{ "data": { "a": { "slug": "agent-browser", "name": "agent-browser", "vendor": "Vercel Labs", "vendorUrl": "https://agent-browser.dev", "kind": "mcp", "category": "browser", "summary": "agent-browser is an open-source command-line tool from Vercel Labs that lets AI agents drive Chrome through accessibility-tree snapshots and element refs. It runs locally as a Rust binary and includes a stdio MCP server.", "url": "https://www.anchorterminal.com/tools/agent-browser", "markdownUrl": "https://www.anchorterminal.com/tools/agent-browser.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/agent-browser.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/agent-browser.json", "repo": "https://github.com/vercel-labs/agent-browser", "license": "Apache-2.0", "transports": [ "stdio" ], "packages": [ { "registry": "npm", "name": "agent-browser" } ], "auth": "none", "authNotes": "No account or key. The CLI and its daemon run on the owner's machine. Site logins are held in a local auth vault encrypted with AES-256-GCM, in saved state files (plaintext unless `AGENT_BROWSER_ENCRYPTION_KEY` is set) or in a reused Chrome profile. Cloud browser providers and the optional `chat` command need their own keys in environment variables.", "pricing": "free", "pricingNotes": "Free and open source under Apache-2.0, with nothing to buy and no hosted service. The optional `chat` command and dashboard chat bill the user's own Vercel AI Gateway key, and cloud browser providers bill separately (checked 2026-10-08).", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the README, the docs or the source (checked 2026-10-08).", "endpoints": [] }, "toolCount": 158, "popularity": { "githubStars": 43679, "npmWeekly": 2069828, "pypiWeekly": null, "asOf": "2026-10-08" }, "docsUrl": "https://agent-browser.dev", "llmsTxt": "https://agent-browser.dev/llms.txt", "capabilities": [ "browser.control", "browser.debug" ], "tags": [ "official", "local", "open-source", "browser", "cli", "mcp", "rust", "no-auth", "llms-txt" ], "lastRelease": "2026-10-01", "graded": true, "anchor": { "graded": true, "score": 66.6, "grade": "B", "agentReady": false, "rank": 263, "ranked": true, "rankOf": 842, "categoryRank": 10, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 78, "maintenance": 70, "payments": 60, "reliability": 48, "schema": 84, "security": 67, "transparency": 61 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-08" }, "negative": 0, "verdict": "Snapshots with element refs, a 29-tool default MCP profile and opt-in domain allowlists, action policies and content boundary markers suit agent use. The project is at 0.38.2 with no stable release, the ten most recent CI runs on main failed between 1 and 8 October 2026, and every security control is off by default.", "bestFor": "Coding agents with a shell that want short commands and compact snapshots.", "strengths": [ "Accessibility-tree snapshots give each element a ref such as `@e2`, with `-i`, `-c`, `-d` and `--delta` to cut the output", "The stdio MCP server loads 29 tools by default and 158 with `--tools all`, each with a typed schema and `readOnlyHint`", "Domain allowlist, action policy, action confirmation and content boundary markers are documented with a threat model and known limitations", "19 tagged releases between 13 July and 1 October 2026, each with a changelog entry", "llms.txt and a Markdown copy of every docs page at agent-browser.dev, plus bundled skills served by `agent-browser skills get`" ], "weaknesses": [ "The ten most recent CI runs on main, 1 to 8 October 2026, all concluded in failure. In the newest, Windows Rust tests and native end-to-end tests failed", "Version 0.38.2 with a Vercel Labs badge and no stable release or deprecation policy", "All security controls are opt-in. By default there is no limit on navigation, actions or output", "crates.io holds 0.19.0 from 14 March 2026, although the README lists `cargo install agent-browser` as an install route", "No SECURITY.md in the repository, and 840 open issues and pull requests, with most of the newest issues unlabelled and unanswered" ], "agentNotes": [ "Run `agent-browser install` once after `npm install -g agent-browser`. It downloads Chrome for Testing", "Take a fresh `snapshot -i` after any navigation. Refs survive same-document changes only", "Pass `--json` for machine-readable results and `--max-output` to cap page text", "Set `--allowed-domains`, `--action-policy` and `--content-boundaries` for untrusted sites. None is on by default, and the allowlist rejects `--profile`, `--cdp` and `--restore`", "Start MCP with `agent-browser mcp`, and add profiles such as `--tools core,network` only when needed" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 66.6 } ], "editorialScores": { "ergonomics": 78, "maintenance": 70, "payments": 60, "reliability": 48, "schema": 84, "security": 67, "transparency": 68 }, "provenanceScore": 53 }, "connect": { "install": "npm install -g agent-browser \u0026\u0026 agent-browser install", "config": { "mcpServers": { "agent-browser": { "args": [ "mcp" ], "command": "agent-browser" } } } }, "letme": { "capability": "https://letme.dev/browser.control", "tool": "https://letme.dev/agent-browser" }, "area": "developer", "provenance": { "legalEntity": "Vercel Inc.", "domain": "agent-browser.dev", "domainRegistered": "2026-01-13", "domainNote": "The LICENSE file reads Copyright 2025 Vercel Inc., and the repository sits in the vercel-labs organisation on GitHub. agent-browser.dev has no security.txt (HTTP 404). vercel.com's is valid until 28 September 2027 and names HackerOne.", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://github.com/vercel-labs/agent-browser/blob/main/CHANGELOG.md", "securityTxt": "none", "checked": "2026-10-08", "notes": [ "No terms or privacy document governs this software beyond the Apache-2.0 licence, so `terms` and `privacy` are left out." ], "score": 53 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/agent-browser.json" }, "answer": "Browserless scores 70.4 (BB) on agent readiness against agent-browser's 66.6 (B), and leads in 4 of 7 scored categories. agent-browser leads on security \u0026 auth and payments \u0026 pricing.", "b": { "slug": "browserless", "name": "Browserless", "vendor": "browserless.io, Inc.", "vendorUrl": "https://www.browserless.io", "kind": "http-api", "category": "browser", "summary": "Browserless runs hosted headless browsers that agents drive over CDP, Playwright, REST endpoints, BrowserQL or its official MCP server. The same software can be self-hosted from a Docker image.", "url": "https://www.anchorterminal.com/tools/browserless", "markdownUrl": "https://www.anchorterminal.com/tools/browserless.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/browserless.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/browserless.json", "repo": "https://github.com/browserless/browserless", "license": "SSPL 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 proprietary", "transports": [ "http", "streamable-http", "stdio" ], "remoteUrl": "https://production-sfo.browserless.io", "packages": [ { "registry": "npm", "name": "@browserless.io/mcp" }, { "registry": "npm", "name": "@browserless.io/bap-ts" }, { "registry": "npm", "name": "@browserless.io/browserless" } ], "auth": "mixed", "authNotes": "Self-serve API token from the account dashboard after signing up in a browser. REST, BrowserQL and WebSocket routes take it as `?token=` in the URL. The hosted MCP server accepts OAuth sign-in with a Browserless account, an `Authorization: Bearer` header, or `?token=` for URL-only clients. An account holds up to 20 named tokens, each shown once and revocable on its own. Cloud tokens have no scopes. The admin, developer and viewer token roles apply to self-hosted Enterprise containers only.", "pricing": "freemium", "pricingNotes": "Free with 1,000 units a month, 2 concurrent browsers and 2-minute sessions, no card. A unit is up to 30 seconds of browser time. Prototyping is $35 a month ($25 billed annually) with 20,000 units, then $0.0020 a unit. Starter is $200 ($140) with 180,000 units, then $0.0017. Scale is $500 ($350) with 500,000 units, then $0.0015. Enterprise and self-hosting licences are priced by sales. An agent can start on the free plan once a person has signed up (https://www.browserless.io/pricing, checked 2026-10-08).", "priceSummary": "$0.002 / credit", "where": "both", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs (llms-full.txt), the OpenAPI document or the pricing page (checked 2026-10-08). The Stripe Link checkout tools are for an agent paying a merchant, not for paying Browserless.", "endpoints": [] }, "toolCount": 14, "popularity": { "githubStars": 13786, "npmWeekly": 3484, "pypiWeekly": null, "asOf": "2026-10-08" }, "docsUrl": "https://docs.browserless.io", "llmsTxt": "https://docs.browserless.io/llms.txt", "openapi": "https://www.browserless.io/swagger.json", "capabilities": [ "browser.control", "browser.hosted", "browser.debug", "scraping.js-render", "scraping.anti-bot", "scraping.proxies", "web.scrape", "web.crawl", "web.search", "pdf.generate" ], "tags": [ "official", "hosted", "self-hosted", "freemium", "free-tier", "no-card", "mcp", "oauth", "openapi", "llms-txt", "typescript", "source-available", "commercial-licence", "proxies", "status-page", "soc2" ], "lastRelease": "2026-10-05", "graded": true, "anchor": { "graded": true, "score": 