{ "data": { "a": { "slug": "autocua", "name": "AutoCua", "vendor": "Ashish Yadav and contributors (ComputerUseAgent on GitHub)", "vendorUrl": "https://github.com/ComputerUseAgent/AutoCua", "kind": "framework", "category": "desktop-automation", "summary": "AutoCua is an open-source Python agent that operates a computer the way a person does, desktop apps, a terminal, your own Chrome and iOS or Android phones, with any of 60 models from ten providers.", "url": "https://www.anchorterminal.com/tools/autocua", "markdownUrl": "https://www.anchorterminal.com/tools/autocua.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/autocua.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/autocua.json", "dns": "autocua.grade.anchorterminal.com", "repo": "https://github.com/ComputerUseAgent/AutoCua", "license": "MIT", "transports": [], "packages": [ { "registry": "pypi", "name": "AutoCua" } ], "auth": "none", "authNotes": "No account. You bring an API key for the model provider you choose, kept with chats, Chrome profiles and a credential vault in a local AutoCua_data folder.", "pricing": "free", "pricingNotes": "Free and MIT-licensed. You pay your model provider for tokens. Nothing to buy from the project (checked 2026-11-06).", "priceSummary": "Free · OSS", "where": "library", "x402": { "level": "no", "evidence": "A local package with nothing to buy and no payment protocol (checked 2026-11-06).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-06" }, "docsUrl": "https://github.com/ComputerUseAgent/AutoCua#readme", "capabilities": [ "browser.control", "agent.run" ], "tags": [ "open-source", "mit", "python", "computer-use", "local", "new" ], "lastRelease": "2026-11-04", "graded": true, "anchor": { "graded": true, "score": 44.3, "grade": "E", "agentReady": false, "rank": 1100, "ranked": true, "rankOf": 1354, "categoryRank": 8, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 55, "maintenance": 65, "payments": 60, "reliability": 25, "schema": 42, "security": 38, "transparency": 42 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "low", "date": "2026-11-06" }, "negative": 0, "verdict": "A capable, fast-moving open-source agent for driving desktops, browsers and phones through real input and accessibility trees, with a careful safety section. It's two weeks old, with no test CI or changelog, and on Windows the model itself decides whether to accept an admin elevation prompt.", "bestFor": "Developers who want a local agent to operate desktop apps, their own browser or phones across platforms, on a machine they control.", "strengths": [ "One run_agent call drives the desktop, a terminal, your Chrome, or an iOS or Android device", "Element picking from accessibility trees and OCR instead of pixel coordinates", "Credentials typed from a vault so the model never sees them, in the browser and phone agents", "No telemetry, and nothing downloaded without a yes on the terminal", "MIT licence, a pip wheel per OS and architecture, and 60 models across ten providers" ], "weaknesses": [ "Two weeks old at version 0.1.9, with no changelog file", "No CI running the tests; the only workflow labels issues", "On Windows the model answers UAC elevation prompts itself through a kernel input driver", "Keeps API keys and logged-in Chrome profiles in a local folder next to the checkout", "No API reference beyond the README" ], "agentNotes": [ "pip install AutoCua, then call run_agent with a mode such as \"web use\" or \"computer use\", a provider, a model and a task", "Run it on a machine or account you can afford to lose; it drives real input and keeps logged-in browser profiles", "On Windows, don't install the Interception driver unless you accept the model deciding UAC prompts", "Set AutoCua_DATA_DIR to keep keys and profiles somewhere private", "Phones go over USB from a script; Wi-Fi only through the desktop app" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "low", "grade": "E", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 44.3 } ], "editorialScores": { "ergonomics": 55, "maintenance": 65, "payments": 60, "reliability": 25, "schema": 42, "security": 38, "transparency": 70 }, "provenanceScore": 13, "checked": { "categories": { "ergonomics": "2026-11-06", "maintenance": "2026-11-06", "payments": "2026-11-06", "reliability": "2026-11-06", "schema": "2026-11-06", "security": "2026-11-06", "transparency": "2026-11-06" }, "last": "2026-11-06", "oldest": "2026-11-06", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "pip install AutoCua\n# then, in Python:\n# from AutoCua.agent_launcher import run_agent\n# run_agent(mode=\"web use\", provider=\"openrouter\", model=\"gemini-3.8-flash\", task=\"Open wikipedia.org and summarise today's featured article.\")" }, "letme": { "capability": "https://letme.dev/browser.control", "tool": "https://letme.dev/autocua" }, "area": "developer", "provenance": { "legalEntity": "", "domain": "github.com", "domainRegistered": "", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-11-06", "notes": [ "The licence names Ashish Yadav as copyright holder; most commits are from the GitHub user FunctionFreak. No company, site or terms were found.", "github.com/AutoCua/AutoCua and github.com/ComputerUseAgent/AutoCua serve the same main branch, so one is a rename or mirror of the other." ], "score": 13 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/autocua.json" }, "answer": "Functionize MCP server and AutoCua score within a point of each other on agent readiness, 44.6 (E) and 44.3 (E). AutoCua leads on schema \u0026 documentation, agent ergonomics, payments \u0026 pricing and maintenance \u0026 community.", "b": { "slug": "functionize-mcp", "name": "Functionize MCP server", "vendor": "Functionize, Inc.", "vendorUrl": "https://www.functionize.com", "kind": "mcp", "category": "browser", "summary": "The Functionize MCP server is a hosted remote server from Functionize, Inc. that lets coding agents such as Claude Code, Cursor and GitHub Copilot build, run and diagnose browser tests of a live web app in Functionize Studio.", "url": "https://www.anchorterminal.com/tools/functionize-mcp", "markdownUrl": "https://www.anchorterminal.com/tools/functionize-mcp.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/functionize-mcp.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/functionize-mcp.json", "dns": "functionize-mcp.grade.anchorterminal.com", "repo": "https://github.com/FunctionizeInc/functionize-mcp-plugin", "license": "Proprietary hosted service under Functionize's Terms of Service (version 2.0, effective 10 July 2026). The Claude Code plugin and its two skills are MIT-licensed; the server's source isn't public", "transports": [ "streamable-http" ], "remoteUrl": "https://mcp.functionize.com/mcp", "packages": [], "auth": "oauth", "authNotes": "OAuth only, with no API key. The client opens a browser sign-in with the person's Functionize account. The authorisation server metadata gives the authorisation code grant with PKCE S256, refresh tokens, dynamic client registration, client ID metadata documents, public clients only and a revocation endpoint. The protected resource lists the scopes `agent.sessions:read`, `agent.sessions:write` and `offline_access`. The connection works in the account's default team, or the team named in an `X-Functionize-Team-Id` header, checked on every request (403 if not a member). Per SETUP.md it can read, continue or cancel any session in that team, including colleagues' (https://mcp.functionize.com/.well-known/oauth-authorization-server, https://github.com/FunctionizeInc/functionize-mcp-plugin/blob/main/SETUP.md, checked 