. The browser is in Anchor's cloud, so a localhost app needs a tunnel, and no snapshot cap or depth option is documented.",
      "source": "https://docs.anchorbrowser.io/advanced/mcp",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/anchor-browser"
    },
    {
      "slug": "browser-use",
      "name": "Browser Use",
      "company": "Browser Use, Inc.",
      "grade": "A",
      "fit": "caveat",
      "why": "The cloud is a goal agent (run_session over MCP, POST /runs) whose browsers cannot reach localhost. The open-source library runs locally and can attach to the person's Chrome, but it too is an agent loop, so per-step pass or fail evidence comes from its history, not a step tool.",
      "source": "https://docs.browser-use.com/cloud/guides/mcp-server",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/browser-use"
    },
    {
      "slug": "browserless",
      "name": "Browserless",
      "company": "browserless.io, Inc.",
      "grade": "BB",
      "fit": "caveat",
      "why": "browserless_agent snapshots interactive and informational elements with maxElements and returns only changes after the first, screenshot toDisk saves a file reference. The browser is in the cloud, so localhost needs a tunnel, and Free sessions end at 2 minutes with 2 concurrent.",
      "source": "https://docs.browserless.io/mcp/browser-agent",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/browserless"
    },
    {
      "slug": "bx-playwright",
      "name": "BxPlaywright",
      "company": "Ortus Solutions, Corp.",
      "grade": "C",
      "fit": "caveat",
      "why": "BoxLang AI agents get browser_visit, browser_snapshot (compact tree with refs, limitable to one selector), browser_click, browser_fill and browser_screenshot against a local browser that reaches localhost. Only BoxLang agents get these tools; others get Microsoft's Playwright MCP, and the in-process snapshot has no depth or size cap.",
      "source": "https://bxplaywright.boxlang.io/ai.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/bx-playwright"
    },
    {
      "slug": "functionize-mcp",
      "name": "Functionize MCP server",
      "company": "Functionize, Inc.",
      "grade": "D",
      "fit": "caveat",
      "why": "Studio runs the test in Chrome, Firefox or Edge with per-step pass or fail, screenshots and video; the coding agent reads the status rather than driving a browser. A local app needs Functionize's tunnel, a generation is green or yellow never red, and creating a test spends unpublished credits.",
      "source": "https://github.com/FunctionizeInc/functionize-mcp-plugin/blob/main/skills/functionize/references/capabilities.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/functionize-mcp"
    },
    {
      "slug": "hyperbrowser",
      "name": "Hyperbrowser",
      "company": "S2 Labs Inc.",
      "grade": "B",
      "fit": "caveat",
      "why": "A cloud Chromium driven over CDP, WebDriver or computer actions, with rrweb recording on by default and a live view. No snapshot or ref tool of its own (the MCP has run_browser_task and web_fetch), and a localhost app needs a tunnel.",
      "source": "https://www.hyperbrowser.ai/docs/sessions/recordings.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/hyperbrowser"
    },
    {
      "slug": "kernel",
      "name": "Kernel",
      "company": "Kernel Technologies, Inc.",
      "grade": "B",
      "fit": "caveat",
      "why": "Cloud Chromium driven by Playwright, CDP or computer controls with replays recorded by browser id; the MCP server launches browsers and runs Playwright code rather than snapshots. A localhost app needs a tunnel, and acc-36 measured 0.94 s to create a browser.",
      "source": "https://www.kernel.sh/docs/reference/mcp-server",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/kernel"
    },
    {
      "slug": "lightpanda",
      "name": "Lightpanda",
      "company": "Selecy SAS",
      "grade": "C",
      "fit": "caveat",
      "why": "A local MCP server with goto, tree, interactiveElements, click, fill, consoleLogs and a screenshot tool reaches localhost cheaply. There is no graphical rendering, iframes, workers and stylesheets are off by default, and acc-64's agent task failed on a link click.",
      "source": "https://lightpanda.io/docs/reference/mcp-tools",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/lightpanda"
    },
    {
      "slug": "notte",
      "name": "Notte",
      "company": "Notte Labs Inc.",
      "grade": "B",
      "fit": "caveat",
      "why": "The MCP gives browser_observe (element IDs), browser_action, browser_scrape and browser_screenshot over a cloud session, and every session records an MP4. The browser is remote, so a localhost app needs the CLI tunnel command, which was not read.",
      "source": "https://docs.notte.cc/mcp-server",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/notte"
    },
    {
      "slug": "playwright-mcp",
      "name": "Playwright MCP",
      "company": "Microsoft Corporation",
      "grade": "B",
      "fit": "caveat",
      "why": "browser_snapshot takes depth, target and filename, browser_find returns matches instead of a tree, --snapshot-mode none stops action responses carrying one, and screenshots land in --output-dir. acc-01, acc-08, acc-09 and acc-10 use it for UI checks; acc-04 spent over 1M tokens on a 20-step test and acc-03 found it slow.",
      "source": "https://github.com/microsoft/playwright-mcp/blob/main/README.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/playwright-mcp"
    },
    {
      "slug": "puppeteer",
      "name": "Puppeteer",
      "company": "Google LLC",
      "grade": "BB",
      "fit": "caveat",
      "why": "A Node library: the agent writes a script that opens localhost, acts through locators and saves screenshots, so evidence per step is whatever the script prints. No snapshot or ref tool; page.accessibility.snapshot is the compact read. acc-58 let an agent troubleshoot web code this way in Docker.",
      "source": "https://pptr.dev/guides/page-interactions",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/puppeteer"