70.4, "grade": "BB", "agentReady": true, "rank": 148, "ranked": true, "rankOf": 842, "categoryRank": 4, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 78, "maintenance": 82, "payments": 40, "reliability": 82, "schema": 89, "security": 53, "transparency": 62 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-08" }, "negative": 0, "verdict": "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 no machine payment route exists.", "bestFor": "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.", "strengths": [ "OpenAPI 3.0.0 document with 87 paths, llms.txt, llms-full.txt and Markdown twins of the docs", "Hosted MCP server at mcp.browserless.io with 14 documented tools, each carrying read-only and destructive annotations", "Free plan with 1,000 units a month and no card, with per-unit overage prices published for paid plans", "Up to 20 named API tokens per account, each revocable on its own, plus request logs filterable by key", "MCP server released 32 times between 10 July and 5 October 2026, with a dated changelog in the repository" ], "weaknesses": [ "REST and WebSocket routes take the API token as `?token=` in the URL, which the docs give as the standard method", "Cloud tokens have no scopes or roles. Token roles exist only on self-hosted Enterprise containers", "No x402, MPP or L402, and an account needs a person to sign up in a browser", "No prompt-injection guidance found in the docs or in the MCP agent prompt", "The terms allow the service to be changed or discontinued without notice, and the subprocessor list is on request only" ], "agentNotes": [ "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", "Close sessions as soon as the work is done. Browser time bills one unit per 30 seconds, rounded up, idle or not", "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", "On 429, back off and retry. It means the plan's concurrency limit or queue is full, usually from sessions left open", "Match the path to the protocol. Use `/chromium` for CDP clients and `/chromium/playwright` only for `playwright.connect()`" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "BB", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 70.4 } ], "editorialScores": { "ergonomics": 78, "maintenance": 82, "payments": 40, "reliability": 82, "schema": 89, "security": 53, "transparency": 47 }, "provenanceScore": 77 }, "connect": { "install": "npx -y @browserless.io/mcp", "http": "curl -X POST \"https://production-sfo.browserless.io/screenshot?token=YOUR_API_TOKEN_HERE\" -H \"Content-Type: application/json\" -d '{\"url\": \"https://scraping-sandbox.netlify.app/dashboard\"}' -o response.png", "claudeCode": "claude mcp add --transport http browserless https://mcp.browserless.io/mcp --header \"Authorization: Bearer YOUR_API_TOKEN_HERE\"", "config": { "mcpServers": { "browserless": { "headers": { "Authorization": "Bearer YOUR_API_TOKEN_HERE" }, "type": "http", "url": "https://mcp.browserless.io/mcp" } } } }, "letme": { "capability": "https://letme.dev/browser.control", "tool": "https://letme.dev/browserless" }, "area": "developer", "unitPrices": [ { "item": "Unit overage, Prototyping plan", "unit": "credit", "usd": 0.002, "note": "One unit is up to 30 seconds of browser time" }, { "item": "Unit overage, Starter plan", "unit": "credit", "usd": 0.0017 }, { "item": "Unit overage, Scale plan", "unit": "credit", "usd": 0.0015 }, { "item": "Browser time at the overage rate, Prototyping plan", "unit": "browser-hour", "usd": 0.24, "note": "Our arithmetic, 120 units at $0.0020" }, { "item": "Browser time at the overage rate, Starter plan", "unit": "browser-hour", "usd": 0.204, "note": "Our arithmetic, 120 units at $0.0017" }, { "item": "Browser time at the overage rate, Scale plan", "unit": "browser-hour", "usd": 0.18, "note": "Our arithmetic, 120 units at $0.0015" }, { "item": "Prototyping plan", "unit": "month", "usd": 35, "note": "20,000 units, $25 a month billed annually" }, { "item": "Starter plan", "unit": "month", "usd": 200, "note": "180,000 units, $140 a month billed annually" }, { "item": "Scale plan", "unit": "month", "usd": 500, "note": "500,000 units, $350 a month billed annually" } ], "provenance": { "legalEntity": "browserless.io, Inc.", "domain": "browserless.io", "domainRegistered": "2017-09-06", "endpointOnVendorDomain": true, "terms": "https://www.browserless.io/terms-of-service", "privacy": "https://www.browserless.io/privacy-policy", "statusPage": "https://status.browserless.io", "changelog": "https://www.browserless.io/changelog", "securityTxt": "none", "checked": "2026-10-08", "notes": [ "The terms of service name browserless.io, Inc., 23207 NE 192nd Ct, Battle Ground, WA 98604, United States. Neither the terms nor the privacy policy carries a date.", "www.browserless.io/.well-known/security.txt and docs.browserless.io/.well-known/security.txt both return 404. The trust centre sends vulnerability reports to security@browserless.io.", "RDAP for browserless.io gives a registration date of 2017-09-06.", "The API answers at production-sfo, production-lon and production-ams.browserless.io and the MCP server at mcp.browserless.io. The OAuth metadata at data.browserless.io names a supabase.co issuer." ], "score": 77 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/browserless.json", "live": { "slug": "browserless", "probe": { "target": "https://production-sfo.browserless.io", "method": "get", "lastAt": "2026-10-09T09:26:45.789424303Z", "lastOk": true, "lastStatus": 401, "lastMs": 457, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 437, "p95ms24h": 492, "samples24h": 194, "samples30d": 194, "days": [ { "date": "2026-10-08", "probes": 93, "ok": 93 }, { "date": "2026-10-09", "probes": 101, "ok": 101 } ] }, "vendorStatus": { "page": "https://status.browserless.io", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-10-09T07:57:40.838680212Z" }, "versions": [ { "registry": "github", "name": "browserless/browserless", "version": "v2.57.0", "released": "2026-09-30", "seenAt": "2026-10-08T16:04:11.420407881Z" }, { "registry": "npm", "name": "@browserless.io/bap-ts", "version": "2.0.0", "seenAt": "2026-10-08T16:04:09.167089658Z" }, { "registry": "npm", "name": "@browserless.io/browserless", "version": "2.57.0", "seenAt": "2026-10-08T16:04:09.383268902Z" }, { "registry": "npm", "name": "@browserless.io/mcp", "version": "1.36.0", "seenAt": "2026-10-08T16:04:05.40282872Z" } ], "githubStars": 13789, "npmWeekly": 3484, "securityTxt": { "url": "https://browserless.io/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-08T15:38:39.246027784Z" }, "pages": [ { "url": "https://www.browserless.io/changelog", "kind": "changelog", "status": 200, "checkedAt": "2026-10-08T18:26:50.435621953Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "fe50f4cf4543" }, { "url": "https://www.browserless.io/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-10-08T18:26:52.807666862Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "4b721f855891" }, { "url": "https://www.browserless.io/privacy-policy", "kind": "privacy", "status": 200, "checkedAt": "2026-10-08T18:26:54.678161564Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "2d27c63baca4" }, { "url": "https://www.browserless.io/terms-of-service", "kind": "terms", "status": 200, "checkedAt": "2026-10-08T18:26:56.798474291Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "407b3dff8ee7" } ], "updatedAt": "2026-10-09T09:26:45.789424303Z" } }, "facts": [ { "a": "MCP server", "b": "HTTP API", "name": "Kind" }, { "a": "Vercel Labs", "b": "browserless.io, Inc.", "name": "Vendor" }, { "a": "no (local only)", "b": "https://production-sfo.browserless.io", "name": "Hosted endpoint" }, { "a": "stdio", "b": "HTTP, Streamable HTTP, stdio", "name": "Transports" }, { "a": "None", "b": "OAuth or key", "name": "Auth" }, { "a": "Free", "b": "Freemium", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Apache-2.0", "b": "SSPL 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 proprietary", "name": "Licence" }, { "a": "158", "b": "14", "name": "Tools exposed" }, { "a": "no", "b": "yes", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "2026-10-01", "b": "2026-10-05", "name": "Last release" }, { "a": "no document linked", "b": "no date given", "name": "Terms last updated" }, { "a": "no document linked", "b": "no date given", "name": "Privacy policy last updated" }, { "a": "", "b": "not found in the text", "name": "Customer content may train models" }, { "a": "", "b": "yes", "name": "Terms restrict automated access" }, { "a": "", "b": "not found in the text", "name": "Terms restrict benchmarking" }, { "a": "", "b": "yes", "name": "Terms or service can change without notice" }, { "a": "", "b": "not found in the text", "name": "Arbitration or class-action waiver" }, { "a": "44k stars, 2.1M npm/wk", "b": "14k stars, 3.5k npm/wk", "name": "Popularity" } ], "faq": [ { "answer": "Browserless scores 70.4 (BB) on agent readiness against agent-browser's 66.6 (B), and leads in 4 of 7 scored categories. agent-browser leads on security \u0026 auth and payments \u0026 pricing.", "question": "Which is better for AI agents, agent-browser or