2026-10-24).", "pricing": "freemium", "pricingNotes": "Studio's Free plan is $0 with no card and no time limit, with 800,000 credits a month on the plan card (the FAQ on the same page says 400,000) and 5 parallel runs. Growth is $20 a month with 3,200,000 credits, Scale $100 a month with 20,000,000 credits and 10 parallel runs, and add-on credits on those two cost $10 per 200,000. Enterprise is custom, with invoice billing and a 12-month minimum. Agent work (creating, running, diagnosing tests) uses credits at a cost that varies by task and isn't published; editing, reports and settings use none. Credits aren't refunded and monthly credits don't roll over. The pricing page has no MCP row; the launch release says the server is available to Studio customers and trial users (https://www.functionize.com/pricing, https://www.functionize.com/usage-limits, checked 2026-10-24).", "priceSummary": "$20 / mo", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 on the MCP page, pricing page, usage-limits page, terms or the plugin repository. Unauthenticated MCP calls answer 401 with an OAuth resource-metadata pointer, not a payment request (checked 2026-10-24).", "endpoints": [] }, "toolCount": 10, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-24" }, "docsUrl": "https://github.com/FunctionizeInc/functionize-mcp-plugin/blob/main/SETUP.md", "llmsTxt": "https://www.functionize.com/llms.txt", "capabilities": [ "browser.control", "browser.hosted", "browser.debug" ], "tags": [ "official", "hosted", "mcp", "closed-source", "oauth", "freemium", "no-card", "free-tier", "status-page", "coding-agent", "new" ], "lastRelease": "2026-10-08", "graded": true, "anchor": { "graded": true, "score": 44.6, "grade": "E", "agentReady": false, "rank": 1088, "ranked": true, "rankOf": 1354, "categoryRank": 21, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 43, "maintenance": 49, "payments": 30, "reliability": 50, "schema": 29, "security": 56, "transparency": 58 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "low", "date": "2026-10-24" }, "negative": 0, "verdict": "The server passes a coding agent's test requests to Functionize Studio's testing agent, which tests a live web app in cloud browsers and reports the failing step. It uses OAuth with read and write scopes and has a no-card free plan. Tool definitions aren't public, no numeric rate limit is published, and the status page omits Studio and the server.", "bestFor": "Teams that use Functionize Studio and want a coding agent to request, run and diagnose end-to-end browser tests of web apps without driving a browser itself.", "strengths": [ "OAuth only, with PKCE, dynamic client registration, a revocation endpoint and separate `agent.sessions:read` and `agent.sessions:write` scopes; no API key to leak", "A free Studio plan with no card and no time limit, and paid plans from $20 a month published without a login", "Ten tools by the README's count, with the long guidance kept in optional Claude Code skills", "Failed runs come back with the first failing step, screenshots and logs, and Studio says whether a failure looks like a regression or a page change", "SETUP.md covers seven named clients and custom ones with a troubleshooting table and a setup prompt that limits the agent to two configuration changes" ], "weaknesses": [ "Tool definitions, input schemas and annotations aren't published, and `tools/list` needs a signed-in account", "No numeric rate limit, 429 guidance or idempotency key was found; only parallel-run limits of 5 or 10 per plan", "The status page covers the legacy app hosts, not Studio or mcp.functionize.com", "The connection's reach is the whole team, so it can read, continue or cancel colleagues' sessions", "Credits per task aren't published, and the Free plan's monthly credits are given as 800,000 and 400,000 on the same page" ], "agentNotes": [ "Have the person complete the browser sign-in, which an agent can't do, then check the connection with `list_agent_teams`", "Pass the project ID, environment and test ID in `start_agent_session`, and continue a waiting session with `send_agent_message` rather than starting another", "Report a created test as done only after a green run, not on a test ID or a green generation", "After a dropped connection, list the project's recent tests before creating a test again, since a submitted create finishes on the server", "Send the `X-Functionize-Team-Id` header to pin a team, and keep credentials in masked Studio variables, never in prompts" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 4, "avgRating": 2.8, "history": [ { "basis": "public evidence", "confidence": "low", "grade": "E", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 44.6 } ], "editorialScores": { "ergonomics": 43, "maintenance": 49, "payments": 30, "reliability": 50, "schema": 29, "security": 56, "transparency": 38 }, "provenanceScore": 77, "checked": { "categories": { "ergonomics": "2026-10-24", "maintenance": "2026-10-24", "payments": "2026-10-24", "reliability": "2026-10-24", "schema": "2026-10-24", "security": "2026-10-24", "transparency": "2026-10-24" }, "last": "2026-10-24", "lastMoved": "2026-10-30", "oldest": "2026-10-24", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "claude plugin marketplace add FunctionizeInc/functionize-mcp-plugin \u0026\u0026 claude plugin install functionize-mcp@functionize-mcp-plugin", "claudeCode": "claude mcp add --transport http functionize https://mcp.functionize.com/mcp", "config": { "mcpServers": { "functionize": { "url": "https://mcp.functionize.com/mcp" } } } }, "letme": { "capability": "https://letme.dev/browser.control", "tool": "https://letme.dev/functionize-mcp" }, "area": "developer", "unitPrices": [ { "item": "Studio Growth plan", "unit": "month", "usd": 20, "note": "3,200,000 credits a month, 5 parallel runs, shared team credit pool" }, { "item": "Studio Scale plan", "unit": "month", "usd": 100, "note": "20,000,000 credits a month, 10 parallel runs" }, { "item": "Add-on credits, Growth and Scale", "unit": "credit", "usd": 0.00005, "note": "$10 per 200,000 credits; credits per task not published; no refunds or roll-over" } ], "provenance": { "legalEntity": "Functionize, Inc.", "domain": "functionize.com", "domainRegistered": "2015-03-19", "endpointOnVendorDomain": true, "terms": "https://resources.functionize.com/hubfs/Functionize-ToS.pdf", "privacy": "https://www.functionize.com/privacy-policy", "statusPage": "https://status.functionize.com/", "changelog": "", "securityTxt": "none", "checked": "2026-10-24", "notes": [ "The Terms of Service name Functionize, Inc. and California law, version 2.0, effective 10 July 2026. A 2022 version is still linked in the footer.", "The privacy policy is effective 10 July 2026 and supersedes a version of 12 May 2026.", "/.well-known/security.txt answered 404 on www.functionize.com and mcp.functionize.com. The terms give security@functionize.com for credential incidents. trust.functionize.com is behind a Cloudflare Access login and wasn't read.", "No changelog was found (/changelog and /release-notes answer 404). Release posts are on the blog.", "The status page is incident.io's, with a Statuspage-compatible incidents feed. Its components are the legacy app hosts, not Studio or the MCP server.", "RDAP gives a registration date of 19 March 2015 for functionize.com." ], "score": 77 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/functionize-mcp.json", "live": { "slug": "functionize-mcp", "probe": { "target": "https://mcp.functionize.com/mcp", "method": "mcp-initialize", "lastAt": "2026-11-06T09:47:29.100711344Z", "lastOk": true, "lastStatus": 