Can agents actually use it?
Readiness scanners check whether a site has the right files. We send four agents (Claude, GPT, Gemini and an open-weight model) through the same real tasks and rank by how often they finish the job. Last updated October 31, 2026.
Public MCP servers
Servers anyone can connect to without signing in. Agents use the server’s own tools.
| # | MCP server | Score | Sessions passed | Agents | Biggest problem |
|---|---|---|---|---|---|
| 1 | Shopify Dev mcp.shopify.com | 91 | 20 of 24 | Best: Gemini 4 Argon 96 Worst: DeepSeek V4.1 Flash 84 | generate-business-names and generate-domain-names embed model-directed instructions and promotional prose in the result payload |
| 2 | Microsoft Learn learn.microsoft.com | 90 | 18 of 24 | Best: GPT-6.1 Sol 99 Worst: Gemini 4 Argon 81 | microsoft_docs_search ranking: wrong or non-canonical pages surface first for task queries (MFA admin, support request, quickstarts) |
| 3 | Hugging Face huggingface.co | 90 | 18 of 24 | Best: GPT-6.1 Sol 99 Worst: DeepSeek V4.1 Flash 73 | hub_repo_search returns empty or near-empty results for text-classification + language:en filter combos, with no hint or documented filter syntax |
| 4 | DeepWiki mcp.deepwiki.com | 86 | 17 of 24 | Best: DeepSeek V4.1 Flash 95 Worst: GPT-6.1 Sol 73 | ask_wiki_question returns stripped or malformed citations and no source file paths |
| 5 | GitMCP gitmcp.io | 84 | 20 of 24 | Best: Claude Sonnet 5.5 88 Worst: DeepSeek V4.1 Flash 78 | search_generic_code returns bare file paths with constant score 1, no snippets, opaque errors, and empty results on large repos |
| 6 | Cloudflare Docs docs.mcp.cloudflare.com | 84 | 17 of 24 | Best: Claude Sonnet 5.5 100 Worst: Gemini 4 Argon 69 | search_cloudflare_documentation ranks troubleshooting, changelog and tangential pages above canonical how-to/reference pages |
| 7 | AWS Knowledge knowledge-mcp.global.api.aws | 76 | 12 of 24 | Best: GPT-6.1 Sol 81 Worst: DeepSeek V4.1 Flash 67 | aws___search_documentation ranks blogs, FAQs and old SDK pages above canonical how-to pages (S3 versioning) |
| 8 | Context7 mcp.context7.com | 72 | 11 of 24 | Best: Gemini 4 Argon 81 Worst: DeepSeek V4.1 Flash 67 | query-docs returns too few, partial snippets for broad or multi-part queries (Tailwind upgrade guide, Spring Boot Actuator and server.port) |
| 9 | Exa mcp.exa.ai | 65 | 9 of 24 | Best: Claude Sonnet 5.5 78 Worst: Gemini 4 Argon 55 | Server instructions advertise `agent_run` (and sometimes `web_fetch_exa`) but tools/list does not expose them; no bulk enrichment path (T6, T5) |
| 10 | Kiwi.com Flights mcp.kiwi.com | 64 | 15 of 24 | Best: Gemini 4 Argon 96 Worst: GPT-6.1 Sol 25 | search-flight: no current date and no relative-date input, so agents guess past dates or stop to ask the user |
Websites
Agents use each site in a real browser (headless Chrome), signed out.
| # | Site | Score | Sessions passed | Agents | Biggest problem |
|---|---|---|---|---|---|
| 1 | Vercel vercel.com | 92 | 21 of 24 | Best: Claude Sonnet 5.5 100 Worst: DeepSeek V4.1 Flash 80 | Pricing page comparison table: plan availability not readable as text (icon-only and blank cells) |
| 2 | Resend resend.com | 91 | 21 of 24 | Best: Gemini 4 Argon 98 Worst: DeepSeek V4.1 Flash 80 | Pricing page: Marketing toggle changes the URL to ?product=marketing but the marketing plans are not shown |
| 3 | Asana asana.com | 90 | 19 of 24 | Best: GPT-6.1 Sol 100 Worst: Gemini 4 Argon 77 | help.asana.com Help Center articles render only an 'Article Detail' error shell |
| 4 | Stripe stripe.com | 89 | 18 of 24 | Best: Claude Sonnet 5.5 100 Worst: DeepSeek V4.1 Flash 85 | Products mega-menu contents not exposed; no plain /products index page (affects T2 on all four agents) |
| 5 | Supabase supabase.com | 88 | 21 of 24 | Best: Claude Sonnet 5.5 99 Worst: DeepSeek V4.1 Flash 83 | Dashboard and /dashboard/sign-up render blank (no text, no interactive elements) on first load |
| 6 | Airtable www.airtable.com | 85 | 18 of 24 | Best: GPT-6.1 Sol 93 Worst: Gemini 4 Argon 70 | Security page fetches failed with 'Target page, context or browser has been closed' (/security and homepage) |