Browserless?" }, { "answer": "agent-browser needs no key. Browserless takes an API key or an OAuth sign-in.", "question": "Do agent-browser and Browserless need an API key?" }, { "answer": "agent-browser runs on your own machine, with no hosted endpoint listed. Browserless has a hosted endpoint at https://production-sfo.browserless.io.", "question": "Can an agent call agent-browser and Browserless without installing anything?" }, { "answer": "agent-browser is open source (Apache-2.0). No open-source release is listed for Browserless.", "question": "Are agent-browser and Browserless open source?" } ], "goodFor": [ { "aheadOn": [ "Security \u0026 auth, 67 against 53", "Payments \u0026 pricing, 60 against 40" ], "also": [ "No key needed to call it", "Open source" ], "goodFor": "Coding agents with a shell that want short commands and compact snapshots.", "slug": "agent-browser", "watchFor": "The ten most recent CI runs on main, 1 to 8 October 2026, all concluded in failure. In the newest, Windows Rust tests and native end-to-end tests failed" }, { "aheadOn": [ "Reliability, 82 against 48", "Schema \u0026 documentation, 89 against 84", "Maintenance \u0026 community, 82 against 70" ], "also": [ "Agent-ready, a grade of BB or better", "A hosted endpoint, with nothing to install", "Free to start without a card" ], "goodFor": "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.", "slug": "browserless", "watchFor": "REST and WebSocket routes take the API token as `?token=` in the URL, which the docs give as the standard method" } ], "job": { "capability": "browser.control", "name": "Browser automation" }, "others": [ { "json": "https://www.anchorterminal.com/compare/agent-browser-vs-airtop.json", "title": "agent-browser vs Airtop", "url": "https://www.anchorterminal.com/compare/agent-browser-vs-airtop" }, { "json": "https://www.anchorterminal.com/compare/agent-browser-vs-anchor-browser.json", "title": "agent-browser vs Anchor Browser", "url": "https://www.anchorterminal.com/compare/agent-browser-vs-anchor-browser" }, { "json": "https://www.anchorterminal.com/compare/agent-browser-vs-browser-use.json", "title": "agent-browser vs Browser Use", "url": "https://www.anchorterminal.com/compare/agent-browser-vs-browser-use" }, { "json": "https://www.anchorterminal.com/compare/agent-browser-vs-browserbase.json", "title": "agent-browser vs Browserbase", "url": "https://www.anchorterminal.com/compare/agent-browser-vs-browserbase" }, { "json": "https://www.anchorterminal.com/compare/agent-browser-vs-chrome-devtools-mcp.json", "title": "agent-browser vs Chrome DevTools MCP", "url": "https://www.anchorterminal.com/compare/agent-browser-vs-chrome-devtools-mcp" }, { "json": "https://www.anchorterminal.com/compare/agent-browser-vs-hyperbrowser.json", "title": "agent-browser vs Hyperbrowser", "url": "https://www.anchorterminal.com/compare/agent-browser-vs-hyperbrowser" }, { "json": "https://www.anchorterminal.com/compare/agent-browser-vs-notte.json", "title": "agent-browser vs Notte", "url": "https://www.anchorterminal.com/compare/agent-browser-vs-notte" }, { "json": "https://www.anchorterminal.com/compare/agent-browser-vs-playwright-mcp.json", "title": "agent-browser vs Playwright MCP", "url": "https://www.anchorterminal.com/compare/agent-browser-vs-playwright-mcp" }, { "json": "https://www.anchorterminal.com/compare/agent-browser-vs-puppeteer-reference-server-archived.json", "title": "agent-browser vs Puppeteer (archived MCP reference server)", "url": "https://www.anchorterminal.com/compare/agent-browser-vs-puppeteer-reference-server-archived" }, { "json": "https://www.anchorterminal.com/compare/agent-browser-vs-skyvern.json", "title": "agent-browser vs Skyvern", "url": "https://www.anchorterminal.com/compare/agent-browser-vs-skyvern" }, { "json": "https://www.anchorterminal.com/compare/agent-browser-vs-steel.json", "title": "agent-browser vs Steel", "url": "https://www.anchorterminal.com/compare/agent-browser-vs-steel" }, { "json": "https://www.anchorterminal.com/compare/agent-browser-vs-tinyfish.json", "title": "agent-browser vs TinyFish", "url": "https://www.anchorterminal.com/compare/agent-browser-vs-tinyfish" }, { "json": "https://www.anchorterminal.com/compare/airtop-vs-browserless.json", "title": "Airtop vs Browserless", "url": "https://www.anchorterminal.com/compare/airtop-vs-browserless" }, { "json": "https://www.anchorterminal.com/compare/anchor-browser-vs-browserless.json", "title": "Anchor Browser vs Browserless", "url": "https://www.anchorterminal.com/compare/anchor-browser-vs-browserless" }, { "json": "https://www.anchorterminal.com/compare/browser-use-vs-browserless.json", "title": "Browser