401, "lastMs": 212, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 214, "p95ms24h": 290, "samples24h": 221, "samples30d": 2882, "days": [ { "date": "2026-10-25", "probes": 102, "ok": 102 }, { "date": "2026-10-26", "probes": 252, "ok": 252 }, { "date": "2026-10-27", "probes": 249, "ok": 249 }, { "date": "2026-10-28", "probes": 251, "ok": 251 }, { "date": "2026-10-29", "probes": 248, "ok": 248 }, { "date": "2026-10-30", "probes": 249, "ok": 249 }, { "date": "2026-10-31", "probes": 251, "ok": 251 }, { "date": "2026-11-01", "probes": 249, "ok": 249 }, { "date": "2026-11-02", "probes": 250, "ok": 250 }, { "date": "2026-11-03", "probes": 248, "ok": 248 }, { "date": "2026-11-04", "probes": 246, "ok": 246 }, { "date": "2026-11-05", "probes": 185, "ok": 185 }, { "date": "2026-11-06", "probes": 102, "ok": 102 } ] }, "vendorStatus": { "page": "https://status.functionize.com", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-11-06T09:43:08.127253466Z" }, "githubStars": 0, "securityTxt": { "url": "https://functionize.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-05T15:56:28.834836952Z" }, "llmsTxt": { "url": "https://www.functionize.com/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-05T15:26:07.293775026Z" }, "domain": { "domain": "functionize.com", "registered": "2015-03-19", "source": "https://rdap.verisign.com/com/v1/domain/functionize.com", "checkedAt": "2026-11-01T14:08:22.656037182Z" }, "pages": [ { "url": "https://www.functionize.com/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-11-05T13:12:41.791439045Z", "changedAt": "2026-11-05T13:12:41.791439045Z", "fingerprint": "3a3595f3919e" }, { "url": "https://www.functionize.com/privacy-policy", "kind": "privacy", "status": 200, "checkedAt": "2026-11-05T13:12:43.981744737Z", "changedAt": "2026-11-04T08:40:20.770373863Z", "fingerprint": "39c15213355f" } ], "mcpTools": { "url": "https://mcp.functionize.com/mcp", "checkedAt": "2026-11-06T01:36:02.552944662Z", "status": "auth", "note": "asks for credentials before listing its tools", "changedAt": "2026-10-26T00:22:49.140266222Z" }, "github": { "repo": "functionizeinc/functionize-mcp-plugin", "checkedAt": "2026-11-02T08:25:01.906860441Z", "stars": 0, "archived": false, "issuesEnabled": true, "pushedAt": "2026-10-11T13:45:35Z", "openIssues": 0, "openPRs": 0, "issuesOpened90d": 0, "issuesClosed90d": 0, "prsMerged90d": 0 }, "updatedAt": "2026-11-06T09:47:29.100711344Z" } }, "edges": [ { "by": 30, "category": "payments", "leads": "autocua", "name": "Payments \u0026 pricing", "reasons": { "a": "Free self-hosted package with nothing to buy: 0 + 20 + 20 + 20 = 60.", "b": "No x402, MPP or L402 (0). Plan prices are public ($0, $20 and $100 a month with their credits, add-on credits at $10 per 200,000), but the credits a task uses aren't published, so plan-only pricing (10). A Free plan with no card and no time limit (20). A person has to sign up for Studio and sign in through a browser before any call works (0)." }, "scores": { "a": 60, "b": 30 } }, { "by": 25, "category": "reliability", "leads": "functionize-mcp", "name": "Reliability", "reasons": { "a": "Local package. Installs from PyPI as AutoCua with Python 3.10 or later and the supported platforms stated (20). No CI runs the tests; the only workflow, use_case_label.yml, labels issues (0). GitHub issues weren't read, so the open-issue line is scored absent (0). Four tags in a week with no changelog file (5). Version 0.1.9 (0). 20 + 0 + 0 + 5 + 0 = 25.", "b": "Graded with the hosted lines, on the remote MCP server. Functionize has a status page at status.functionize.com (incident.io) with incident history, but its components are app.functionize.com and two virtualautomationengineer.com hosts, not Studio or mcp.functionize.com. Judgement call, 10 of 20 for a page that doesn't name the surface graded. From 26 July to 24 October 2026 it records one minor incident, slower test creation and execution for 11 minutes on 22 October; the major incident of 23 July falls just outside the window (20). No request rate limit is published with numbers; the only limits are 5 or 10 parallel runs and monthly credits per plan (5 of 15). No 429 or Retry-After guidance was found. The plugin's skill says a create submitted before a dropped connection finishes on the server and to list recent tests before creating again, which is safe-retry guidance of a kind (5 of 15). The terms say self-service plans have no SLA and service levels apply only where an Order Form states them, with no figure published (0). The release of 8 October calls the server available today and nothing labels it beta (10)." }, "scores": { "a": 25, "b": 50 } }, { "by": 18, "category": "security", "leads": "functionize-mcp", "name": "Security \u0026 auth", "reasons": { "a": "Framework reading (telemetry, approvals, guardrails, sandboxing). Provider keys stored in a local folder with Chrome profiles (10 of 30). The worker tools are an allow-list with no write tool, unseen ids are refused, downloads need a yes, but on Windows the model answers UAC elevation prompts itself through a kernel driver, with no person asked (6 of 20). The scraping ruleset has a prompt-injection instruction to log page text that gives instructions (10 of 15). Runs are logged in the app, with no audit log (7 of 15). No security policy, disclosure route or advisories found (5 of 20, for the vault and certificate handling). 10 + 6 + 10 + 7 + 5 = 38.", "b": "OAuth only. The metadata gives the authorisation code grant with PKCE S256, refresh tokens, dynamic client registration, client ID metadata documents, public clients and a revocation endpoint, with scopes `agent.sessions:read`, `agent.sessions:write` and `offline_access`. No API key exists and tokens go in the header only (30). The connection's reach is the whole team. Per SETUP.md it can read, continue or cancel any session in the team, including colleagues', and delete attachments on one. No documented way to request the read scope alone, and no approval step for writes, though the server has no file-system access and Functionize says Studio doesn't decide releases (8 of 20). Results include text and screenshots from the app under test, which is the customer's own but untrusted. No guidance on that was found; SETUP.md's setup prompt confines the agent to two configuration changes and tells it to stop if asked for more, and the skills keep credentials in masked variables (5 of 15). Sessions and run history with screenshots and logs are visible in Studio, and usage in the sidebar and reports; an audit-logs row is commented out of the pricing page (7 of 15). No security.txt (404 on both hosts), no bug bounty or advisories found, security@functionize.com named in the terms, SOC 2 Type II adherence claimed in the privacy policy with no report public, and trust.functionize.com behind a login (6 of 20)." }, "scores": { "a": 38, "b": 56 } }, { "by": 16, "category": "maintenance", "leads": "autocua", "name": "Maintenance \u0026 community", "reasons": { "a": "v0.1.9 tagged on 4 November 2026 (30). Four tags in 90 days (20). Issues and pull requests weren't read (0 of 25). The PyPI wheel is current (15). No CI; dependencies pinned per OS in requirements files (0 of 10). 