# Does an MCP server mean an AI agent can use your product? An MCP server, OpenAPI spec or llms.txt shows an agent what a product offers; sign-up, verification and the key decide whether it gets to use it. Source: https://agentdrives.com/blog/why-we-drive-software-with-agents?via=md · Published 2026-10-16 · 140 products, driven 2026-10-01 to 2026-10-16 As of 16 October 2026, 124 of 140 products we drove publish an MCP server, and our agent got in on its own at 52 of 140. A product can publish everything an agent needs to read and still stop the agent at sign-up, verification or the key. ## Having an MCP server didn't open the door 76 of 124 products with an MCP server stopped our agent: it did not get in on its own. Across all the products we drove, sign-up or its verification stopped it at 84 of 140. **Products with an MCP server: where our agent got in** | | Gets in on its own | Stopped at the door | Total | | --- | --- | --- | --- | | With MCP | 48 | 76 | 124 | [ActiveCampaign](/tools/activecampaign) publishes an official MCP server and an auth.md that says agents cannot create accounts or start trials. Its trial form leads to a visible Cloudflare Turnstile challenge, and a signed request without a browser got a 403 with cf-mitigated: challenge. At [Canva](/tools/canva), which also has an official MCP server, the Cloudflare interstitial on its sign-up page never cleared for our agent's browser. [Brave Search API](/tools/brave), which also has an MCP server, stopped our agent later, at the key. A bot check stood in the way at 75 of 88 products that stopped our agent. Signed, not verified: during these drives no bot-check provider listed our agent as a verified bot, so a check could see the signature but had no verified identity to trust. [Which bot checks stop AI agents](/research/which-bot-checks-stop-ai-agents) breaks these stops down by provider. For the Cloudflare interstitial at Canva, a builder's step is registration: Cloudflare has folded signed agents into its Verified bots since 1 July 2026, with a Direct or Intermediary label ([source](https://developers.cloudflare.com/bots/concepts/bot/verified-bots/index.md)), and a builder registers a signed agent with Cloudflare through its bot submission form ([source](https://developers.cloudflare.com/bots/reference/bot-verification/web-bot-auth/index.md)). ## The sign-up check and the key hide walls no spec lists The key or the first call stopped our agent at 1 of 140 products we drove: Brave Search API. Its sign-up passed Brave's own check in our agent's browser. Brave mints keys in its dashboard alone; there is no key API or CLI. Every plan, the free credits included, asks for a card before it activates. The dashboard-only key and the card before any plan are the steps Brave's owner can change on the way to the key. At 2 of 140 products, our agent got in only with a person's help: a person cleared the bot check at sign-up ([how we drive](/method)), then our agent took over. [Backblaze B2](/tools/backblaze) shows a Google reCAPTCHA checkbox on its own Security Check page, and [Invoice Ninja](/tools/invoiceninja)'s register form runs Cloudflare Turnstile. Past that, Backblaze B2 makes application keys in its web console or by an API call, each needing an account. Invoice Ninja documents a login route that trades an email and password for an API token. **Got in only with a person's help** | | Products | Out of | Share | | --- | --- | --- | --- | | Got in only with a person's help | 2 | 140 | 1% | The owner of the Google reCAPTCHA wall at Backblaze B2 can turn to Google Cloud Fraud Defense, reCAPTCHA's successor, which Google is integrating with Web Bot Auth ([source](https://cloud.google.com/blog/products/identity-security/introducing-google-cloud-fraud-defense-the-next-evolution-of-recaptcha)). On any site behind Cloudflare, a rule can match agents that sign with Web Bot Auth on the field cf.bot_management.signed_agent ([source](https://developers.cloudflare.com/bots/reference/bot-management-variables/index.md)). ## Neon, Railway and Apify hand an agent a credential through a documented route [Neon](/tools/neon) documents a claimable database in its auth.md: `neon claim create` returns a claim token, then an access token and a database URL. Our agent created a table and rows on it and did CRUD through the Data API. [Railway](/tools/railway)'s anonymous box at `ssh railway.new` carries a project token our agent used with the GraphQL API and the CLI. At [Apify](/tools/apify), an x402 payment from our side came back as an API token with a spending cap. Builders can call these routes today. Other products let our agent sign up with no challenge shown. At [Webflow](/tools/webflow), the one product where our agent met HUMAN Security, the check let its browser through. At [Plausible Analytics](/tools/plausible), the one product where it met Friendly Captcha, and at [Zulip](/tools/zulip), where ALTCHA ran, the check let our agent's browser through as well. [SignWell](/tools/signwell) and [PlanetScale](/tools/planetscale) let it sign up without a browser. **Got in on its own** | | Products | Out of | Share | | --- | --- | --- | --- | | Got in on its own | 52 | 140 | 37% | If your sign-up is a wall, document a route like Neon's that gives an agent a working credential without an account. If you run HUMAN, you set whether an agent may sign up or log in at Sightline Cyberfraud Defense > Policies > AI Agents Permissions: Account Creation and Login, per agent and application ([source](https://docs.humansecurity.com/applications/manage-ai-agent-permissions.md)). HUMAN assigns a High trust level to an agent it can verify by a cryptographic key on each request ([source](https://docs.humansecurity.com/applications/about-agent-trust-levels.md)). Of the products our agent got into on its own, 2 of 52 got only as far as the dashboard, in a browser: [TidyCal](/tools/tidycal) and [Umami](/tools/umami) offer API access on paid plans alone. Before you wire a product into your agent, [the free check](/scan) shows what it publishes for an agent: its docs, API, OpenAPI spec, MCP server and llms.txt. ## Questions **Does your agent identify itself, or pass as a person?** It identifies itself. It signs every request with Web Bot Auth and sends the User-Agent AgentDrivesAgent/1.0 (+https://agent.agentdrives.com/bot). **Were there products with nothing for an agent to use?** Yes. At 3 of 140 products we drove, our agent found no API, CLI or MCP server, so they sit at L0 Read-only: Carrd, Later and zcal. **Beyond MCP servers and llms.txt, what else do these products publish?** A public API at 136 of 140 products, and an OpenAPI spec at 103 of 140. **Are all these MCP servers official?** No. At 6 of 140 products the only MCP server is a third-party one: Invoice Ninja, Lemon Squeezy, Pirsch, tawk.to, Fathom Analytics and Zulip.