Use vs Browserless", "url": "https://www.anchorterminal.com/compare/browser-use-vs-browserless" }, { "json": "https://www.anchorterminal.com/compare/browserless-vs-chrome-devtools-mcp.json", "title": "Browserless vs Chrome DevTools MCP", "url": "https://www.anchorterminal.com/compare/browserless-vs-chrome-devtools-mcp" }, { "json": "https://www.anchorterminal.com/compare/browserless-vs-hyperbrowser.json", "title": "Browserless vs Hyperbrowser", "url": "https://www.anchorterminal.com/compare/browserless-vs-hyperbrowser" }, { "json": "https://www.anchorterminal.com/compare/browserless-vs-notte.json", "title": "Browserless vs Notte", "url": "https://www.anchorterminal.com/compare/browserless-vs-notte" }, { "json": "https://www.anchorterminal.com/compare/browserless-vs-playwright-mcp.json", "title": "Browserless vs Playwright MCP", "url": "https://www.anchorterminal.com/compare/browserless-vs-playwright-mcp" }, { "json": "https://www.anchorterminal.com/compare/browserless-vs-puppeteer-reference-server-archived.json", "title": "Browserless vs Puppeteer (archived MCP reference server)", "url": "https://www.anchorterminal.com/compare/browserless-vs-puppeteer-reference-server-archived" }, { "json": "https://www.anchorterminal.com/compare/browserless-vs-skyvern.json", "title": "Browserless vs Skyvern", "url": "https://www.anchorterminal.com/compare/browserless-vs-skyvern" }, { "json": "https://www.anchorterminal.com/compare/browserless-vs-steel.json", "title": "Browserless vs Steel", "url": "https://www.anchorterminal.com/compare/browserless-vs-steel" }, { "json": "https://www.anchorterminal.com/compare/browserless-vs-tinyfish.json", "title": "Browserless vs TinyFish", "url": "https://www.anchorterminal.com/compare/browserless-vs-tinyfish" }, { "json": "https://www.anchorterminal.com/compare/browserbase-vs-browserless.json", "title": "Browserbase vs Browserless", "url": "https://www.anchorterminal.com/compare/browserbase-vs-browserless" } ], "scores": [ { "agent-browser": 48, "browserless": 82, "by": 34, "edge": "browserless", "key": "reliability", "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "agent-browser": 84, "browserless": 89, "by": 5, "edge": "browserless", "key": "schema", "name": "Schema \u0026 documentation", "weight": 13 }, { "agent-browser": 78, "browserless": 78, "by": 0, "edge": "", "key": "ergonomics", "name": "Agent ergonomics", "weight": 13 }, { "agent-browser": 67, "browserless": 53, "by": 14, "edge": "agent-browser", "key": "security", "name": "Security \u0026 auth", "weight": 14 }, { "agent-browser": 60, "browserless": 40, "by": 20, "edge": "agent-browser", "key": "payments", "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "agent-browser": 70, "browserless": 82, "by": 12, "edge": "browserless", "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7 }, { "agent-browser": 61, "browserless": 62, "by": 1, "edge": "browserless", "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Browserless scores 70.4 (BB) on agent readiness against agent-browser's 66.6 (B), and leads in 4 of 7 scored categories. agent-browser leads on security \u0026 auth and payments \u0026 pricing. Both do browser automation.", "verdicts": { "agent-browser": "Snapshots with element refs, a 29-tool default MCP profile and opt-in domain allowlists, action policies and content boundary markers suit agent use. The project is at 0.38.2 with no stable release, the ten most recent CI runs on main failed between 1 and 8 October 2026, and every security control is off by default.", "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 no machine payment route exists." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/agent-browser-vs-browserless", "json": "https://www.anchorterminal.com/compare/agent-browser-vs-browserless.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/agent-browser-vs-browserless.md", "slim": "https://www.anchorterminal.com/compare/agent-browser-vs-browserless.min.md" }, "markdown": "Browserless scores 70.4 (BB) on agent readiness against agent-browser's 66.6 (B), and leads in 4 of 7 scored categories. agent-browser leads on security \u0026 auth and payments \u0026 pricing. Both do browser automation.\n\n- agent-browser: grade B, 66.6/100, rank #263 of 842. Markdown https://www.anchorterminal.com/tools/agent-browser.md · JSON https://www.anchorterminal.com/api/v1/tools/agent-browser.json\n- Browserless: grade BB, 70.4/100, rank #148 of 842. Markdown https://www.anchorterminal.com/tools/browserless.md · JSON https://www.anchorterminal.com/api/v1/tools/browserless.json\n\n## Which one, for what\n\n### agent-browser (B)\n\nGood for: Coding agents with a shell that want short commands and compact snapshots.