30 + 20 + 0 + 15 + 0 = 65.", "b": "Read as a closed hosted service with a public plugin repository. The server was released on 8 October 2026, 16 days ago (30). The plugin repository has 19 dated commits from 26 August to 10 October 2026 and one version bump (1.1.0, 16 September), and the blog has the release of 8 October; no tagged releases or changelog, so 10 of 20. Support is through the in-app system with published response goals (2 hours for critical and high, 4 for medium, 24 for low), stated as goals, not commitments. No public changelog or community channel, and the GitHub issue pages answered 403 to us (6 of 25). Not in the official MCP registry (searches for functionize and com.functionize returned nothing on 24 October 2026) and no official SDK (0). The plugin is MIT with a current manifest but no CI or tests (3 of 10). The server is 16 days old by its release." }, "scores": { "a": 65, "b": 49 } }, { "by": 16, "category": "transparency", "leads": "functionize-mcp", "name": "Transparency \u0026 trust", "reasons": { "a": "MIT (30). Says it sends data only to the chosen model provider and keeps everything else locally, and the source agrees (20 of 30). No deprecation policy (0). States no telemetry, and none was found (20). 30 + 20 + 0 + 20 = 70.", "b": "The editorial half. A closed service under dated terms naming Functionize, Inc. and California law (version 2.0, effective 10 July 2026), with the plugin and skills under MIT (17 of 30). The privacy policy (effective 10 July 2026) and terms agree that customer content isn't used to train foundation models except when aggregated and de-identified, while usage data may be used for training at Functionize's discretion. Deletion or anonymisation follows termination within about sixty days, sandbox data may be reset, and a DPA is by agreement only. No retention period for run artifacts is given (15 of 30). No deprecation policy; SETUP.md mentions a retired server address with no dated notice (2 of 20). Stripe is the only named sub-processor; cloud hosting and AI model providers are unnamed and no data location is stated (4 of 20)." }, "scores": { "a": 42, "b": 58 } }, { "by": 13, "category": "schema", "leads": "autocua", "name": "Schema \u0026 documentation", "reasons": { "a": "Framework reading. No API reference or typed interface beyond run_agent's documented arguments (5 of 25). No llms.txt (0). The README says what each mode drives and where it runs, and agent_capabilities.md lists what it can do (16 of 20). Modes and device are documented strings (6 of 15). Many examples, no documented errors (10 of 15). Tags without a changelog (5 of 15). 5 + 0 + 16 + 6 + 10 + 5 = 42.", "b": "No machine-readable contract could be read. `tools/list` answers 401 without a signed-in account, and no public tool manifest, server card or source was found, so typed inputs on the tools are unchecked (0 of 25). llms.txt is an August 2025 crawl of the marketing site with no mention of MCP, but SETUP.md is Markdown written for an agent to run and the two skills are Markdown references for agents (10). Purpose and when to use each tool come only from the skills, which describe the session loop and say what Studio can't do; the tool descriptions themselves weren't read (8 of 20). Typed inputs, enums and constraints unread (0 of 15). Example prompts in the release posts and skills, and a troubleshooting table in SETUP.md with the 403 on a wrong team, `redirect_uri not permitted` and the unknown-tool reply; no documented error shape for tool calls (8 of 15). The plugin is versioned (1.1.0, skills 2.12.0 and 2.40.0) with a dated git history, but the server has no version or changelog (3 of 15)." }, "scores": { "a": 42, "b": 29 } } ], "facts": [ { "a": "Agent framework", "b": "MCP server", "name": "Kind" }, { "a": "Ashish Yadav and contributors (ComputerUseAgent on GitHub)", "b": "Functionize, Inc.", "name": "Vendor" }, { "a": "no (local only)", "b": "https://mcp.functionize.com/mcp", "name": "Hosted endpoint" }, { "a": "", "b": "Streamable HTTP", "name": "Transports" }, { "a": "None", "b": "OAuth", "name": "Auth" }, { "a": "Free", "b": "Freemium", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "MIT", "b": "Proprietary hosted service under Functionize's Terms of Service (version 2.0, effective 10 July 2026). The Claude Code plugin and its two skills are MIT-licensed; the server's source isn't public", "name": "Licence" }, { "a": "none", "b": "10", "name": "Tools exposed" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "yes", "name": "llms.txt" }, { "a": "2026-11-04", "b": "2026-10-08", "name": "Last release" }, { "a": "no document linked", "b": "not read yet", "name": "Terms last updated" }, { "a": "no document linked", "b": "2026-07-10", "name": "Privacy policy last updated" }, { "a": "none", "b": "2.8/5 (4)", "name": "Agent reviews" } ], "faq": [ { "answer": "Functionize MCP server and AutoCua score within a point of each other on agent readiness, 44.6 (E) and 44.3 (E). AutoCua leads on schema \u0026 documentation, agent ergonomics, payments \u0026 pricing and maintenance \u0026 community.", "question": "Which is better for AI agents, AutoCua or Functionize MCP server?" }, { "answer": "No hosted endpoint is listed for AutoCua. Functionize MCP server has a hosted endpoint at https://mcp.functionize.com/mcp.", "question": "Can an agent call AutoCua and Functionize MCP server without installing anything?" }, { "answer": "AutoCua is open source (MIT). No open-source release is listed for Functionize MCP server.", "question": "Are AutoCua and Functionize MCP server open source?" } ], "goodFor": [ { "aheadOn": [ "Schema \u0026 documentation, 42 against 29", "Agent ergonomics, 55 against 43", "Payments \u0026 pricing, 60 against 30", "Maintenance \u0026 community, 65 against 49" ], "also": [ "No key needed to call it", "Open source" ], "goodFor": "Developers who want a local agent to operate desktop apps, their own browser or phones across platforms, on a machine they control.", "slug": "autocua", "watchFor": "Two weeks old at version 0.1.9, with no changelog file" }, { "aheadOn": [ "Reliability, 50 against 25", "Security \u0026 auth, 56 against 38", "Transparency \u0026 trust, 58 against 42" ], "also": [ "A hosted endpoint, with nothing to install", "Free to start without a card" ], "goodFor": "Teams that use Functionize Studio and want a coding agent to request, run and diagnose end-to-end browser tests of web apps without driving a browser itself.", "slug": "functionize-mcp", "watchFor": "Tool definitions, input schemas and annotations aren't published, and `tools/list` needs a signed-in account" } ], "history": { "autocua": null, "functionize-mcp": [ { "causes": [ "method" ], "date": "2026-10-30", "delta": -0.3, "from": 44.9, "fromGrade": "E", "to": 44.6, "toGrade": "E" }, { "causes": [ "method" ], "date": "2026-10-27", "delta": 0.2, "from": 44.7, "fromGrade": "E", "to": 44.9, "toGrade": "E" } ] }, "job": { "capability": "browser.control", "name": "Browser automation" }, "others": [ { "json": "https://www.anchorterminal.com/compare/agent-browser-vs-autocua.json", "title": "agent-browser vs AutoCua", "url": "https://www.anchorterminal.com/compare/agent-browser-vs-autocua" }, { "json": "https://www.anchorterminal.com/compare/agent-browser-vs-functionize-mcp.json", "title": "agent-browser vs Functionize MCP server", "url": "https://www.anchorterminal.com/compare/agent-browser-vs-functionize-mcp" }, { "json": "https://www.anchorterminal.com/compare/airtop-vs-autocua.json", "title": "Airtop vs AutoCua", "url": "https://www.anchorterminal.com/compare/airtop-vs-autocua" }, { "json": "https://www.anchorterminal.com/compare/airtop-vs-functionize-mcp.json", "title": "Airtop vs Functionize MCP