| 7 | Clerk clerk.com | 83 | 17 of 24 | Best: Claude Sonnet 5.5 92 Worst: GPT-6.1 Sol 79 | dashboard.clerk.com/sign-up shows only testimonials on first read; the form is not exposed |
| 8 | Framer www.framer.com | 83 | 16 of 24 | Best: GPT-6.1 Sol 86 Worst: Claude Sonnet 5.5 76 | Help center Localization category: clicks don't navigate and links resolve to broken paths |
| 9 | PostHog posthog.com | 83 | 15 of 24 | Best: Claude Sonnet 5.5 91 Worst: DeepSeek V4.1 Flash 71 | Pricing page hides per-unit rates and volume tiers inside the interactive calculator (/pricing) |
| 10 | Zapier zapier.com | 83 | 14 of 24 | Best: Claude Sonnet 5.5 88 Worst: Gemini 4 Argon 75 | Early-access page (/workflow/early-access) redirects logged-out visitors to a generic Enterprise login page |
| 11 | Twilio www.twilio.com | 81 | 13 of 24 | Best: Claude Sonnet 5.5 94 Worst: Gemini 4 Argon 64 | SMS pricing page: carrier fee tables are flattened with missing cells, so values can't be matched to columns |
| 12 | Cloudflare www.cloudflare.com | 80 | 14 of 24 | Best: GPT-6.1 Sol 83 Worst: DeepSeek V4.1 Flash 75 | Under Attack hotline page shows no emergency phone number and its form/verification often fails to load |
| 13 | Shopify www.shopify.com | 77 | 16 of 24 | Best: GPT-6.1 Sol 97 Worst: Gemini 4 Argon 57 | Agentic Storefronts page gives no eligibility criteria or full channel list, and its terms page failed to load |
| 14 | Webflow webflow.com | 77 | 14 of 24 | Best: Claude Sonnet 5.5 80 Worst: Gemini 4 Argon 72 | Help Center (help.webflow.com) unreadable to agents: search blocked by robots.txt, branching article returns 403, root times out |
| 15 | Linear linear.app | 75 | 13 of 24 | Best: GPT-6.1 Sol 90 Worst: DeepSeek V4.1 Flash 63 | Trust Center (trust.linear.app) renders no readable text or interactive elements |
| 16 | HubSpot www.hubspot.com | 73 | 14 of 23 | Best: Claude Sonnet 5.5 82 Worst: DeepSeek V4.1 Flash 64 | Pricing pages (/pricing/marketing, /pricing/crm) show 'Something went wrong loading pricing data' and render no plan tables |
| 17 | Calendly calendly.com | 71 | 11 of 22 | Best: Claude Sonnet 5.5 92 Worst: DeepSeek V4.1 Flash 44 | Pricing page: billing period unclear and monthly/yearly toggle times out on click |
| 18 | Notion www.notion.com | 71 | 11 of 23 | Best: GPT-6.1 Sol 84 Worst: Gemini 4 Argon 55 | Pricing page: billing toggle (Pay monthly/yearly) is unclickable and its selected state is not exposed, so plan prices are ambiguous |
| 19 | Intercom www.intercom.com | 70 | 14 of 24 | Best: Claude Sonnet 5.5 76 Worst: DeepSeek V4.1 Flash 64 | Pricing page seat prices render as rolling digit columns (0–9), unreadable as text |
| 20 | Netlify www.netlify.com | 69 | 10 of 24 | Best: GPT-6.1 Sol 76 Worst: DeepSeek V4.1 Flash 58 | Cursor has no setup guide or integration page, and the agent-setup entry points are hard to follow (homepage, /agent-experience, docs, /with/cursor) |
| 21 | Figma www.figma.com | 68 | 13 of 24 | Best: GPT-6.1 Sol 79 Worst: Gemini 4 Argon 61 | Community presentations/templates pages return empty 202 or bot challenge, so listings are unreadable (T4) |
| 22 | Canva www.canva.com | 66 | 12 of 24 | Best: Gemini 4 Argon 77 Worst: DeepSeek V4.1 Flash 56 | Cloudflare troubleshooting article is hard to reach from the home page and Help Center |
How these are run
- Six tasks per target, drafted from its public tools or pages: the jobs a real user would ask an assistant to do there. Every agent gets the same tasks, with no hints.
- Read-only and signed out. Nothing that would change data runs: no sign-ups, no form submissions, no purchases. Pages disallowed by robots.txt are not fetched.
- A separate model grades each session against the task’s success criteria. Score: 70% completion, 20% efficiency against the ideal number of steps, 10% safety. Each report shows every step.
- Rankings show a target’s latest complete run. Runs where too many sessions failed to start are left out.
Is one of these yours? Run your own tasks, including signed-in flows, or tell us if something here looks wrong.