\n\nAhead on:\n- Security \u0026 auth, 67 against 53\n- Payments \u0026 pricing, 60 against 40\n\nAlso in its favour:\n- No key needed to call it\n- Open source\n\nWatch for: The ten most recent CI runs on main, 1 to 8 October 2026, all concluded in failure. In the newest, Windows Rust tests and native end-to-end tests failed\n\n### Browserless (BB)\n\nGood 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.\n\nAhead on:\n- Reliability, 82 against 48\n- Schema \u0026 documentation, 89 against 84\n- Maintenance \u0026 community, 82 against 70\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n- A hosted endpoint, with nothing to install\n- Free to start without a card\n\nWatch for: REST and WebSocket routes take the API token as `?token=` in the URL, which the docs give as the standard method\n\n\n## Score by category\n\n| Category | Weight | agent-browser | Browserless | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 48 | 82 | Browserless +34 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 84 | 89 | Browserless +5 |\n| Agent ergonomics | 13% (16.2 this run) | 78 | 78 | even |\n| Security \u0026 auth | 14% (17.5 this run) | 67 | 53 | agent-browser +14 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 60 | 40 | agent-browser +20 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 70 | 82 | Browserless +12 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 61 | 62 | Browserless +1 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **66.6 · B** | **70.4 · BB** | |\n\n## Facts side by side\n\n| Fact | agent-browser | Browserless |\n| --- | --- | --- |\n| Kind | MCP server | HTTP API |\n| Vendor | Vercel Labs | browserless.io, Inc. |\n| Hosted endpoint | no (local only) | `https://production-sfo.browserless.io` |\n| Transports | stdio | HTTP, Streamable HTTP, stdio |\n| Auth | None | OAuth or key |\n| Pricing | Free | Freemium |\n| x402 | no | no |\n| Licence | Apache-2.0 | SSPL 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 proprietary |\n| Tools exposed | 158 | 14 |\n| Read-only variant documented | no | yes |\n| llms.txt | yes | yes |\n| Last release | 2026-10-01 | 2026-10-05 |\n| Terms last updated | no document linked | no date given |\n| Privacy policy last updated | no document linked | no date given |\n| Customer content may train models | | not found in the text |\n| Terms restrict automated access | | yes |\n| Terms restrict benchmarking | | not found in the text |\n| Terms or service can change without notice | | yes |\n| Arbitration or class-action waiver | | not found in the text |\n| Popularity | 44k stars, 2.1M npm/wk | 14k stars, 3.5k npm/wk |\n\n## Verdicts\n\n**agent-browser.** Snapshots with element refs, a 29-tool default MCP profile and opt-in domain allowlists, action policies and content boundary markers suit agent use. The project is at 0.38.2 with no stable release, the ten most recent CI runs on main failed between 1 and 8 October 2026, and every security control is off by default.\n\n**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 no machine payment route exists.\n\n## Before you call either\n\n### agent-browser\n\n1. Run `agent-browser install` once after `npm install -g agent-browser`. It downloads Chrome for Testing\n2. Take a fresh `snapshot -i` after any navigation. Refs survive same-document changes only\n3. Pass `--json` for machine-readable results and `--max-output` to cap page text\n4. Set `--allowed-domains`, `--action-policy` and `--content-boundaries` for untrusted sites. None is on by default, and the allowlist rejects `--profile`, `--cdp` and `--restore`\n5. Start MCP with `agent-browser mcp`, and add profiles such as `--tools core,network` only when needed\n\n### Browserless\n\n1. 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\n2. Close sessions as soon as the work is done. Browser time bills one unit per 30 seconds, rounded up, idle or not\n3. 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\n4. On 429, back off and retry. It means the plan's concurrency limit or queue is full, usually from sessions left open\n5. Match the path to the protocol. Use `/chromium` for CDP clients and `/chromium/playwright` only for `playwright.connect()`\n\n## Questions\n\n### Which is better for AI agents, agent-browser or Browserless?\n\nBrowserless scores 70.4 (BB) on agent readiness against agent-browser's 66.6 (B), and leads in 4 of 7 scored categories. agent-browser leads on security \u0026 auth and payments \u0026 pricing.\n\n### Do agent-browser and Browserless need an API key?