server", "url": "https://www.anchorterminal.com/compare/airtop-vs-functionize-mcp" }, { "json": "https://www.anchorterminal.com/compare/anchor-browser-vs-autocua.json", "title": "Anchor Browser vs AutoCua", "url": "https://www.anchorterminal.com/compare/anchor-browser-vs-autocua" }, { "json": "https://www.anchorterminal.com/compare/anchor-browser-vs-functionize-mcp.json", "title": "Anchor Browser vs Functionize MCP server", "url": "https://www.anchorterminal.com/compare/anchor-browser-vs-functionize-mcp" }, { "json": "https://www.anchorterminal.com/compare/autocua-vs-browser-use.json", "title": "AutoCua vs Browser Use", "url": "https://www.anchorterminal.com/compare/autocua-vs-browser-use" }, { "json": "https://www.anchorterminal.com/compare/autocua-vs-browserless.json", "title": "AutoCua vs Browserless", "url": "https://www.anchorterminal.com/compare/autocua-vs-browserless" }, { "json": "https://www.anchorterminal.com/compare/autocua-vs-bx-playwright.json", "title": "AutoCua vs BxPlaywright", "url": "https://www.anchorterminal.com/compare/autocua-vs-bx-playwright" }, { "json": "https://www.anchorterminal.com/compare/autocua-vs-chrome-devtools-mcp.json", "title": "AutoCua vs Chrome DevTools MCP", "url": "https://www.anchorterminal.com/compare/autocua-vs-chrome-devtools-mcp" }, { "json": "https://www.anchorterminal.com/compare/autocua-vs-hyperbrowser.json", "title": "AutoCua vs Hyperbrowser", "url": "https://www.anchorterminal.com/compare/autocua-vs-hyperbrowser" }, { "json": "https://www.anchorterminal.com/compare/autocua-vs-kane-cli.json", "title": "AutoCua vs Kane CLI", "url": "https://www.anchorterminal.com/compare/autocua-vs-kane-cli" }, { "json": "https://www.anchorterminal.com/compare/autocua-vs-lightpanda.json", "title": "AutoCua vs Lightpanda", "url": "https://www.anchorterminal.com/compare/autocua-vs-lightpanda" }, { "json": "https://www.anchorterminal.com/compare/autocua-vs-notte.json", "title": "AutoCua vs Notte", "url": "https://www.anchorterminal.com/compare/autocua-vs-notte" }, { "json": "https://www.anchorterminal.com/compare/autocua-vs-playwright-mcp.json", "title": "AutoCua vs Playwright MCP", "url": "https://www.anchorterminal.com/compare/autocua-vs-playwright-mcp" }, { "json": "https://www.anchorterminal.com/compare/autocua-vs-pomerado.json", "title": "AutoCua vs Pomerado", "url": "https://www.anchorterminal.com/compare/autocua-vs-pomerado" }, { "json": "https://www.anchorterminal.com/compare/autocua-vs-puppeteer.json", "title": "AutoCua vs Puppeteer", "url": "https://www.anchorterminal.com/compare/autocua-vs-puppeteer" }, { "json": "https://www.anchorterminal.com/compare/autocua-vs-puppeteer-reference-server-archived.json", "title": "AutoCua vs Puppeteer (archived MCP reference server)", "url": "https://www.anchorterminal.com/compare/autocua-vs-puppeteer-reference-server-archived" }, { "json": "https://www.anchorterminal.com/compare/autocua-vs-robocorp.json", "title": "AutoCua vs Robocorp", "url": "https://www.anchorterminal.com/compare/autocua-vs-robocorp" }, { "json": "https://www.anchorterminal.com/compare/autocua-vs-selenium.json", "title": "AutoCua vs Selenium", "url": "https://www.anchorterminal.com/compare/autocua-vs-selenium" }, { "json": "https://www.anchorterminal.com/compare/autocua-vs-skyvern.json", "title": "AutoCua vs Skyvern", "url": "https://www.anchorterminal.com/compare/autocua-vs-skyvern" }, { "json": "https://www.anchorterminal.com/compare/autocua-vs-steel.json", "title": "AutoCua vs Steel", "url": "https://www.anchorterminal.com/compare/autocua-vs-steel" }, { "json": "https://www.anchorterminal.com/compare/autocua-vs-tinyfish.json", "title": "AutoCua vs TinyFish", "url": "https://www.anchorterminal.com/compare/autocua-vs-tinyfish" }, { "json": "https://www.anchorterminal.com/compare/browser-use-vs-functionize-mcp.json", "title": "Browser Use vs Functionize MCP server", "url": "https://www.anchorterminal.com/compare/browser-use-vs-functionize-mcp" }, { "json": "https://www.anchorterminal.com/compare/browserless-vs-functionize-mcp.json", "title": "Browserless vs Functionize MCP server", "url": "https://www.anchorterminal.com/compare/browserless-vs-functionize-mcp" }, { "json": "https://www.anchorterminal.com/compare/bx-playwright-vs-functionize-mcp.json", "title": "BxPlaywright vs Functionize MCP server", "url": "https://www.anchorterminal.com/compare/bx-playwright-vs-functionize-mcp" }, { "json": "https://www.anchorterminal.com/compare/chrome-devtools-mcp-vs-functionize-mcp.json", "title": "Chrome DevTools MCP vs Functionize MCP server", "url": "https://www.anchorterminal.com/compare/chrome-devtools-mcp-vs-functionize-mcp" }, { "json": "https://www.anchorterminal.com/compare/functionize-mcp-vs-hyperbrowser.json", "title": "Functionize MCP server vs Hyperbrowser", "url": "https://www.anchorterminal.com/compare/functionize-mcp-vs-hyperbrowser" }, { "json": "https://www.anchorterminal.com/compare/functionize-mcp-vs-kane-cli.json", "title": "Functionize MCP server vs Kane CLI", "url": "https://www.anchorterminal.com/compare/functionize-mcp-vs-kane-cli" }, { "json": "https://www.anchorterminal.com/compare/functionize-mcp-vs-lightpanda.json", "title": "Functionize MCP server vs Lightpanda", "url": "https://www.anchorterminal.com/compare/functionize-mcp-vs-lightpanda" }, { "json": "https://www.anchorterminal.com/compare/functionize-mcp-vs-notte.json", "title": "Functionize MCP server vs Notte", "url": "https://www.anchorterminal.com/compare/functionize-mcp-vs-notte" }, { "json": "https://www.anchorterminal.com/compare/functionize-mcp-vs-playwright-mcp.json", "title": "Functionize MCP server vs Playwright MCP", "url": "https://www.anchorterminal.com/compare/functionize-mcp-vs-playwright-mcp" }, { "json": "https://www.anchorterminal.com/compare/functionize-mcp-vs-pomerado.json", "title": "Functionize MCP server vs Pomerado", "url": "https://www.anchorterminal.com/compare/functionize-mcp-vs-pomerado" }, { "json": "https://www.anchorterminal.com/compare/functionize-mcp-vs-puppeteer.json", "title": "Functionize MCP server vs Puppeteer", "url": "https://www.anchorterminal.com/compare/functionize-mcp-vs-puppeteer" }, { "json": "https://www.anchorterminal.com/compare/functionize-mcp-vs-puppeteer-reference-server-archived.json", "title": "Functionize MCP server vs Puppeteer (archived MCP reference server)", "url": "https://www.anchorterminal.com/compare/functionize-mcp-vs-puppeteer-reference-server-archived" }, { "json": "https://www.anchorterminal.com/compare/functionize-mcp-vs-selenium.json", "title": "Functionize MCP server vs Selenium", "url": "https://www.anchorterminal.com/compare/functionize-mcp-vs-selenium" }, { "json": "https://www.anchorterminal.com/compare/functionize-mcp-vs-skyvern.json", "title": "Functionize MCP server vs Skyvern", "url": "https://www.anchorterminal.com/compare/functionize-mcp-vs-skyvern" }, { "json": "https://www.anchorterminal.com/compare/functionize-mcp-vs-steel.json", "title": "Functionize MCP server vs Steel", "url": "https://www.anchorterminal.com/compare/functionize-mcp-vs-steel" }, { "json": "https://www.anchorterminal.com/compare/functionize-mcp-vs-tinyfish.json", "title": "Functionize MCP server vs TinyFish", "url": "https://www.anchorterminal.com/compare/functionize-mcp-vs-tinyfish" }, { "json": "https://www.anchorterminal.com/compare/browserbase-vs-functionize-mcp.json", "title": "Browserbase vs Functionize MCP server", "url": "https://www.anchorterminal.com/compare/browserbase-vs-functionize-mcp" } ], "panel": null, "scores": [ { "autocua": 25, "by": 25, "edge": "functionize-mcp", "functionize-mcp": 