    },
    {
      "slug": "selenium",
      "name": "Selenium",
      "company": "Software Freedom Conservancy",
      "grade": "BB",
      "fit": "caveat",
      "why": "The agent writes WebDriver scripts in one of five languages and attaches screenshots on failure; there is no accessibility snapshot or ref tool, so page reads are page source or element queries. acc-59 had Claude write JUnit and Selenium tests with no result reported.",
      "source": "https://www.selenium.dev/documentation/guides/screenshots/",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/selenium"
    },
    {
      "slug": "skyvern",
      "name": "Skyvern",
      "company": "Ikonomos Inc.",
      "grade": "C",
      "fit": "caveat",
      "why": "An agent run records video, a screenshot and reasoning per step and Browser Address lets Skyvern drive your own browser over CDP, so localhost is reachable. Each action costs 30 credits, acc-54 waited 4 to 5 minutes for a six-field form, and a new account needs a card.",
      "source": "https://www.skyvern.com/docs/cloud/runs",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/skyvern"
    },
    {
      "slug": "steel",
      "name": "Steel",
      "company": "Nen Labs, Inc.",
      "grade": "BB",
      "fit": "caveat",
      "why": "The steel CLI drives a session with snapshot refs (@e3), waits for downloads and screenshots, and every session has replay, console and network tabs plus Agent Traces. The browser is in Steel's cloud, so localhost needs a tunnel, and Launch sessions end after 15 minutes.",
      "source": "https://docs.steel.dev/llms-full.txt",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/steel"
    },
    {
      "slug": "tinyfish",
      "name": "TinyFish",
      "company": "Tiny Fish, Inc.",
      "grade": "B",
      "fit": "caveat",
      "why": "A how-to runs a numbered user flow against a preview deploy or tunnelled localhost in Strict mode and returns passed as JSON, telling you to check passed rather than run status. Strict mode and max_steps are beta-gated, and steps cost $0.016 each.",
      "source": "https://docs.tinyfish.ai/agent/how-to/qa-preview-localhost",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/tinyfish"
    },
    {
      "slug": "curlshot",
      "name": "CurlShot",
      "company": "MEDIAPRONET SRL",
      "grade": "D",
      "fit": "no",
      "why": "One capture per call of a public URL; the MCP tool has no click, type or snapshot and cannot reach localhost. The REST click and wait_for_selector parameters stage one render, not a flow.",
      "source": "https://curlshot.com/docs/guides/ai-agents.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/curlshot"
    },
    {
      "slug": "pomerado",
      "name": "Pomerado",
      "company": "Pomerado AI, Inc.",
      "grade": "B",
      "fit": "no",
      "why": "Builds tools for public consumer sites and portals from a site_url origin; nothing drives a localhost or preview app step by step, and no screenshot or snapshot tool exists.",
      "source": "https://docs.pomerado.ai/guides/build/overview",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/pomerado"
    }
  ],
  "marks": "yes: the docs show it does the job as the success test says. caveat: it does the job with a limit an agent should know. no: it doesn't do this job. unchecked: we couldn't read it.",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-11-16",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.8",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run",
    "terms": "https://www.anchorterminal.com/terms/#data"
  },
  "useCase": {
    "accounts": 17,
    "after": [
      "agent-harnesses.spec-to-build-loop",
      "browser.capture-evidence"
    ],
    "area": "developer",
    "asks": [
      "open the app and check the signup flow works",
      "run the UI through the browser and tell me what breaks",
      "test this page as a new user",
      "take a look at the page and compare it with the design"
    ],
    "before": [
      "agent-harnesses.spec-to-build-loop",
      "agent-harnesses.fix-failing-ci"
    ],
    "blockers": [
      "a 20-step test that spends over a million tokens on snapshots (acc-04)",
      "refs that go stale after navigation so the agent retries blindly (acc-15)",
      "canvas and custom widgets outside the accessibility tree",
      "a tool that reports a saved screenshot that was never written (acc-62)"
    ],
    "capabilities": [
      "browser.control",
      "browser.debug",
      "browser.snapshot"
    ],
    "category": "browser",
    "categoryName": "Browser automation",
    "checked": "2026-11-12",
    "companies": {
      "fit": 4,
      "fitWithLimit": 15,
      "tagged": 30
    },
    "competition": "crowded",
    "fits": [
      "agent-browser",
      "browserbase",
      "chrome-devtools-mcp",
      "kane-cli"
    ],
    "fitsWithLimit": [
      "airtop",
      "anchor-browser",
      "browser-use",
      "browserless",
      "bx-playwright",
      "functionize-mcp",
      "hyperbrowser",
      "kernel",
      "lightpanda",
      "notte",
      "playwright-mcp",
      "puppeteer",
      "selenium",
      "skyvern",
      "steel",
      "tinyfish"
    ],
    "id": "browser.check-web-app",
    "listings": {
      "caveat": 16,
      "no": 2,
      "notRead": 0,
      "tagged": 33,
      "unchecked": 0,
      "yes": 4
    },
    "name": "Check a web app the agent is building in a real browser",
    "status": "draft",
    "success": "The agent reports pass or fail for each named step with a screenshot or snapshot as evidence. Measured: a 10-step flow takes at most 20 browser actions, and its page reads do not exceed about 50k tokens.",
    "url": "https://www.anchorterminal.com/api/v1/use-cases/browser.check-web-app.json",
    "weight": 22,
    "weightBasis": "15 of 61 accounts, the most common job on Hacker News among coding-agent users (acc-01, acc-03, acc-04, acc-08 to acc-11, acc-13, acc-16, acc-37, acc-39, acc-40, acc-48, acc-59, acc-61)"
  }
}