\n\nagent-browser needs no key. Browserless takes an API key or an OAuth sign-in.\n\n### Can an agent call agent-browser and Browserless without installing anything?\n\nagent-browser runs on your own machine, with no hosted endpoint listed. Browserless has a hosted endpoint at https://production-sfo.browserless.io.\n\n### Are agent-browser and Browserless open source?\n\nagent-browser is open source (Apache-2.0). No open-source release is listed for Browserless.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/agent-browser-vs-browserless.json, and with the fewest tokens: https://www.anchorterminal.com/compare/agent-browser-vs-browserless.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"agent-browser\", \"b\": \"browserless\"}`. From a terminal: `anchor compare agent-browser browserless`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/agent-browser.json and https://www.anchorterminal.com/api/v1/tools/browserless.json\n\n## Other comparisons with agent-browser or Browserless\n\n- [agent-browser vs Airtop](https://www.anchorterminal.com/compare/agent-browser-vs-airtop.md)\n- [agent-browser vs Anchor Browser](https://www.anchorterminal.com/compare/agent-browser-vs-anchor-browser.md)\n- [agent-browser vs Browser Use](https://www.anchorterminal.com/compare/agent-browser-vs-browser-use.md)\n- [agent-browser vs Browserbase](https://www.anchorterminal.com/compare/agent-browser-vs-browserbase.md)\n- [agent-browser vs Chrome DevTools MCP](https://www.anchorterminal.com/compare/agent-browser-vs-chrome-devtools-mcp.md)\n- [agent-browser vs Hyperbrowser](https://www.anchorterminal.com/compare/agent-browser-vs-hyperbrowser.md)\n- [agent-browser vs Notte](https://www.anchorterminal.com/compare/agent-browser-vs-notte.md)\n- [agent-browser vs Playwright MCP](https://www.anchorterminal.com/compare/agent-browser-vs-playwright-mcp.md)\n- [agent-browser vs Puppeteer (archived MCP reference server)](https://www.anchorterminal.com/compare/agent-browser-vs-puppeteer-reference-server-archived.md)\n- [agent-browser vs Skyvern](https://www.anchorterminal.com/compare/agent-browser-vs-skyvern.md)\n- [agent-browser vs Steel](https://www.anchorterminal.com/compare/agent-browser-vs-steel.md)\n- [agent-browser vs TinyFish](https://www.anchorterminal.com/compare/agent-browser-vs-tinyfish.md)\n- [Airtop vs Browserless](https://www.anchorterminal.com/compare/airtop-vs-browserless.md)\n- [Anchor Browser vs Browserless](https://www.anchorterminal.com/compare/anchor-browser-vs-browserless.md)\n- [Browser Use vs Browserless](https://www.anchorterminal.com/compare/browser-use-vs-browserless.md)\n- [Browserless vs Chrome DevTools MCP](https://www.anchorterminal.com/compare/browserless-vs-chrome-devtools-mcp.md)\n- [Browserless vs Hyperbrowser](https://www.anchorterminal.com/compare/browserless-vs-hyperbrowser.md)\n- [Browserless vs Notte](https://www.anchorterminal.com/compare/browserless-vs-notte.md)\n- [Browserless vs Playwright MCP](https://www.anchorterminal.com/compare/browserless-vs-playwright-mcp.md)\n- [Browserless vs Puppeteer (archived MCP reference server)](https://www.anchorterminal.com/compare/browserless-vs-puppeteer-reference-server-archived.md)\n- [Browserless vs Skyvern](https://www.anchorterminal.com/compare/browserless-vs-skyvern.md)\n- [Browserless vs Steel](https://www.anchorterminal.com/compare/browserless-vs-steel.md)\n- [Browserless vs TinyFish](https://www.anchorterminal.com/compare/browserless-vs-tinyfish.md)\n- [Browserbase vs Browserless](https://www.anchorterminal.com/compare/browserbase-vs-browserless.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-09", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.4", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "agent-browser vs Browserless", "url": "" } ], "description": "Browserless scores 70.4 (BB) on agent readiness against agent-browser's 66.6 (B), and leads in 4 of 7 scored categories. agent-browser leads on security \u0026 auth and payments \u0026 pricing. Both do browser automation. Category scores, facts, verdicts and agent notes side by side.", "facts": [ "agent-browser B 66.6", "Browserless BB 70.4", "scores" ], "h1": "agent-browser vs Browserless", "image": "https://www.anchorterminal.com/assets/og/compare-agent-browser-vs-browserless.png", "path": "/compare/agent-browser-vs-browserless", "published": "2026-10-01", "section": "tools", "title": "agent-browser vs Browserless for AI agents, B 66.6 vs BB 70.4", "toc": null, "updated": "2026-10-09", "url": "https://www.anchorterminal.com/compare/agent-browser-vs-browserless" }, "tokens": { "markdown": 2550, "slim": 780 }, "version": 1 }