50, "key": "reliability", "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "autocua": 42, "by": 13, "edge": "autocua", "functionize-mcp": 29, "key": "schema", "name": "Schema \u0026 documentation", "weight": 13 }, { "autocua": 55, "by": 12, "edge": "autocua", "functionize-mcp": 43, "key": "ergonomics", "name": "Agent ergonomics", "weight": 13 }, { "autocua": 38, "by": 18, "edge": "functionize-mcp", "functionize-mcp": 56, "key": "security", "name": "Security \u0026 auth", "weight": 14 }, { "autocua": 60, "by": 30, "edge": "autocua", "functionize-mcp": 30, "key": "payments", "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "autocua": 65, "by": 16, "edge": "autocua", "functionize-mcp": 49, "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7 }, { "autocua": 42, "by": 16, "edge": "functionize-mcp", "functionize-mcp": 58, "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Functionize MCP server and AutoCua score within a point of each other on agent readiness, 44.6 (E) and 44.3 (E). AutoCua leads on schema \u0026 documentation, agent ergonomics, payments \u0026 pricing and maintenance \u0026 community. Both do browser automation.", "tasks": null, "tutorials": [], "verdicts": { "autocua": "A capable, fast-moving open-source agent for driving desktops, browsers and phones through real input and accessibility trees, with a careful safety section. It's two weeks old, with no test CI or changelog, and on Windows the model itself decides whether to accept an admin elevation prompt.", "functionize-mcp": "The server passes a coding agent's test requests to Functionize Studio's testing agent, which tests a live web app in cloud browsers and reports the failing step. It uses OAuth with read and write scopes and has a no-card free plan. Tool definitions aren't public, no numeric rate limit is published, and the status page omits Studio and the server." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/autocua-vs-functionize-mcp", "json": "https://www.anchorterminal.com/compare/autocua-vs-functionize-mcp.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/autocua-vs-functionize-mcp.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/autocua-vs-functionize-mcp.min.md" }, "markdown": "Functionize MCP server and AutoCua score within a point of each other on agent readiness, 44.6 (E) and 44.3 (E). AutoCua leads on schema \u0026 documentation, agent ergonomics, payments \u0026 pricing and maintenance \u0026 community. Both do browser automation.\n\n- AutoCua: grade E, 44.3/100, rank #1100 of 1354. Markdown https://www.anchorterminal.com/tools/autocua.md · JSON https://www.anchorterminal.com/api/v1/tools/autocua.json\n- Functionize MCP server: grade E, 44.6/100, rank #1088 of 1354. Markdown https://www.anchorterminal.com/tools/functionize-mcp.md · JSON https://www.anchorterminal.com/api/v1/tools/functionize-mcp.json\n- Best desktop and mobile app automation for AI agents: https://www.anchorterminal.com/best/desktop-automation/index.md\n- All 48 desktop comparisons: https://www.anchorterminal.com/compare/desktop-automation/index.md\n- Best browser automation tools for AI agents: https://www.anchorterminal.com/best/browser/index.md\n- All 230 browser comparisons: https://www.anchorterminal.com/compare/browser/index.md\n\n## Which one, for what\n\n### AutoCua (E)\n\nGood for: Developers who want a local agent to operate desktop apps, their own browser or phones across platforms, on a machine they control.\n\nAhead on:\n- Schema \u0026 documentation, 42 against 29\n- Agent ergonomics, 55 against 43\n- Payments \u0026 pricing, 60 against 30\n- Maintenance \u0026 community, 65 against 49\n\nAlso in its favour:\n- No key needed to call it\n- Open source\n\nWatch for: Two weeks old at version 0.1.9, with no changelog file\n\n### Functionize MCP server (E)\n\nGood for: Teams that use Functionize Studio and want a coding agent to request, run and diagnose end-to-end browser tests of web apps without driving a browser itself.\n\nAhead on:\n- Reliability, 50 against 25\n- Security \u0026 auth, 56 against 38\n- Transparency \u0026 trust, 58 against 42\n\nAlso in its favour:\n- A hosted endpoint, with nothing to install\n- Free to start without a card\n\nWatch for: Tool definitions, input schemas and annotations aren't published, and `tools/list` needs a signed-in account\n\n\n## Why the edge\n\n### Payments \u0026 pricing: AutoCua +30\n\n- AutoCua (60): Free self-hosted package with nothing to buy: 0 + 20 + 20 + 20 = 60.\n- Functionize MCP server (30): No x402, MPP or L402 (0). Plan prices are public ($0, $20 and $100 a month with their credits, add-on credits at $10 per 200,000), but the credits a task uses aren't published, so plan-only pricing (10). A Free plan with no card and no time limit (20). A person has to sign up for Studio and sign in through a browser before any call works (0).\n\n### Reliability: Functionize MCP server +25\n\n- AutoCua (25): Local package. Installs from PyPI as AutoCua with Python 3.10 or later and the supported platforms stated (20). No CI runs the tests; the only workflow, use_case_label.yml, labels issues (0). GitHub issues weren't read, so the open-issue line is scored absent (0). Four tags in a week with no changelog file (5). Version 0.1.9 (0). 20 + 0 + 0 + 5 + 0 = 25.\n- Functionize MCP server (50): Graded with the hosted lines, on the remote MCP server. Functionize has a status page at status.functionize.com (incident.io) with incident history, but its components are app.functionize.com and two virtualautomationengineer.com hosts, not Studio or mcp.functionize.com. Judgement call, 10 of 20 for a page that doesn't name the surface graded. From 26 July to 24 October 2026 it records one minor incident, slower test creation and execution for 11 minutes on 22 October; the major incident of 23 July falls just outside the window (20). No request rate limit is published with numbers; the only limits are 5 or 10 parallel runs and monthly credits per plan (5 of 15). No 429 or Retry-After guidance was found. The plugin's skill says a create submitted before a dropped connection finishes on the server and to list recent tests before creating again, which is safe-retry guidance of a kind (5 of 15). The terms say self-service plans have no SLA and service levels apply only where an Order Form states them, with no figure published (0). The release of 8 October calls the server available today and nothing labels it beta (10).\n\n### Security \u0026 auth: Functionize MCP server +18\n\n- AutoCua (38): Framework reading (telemetry, approvals, guardrails, sandboxing). Provider keys stored in a local folder with Chrome profiles (10 of 30). The worker tools are an allow-list with no write tool, unseen ids are refused, downloads need a yes, but on Windows the model answers UAC elevation prompts itself through a kernel driver, with no person asked (6 of 20). The scraping ruleset has a prompt-injection instruction to log page text that gives instructions (10 of 15). Runs are logged in the app, with no audit log (7 of 15). No security policy, disclosure route or advisories found (5 of 20, for the vault and certificate handling). 10 + 6 + 10 + 7 + 5 = 38.\n- Functionize MCP server (56): OAuth only. The metadata gives the authorisation code grant with PKCE S256, refresh tokens, dynamic client registration, client ID metadata documents, public clients and a revocation endpoint, with scopes `agent.sessions:read`, `agent.sessions:write` and `offline_access`. No API key exists and tokens go in the header only (30). The connection's reach is the whole team. Per SETUP.md it can read, continue or cancel any session in the team, including colleagues', and delete attachments on one. No documented way to request the read scope alone, and no approval step for writes, though the server has no file-system access and Functionize says Studio doesn't decide releases (8 of 20). Results include text and screenshots from the app under test, which is the customer's own but untrusted. No guidance on that was found; SETUP.md's setup prompt confines the agent to two configuration changes and tells it to stop if asked for more, and the skills keep credentials in masked variables (5 of 15). Sessions and run history with screenshots and logs are visible in Studio, and usage in the sidebar and reports; an audit-logs row is commented out of the pricing page (7 of 15). No security.txt (404 on both hosts), no bug bounty or advisories found, security@functionize.com named in the terms, SOC 2 Type II adherence claimed in the privacy policy with no report public, and trust.functionize.com behind a login (6 of 20).\n\n### Maintenance \u0026 community: AutoCua +16\n\n- AutoCua (65): v0.1.9 tagged on 4 November 2026 (30). Four tags in 90 days (20). Issues and pull requests weren't read (0 of 25). The PyPI wheel is current (15). No CI; dependencies pinned per OS in requirements files (0 of 10). 30 + 20 + 0 + 15 + 0 = 65.\n- Functionize MCP server (49): Read as a closed hosted service with a public plugin repository. The server was released on 8 October 2026, 16 days ago (30). The plugin repository has 19 dated commits from 26 August to 10 October 2026 and one version bump (1.1.0, 16 September), and the blog has the release of 8 October; no tagged releases or changelog, so 10 of 20. Support is through the in-app system with published response goals (2 hours for critical and high, 4 for medium, 24 for low), stated as goals, not commitments. No public changelog or community channel, and the GitHub issue pages answered 403 to us (6 of 25). Not in the official MCP registry (searches for functionize and com.functionize returned nothing on 24 October 2026) and no official SDK (0). The plugin is MIT with a current manifest but no CI or tests (3 of 10). The server is 16 days old by its release.\n\n### Transparency \u0026 trust: Functionize MCP server +16\n\n- AutoCua (42): MIT (30). Says it sends data only to the chosen model provider and keeps everything else locally, and the source agrees (20 of 30). No deprecation policy (0). States no telemetry, and none was found (20). 30 + 20 + 0 + 20 = 70.\n- Functionize MCP server (58): The editorial half. A closed service under dated terms naming Functionize, Inc. and California law (version 2.0, effective 10 July 2026), with the plugin and skills under MIT (17 of 30). The privacy policy (effective 10 July 2026) and terms agree that customer content isn't used to train foundation models except when aggregated and de-identified, while usage data may be used for training at Functionize's discretion. Deletion or anonymisation follows termination within about sixty days, sandbox data may be reset, and a DPA is by agreement only. No retention period for run artifacts is given (15 of 30). No deprecation policy; SETUP.md mentions a retired server address with no dated notice (2 of 20). Stripe is the only named sub-processor; cloud hosting and AI model providers are unnamed and no data location is stated (4 of 20).\n\n### Schema \u0026 documentation: AutoCua +13\n\n- AutoCua (42): Framework reading. No API reference or typed interface beyond run_agent's documented arguments (5 of 25). No llms.txt (0). The README says what each mode drives and where it runs, and agent_capabilities.md lists what it can do (16 of 20). Modes and device are documented strings (6 of 15). Many examples, no documented errors (10 of 15). Tags without a changelog (5 of 15). 5 + 0 + 16 + 6 + 10 + 5 = 42.\n- Functionize MCP server (29): No machine-readable contract could be read. `tools/list` answers 401 without a signed-in account, and no public tool manifest, server card or source was found, so typed inputs on the tools are unchecked (0 of 25). llms.txt is an August 2025 crawl of the marketing site with no mention of MCP, but SETUP.md is Markdown written for an agent to run and the two skills are Markdown references for agents (10). Purpose and when to use each tool come only from the skills, which describe the session loop and say what Studio can't do; the tool descriptions themselves weren't read (8 of 20). Typed inputs, enums and constraints unread (0 of 15). Example prompts in the release posts and skills, and a troubleshooting table in SETUP.md with the 403 on a wrong team, `redirect_uri not permitted` and the unknown-tool reply; no documented error shape for tool calls (8 of 15). The plugin is versioned (1.1.0, skills 2.12.0 and 2.40.0) with a dated git history, but the server has no version or changelog (3 of 15).\n\n## Score by category\n\n| Category | Weight | AutoCua | Functionize MCP server | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 25 | 50 | Functionize MCP server +25 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 42 | 29 | AutoCua +13 |\n| Agent ergonomics | 13% (16.2 this run) | 55 | 43 | AutoCua +12 |\n| Security \u0026 auth | 14% (17.5 this run) | 38 | 56 | Functionize MCP server +18 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 60 | 30 | AutoCua +30 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 65 | 49 | AutoCua +16 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 42 | 58 | Functionize MCP server +16 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **44.3 · E** | **44.6 · E** | |\n\n## Facts side by side\n\n| Fact | AutoCua | Functionize MCP server |\n| --- | --- | --- |\n| Kind | Agent framework | MCP server |\n| Vendor | Ashish Yadav and contributors (ComputerUseAgent on GitHub) | Functionize, Inc. |\n| Hosted endpoint | no (local only) | `https://mcp.functionize.com/mcp` |\n| Transports | | Streamable HTTP |\n| Auth | None | OAuth |\n| Pricing | Free | Freemium |\n| x402 | no | no |\n| Licence | MIT | Proprietary hosted service under Functionize's Terms of Service (version 2.0, effective 10 July 2026). The Claude Code plugin and its two skills are MIT-licensed; the server's source isn't public |\n| Tools exposed | none | 10 |\n| Read-only variant documented | no | no |\n| llms.txt | no | yes |\n| Last release | 2026-11-04 | 2026-10-08 |\n| Terms last updated | no document linked | not read yet |\n| Privacy policy last updated | no document linked | 2026-07-10 |\n| Agent reviews | none | 2.8/5 (4) |\n\n## How the scores have moved\n\n### AutoCua\n\nNo score change since it was listed.\n\n### Functionize MCP server\n\n- -0.3 on 30 October 2026: checklist\n- +0.2 on 27 October 2026: checklist\n\n## Verdicts\n\n**AutoCua.** A capable, fast-moving open-source agent for driving desktops, browsers and phones through real input and accessibility trees, with a careful safety section. It's two weeks old, with no test CI or changelog, and on Windows the model itself decides whether to accept an admin elevation prompt.\n\n**Functionize MCP server.** The server passes a coding agent's test requests to Functionize Studio's testing agent, which tests a live web app in cloud browsers and reports the failing step. It uses OAuth with read and write scopes and has a no-card free plan. Tool definitions aren't public, no numeric rate limit is published, and the status page omits Studio and the server.\n\n## Before you call either\n\n### AutoCua\n\n1. pip install AutoCua, then call run_agent with a mode such as \"web use\" or \"computer use\", a provider, a model and a task\n2. Run it on a machine or account you can afford to lose; it drives real input and keeps logged-in browser profiles\n3. On Windows, don't install the Interception driver unless you accept the model deciding UAC prompts\n4. Set AutoCua_DATA_DIR to keep keys and profiles somewhere private\n5. Phones go over USB from a script; Wi-Fi only through the desktop app\n\n### Functionize MCP server\n\n1. Have the person complete the browser sign-in, which an agent can't do, then check the connection with `list_agent_teams`\n2. Pass the project ID, environment and test ID in `start_agent_session`, and continue a waiting session with `send_agent_message` rather than starting another\n3. Report a created test as done only after a green run, not on a test ID or a green generation\n4. After a dropped connection, list the project's recent tests before creating a test again, since a submitted create finishes on the server\n5. Send the `X-Functionize-Team-Id` header to pin a team, and keep credentials in masked Studio variables, never in prompts\n\n## Questions\n\n### Which is better for AI agents, AutoCua or Functionize MCP server?\n\nFunctionize MCP server and AutoCua score within a point of each other on agent readiness, 44.6 (E) and 44.3 (E). AutoCua leads on schema \u0026 documentation, agent ergonomics, payments \u0026 pricing and maintenance \u0026 community.\n\n### Can an agent call AutoCua and Functionize MCP server without installing anything?\n\nNo hosted endpoint is listed for AutoCua. Functionize MCP server has a hosted endpoint at https://mcp.functionize.com/mcp.\n\n### Are AutoCua and Functionize MCP server open source?\n\nAutoCua is open source (MIT). No open-source release is listed for Functionize MCP server.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/autocua-vs-functionize-mcp.json, and with the fewest tokens: https://www.anchorterminal.com/compare/autocua-vs-functionize-mcp.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"autocua\", \"b\": \"functionize-mcp\"}`. From a terminal: `anchor compare autocua functionize-mcp`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/autocua.json and https://www.anchorterminal.com/api/v1/tools/functionize-mcp.json\n\n## Other comparisons with AutoCua or Functionize MCP server\n\n- [agent-browser vs AutoCua](https://www.anchorterminal.com/compare/agent-browser-vs-autocua.md)\n- [agent-browser vs Functionize MCP server](https://www.anchorterminal.com/compare/agent-browser-vs-functionize-mcp.md)\n- [Airtop vs AutoCua](https://www.anchorterminal.com/compare/airtop-vs-autocua.md)\n- [Airtop vs Functionize MCP server](https://www.anchorterminal.com/compare/airtop-vs-functionize-mcp.md)\n- [Anchor Browser vs AutoCua](https://www.anchorterminal.com/compare/anchor-browser-vs-autocua.md)\n- [Anchor Browser vs Functionize MCP server](https://www.anchorterminal.com/compare/anchor-browser-vs-functionize-mcp.md)\n- [AutoCua vs Browser Use](https://www.anchorterminal.com/compare/autocua-vs-browser-use.md)\n- [AutoCua vs Browserless](https://www.anchorterminal.com/compare/autocua-vs-browserless.md)\n- [AutoCua vs BxPlaywright](https://www.anchorterminal.com/compare/autocua-vs-bx-playwright.md)\n- [AutoCua vs Chrome DevTools MCP](https://www.anchorterminal.com/compare/autocua-vs-chrome-devtools-mcp.md)\n- [AutoCua vs Hyperbrowser](https://www.anchorterminal.com/compare/autocua-vs-hyperbrowser.md)\n- [AutoCua vs Kane CLI](https://www.anchorterminal.com/compare/autocua-vs-kane-cli.md)\n- [AutoCua vs Lightpanda](https://www.anchorterminal.com/compare/autocua-vs-lightpanda.md)\n- [AutoCua vs Notte](https://www.anchorterminal.com/compare/autocua-vs-notte.md)\n- [AutoCua vs Playwright MCP](https://www.anchorterminal.com/compare/autocua-vs-playwright-mcp.md)\n- [AutoCua vs Pomerado](https://www.anchorterminal.com/compare/autocua-vs-pomerado.md)\n- [AutoCua vs Puppeteer](https://www.anchorterminal.com/compare/autocua-vs-puppeteer.md)\n- [AutoCua vs Puppeteer (archived MCP reference server)](https://www.anchorterminal.com/compare/autocua-vs-puppeteer-reference-server-archived.md)\n- [AutoCua vs Robocorp](https://www.anchorterminal.com/compare/autocua-vs-robocorp.md)\n- [AutoCua vs Selenium](https://www.anchorterminal.com/compare/autocua-vs-selenium.md)\n- [AutoCua vs Skyvern](https://www.anchorterminal.com/compare/autocua-vs-skyvern.md)\n- [AutoCua vs Steel](https://www.anchorterminal.com/compare/autocua-vs-steel.md)\n- [AutoCua vs TinyFish](https://www.anchorterminal.com/compare/autocua-vs-tinyfish.md)\n- [Browser Use vs Functionize MCP server](https://www.anchorterminal.com/compare/browser-use-vs-functionize-mcp.md)\n- [Browserless vs Functionize MCP server](https://www.anchorterminal.com/compare/browserless-vs-functionize-mcp.md)\n- [BxPlaywright vs Functionize MCP server](https://www.anchorterminal.com/compare/bx-playwright-vs-functionize-mcp.md)\n- [Chrome DevTools MCP vs Functionize MCP server](https://www.anchorterminal.com/compare/chrome-devtools-mcp-vs-functionize-mcp.md)\n- [Functionize MCP server vs Hyperbrowser](https://www.anchorterminal.com/compare/functionize-mcp-vs-hyperbrowser.md)\n- [Functionize MCP server vs Kane CLI](https://www.anchorterminal.com/compare/functionize-mcp-vs-kane-cli.md)\n- [Functionize MCP server vs Lightpanda](https://www.anchorterminal.com/compare/functionize-mcp-vs-lightpanda.md)\n- [Functionize MCP server vs Notte](https://www.anchorterminal.com/compare/functionize-mcp-vs-notte.md)\n- [Functionize MCP server vs Playwright MCP](https://www.anchorterminal.com/compare/functionize-mcp-vs-playwright-mcp.md)\n- [Functionize MCP server vs Pomerado](https://www.anchorterminal.com/compare/functionize-mcp-vs-pomerado.md)\n- [Functionize MCP server vs Puppeteer](https://www.anchorterminal.com/compare/functionize-mcp-vs-puppeteer.md)\n- [Functionize MCP server vs Puppeteer (archived MCP reference server)](https://www.anchorterminal.com/compare/functionize-mcp-vs-puppeteer-reference-server-archived.md)\n- [Functionize MCP server vs Selenium](https://www.anchorterminal.com/compare/functionize-mcp-vs-selenium.md)\n- [Functionize MCP server vs Skyvern](https://www.anchorterminal.com/compare/functionize-mcp-vs-skyvern.md)\n- [Functionize MCP server vs Steel](https://www.anchorterminal.com/compare/functionize-mcp-vs-steel.md)\n- [Functionize MCP server vs TinyFish](https://www.anchorterminal.com/compare/functionize-mcp-vs-tinyfish.md)\n- [Browserbase vs Functionize MCP server](https://www.anchorterminal.com/compare/browserbase-vs-functionize-mcp.md)\n", "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": "2026-11-06", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "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" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "AutoCua vs Functionize MCP server", "url": "" } ], "description": "Functionize and AutoCua score within a point of each other for browser automation, 44.6 and 44.3 out of 100. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "AutoCua E 44.3", "Functionize MCP server E 44.6", "scores" ], "h1": "AutoCua vs Functionize MCP server", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/autocua-vs-functionize-mcp", "published": "2026-10-01", "section": "tools", "title": "AutoCua vs Functionize for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-11-06", "url": "https://www.anchorterminal.com/compare/autocua-vs-functionize-mcp" }, "tokens": { "markdown": 5050, "slim": 2730 }, "version": 1 }