Baserow vs Supabase for AI agents
As of 16 Oct 2026, both reach L1 · Needs a person. Our agent got further with Supabase: with Supabase it got in and met its first wall at pay (blocked), with Baserow it was stopped at sign up (needs a human).
- Find: Docs for agents: llms.txt, an OpenAPI and an MCP server.
- Access: Can't sign up.
- Use: Work not reached.
- Pay: Payment not reached.
- Leave: Leaving not reached.
Stopped at sign up: needs a human. Next: let an agent sign up on its own
Needs a person to get in: L1 · Needs a person. Our agent read the user docs, the ReDoc API reference and llms.txt on its own, then stopped at signup: the documented account endpoint answers an error demanding a Cloudflare Turnstile token, and the web form shows the same visible challenge. With no account, the key page, the first call and the first piece of work in the API or the official MCP server were never reached. Paying stays card-only through the signed-in web UI once a person sets up the account; the UI also handles cancelling, though the docs name an API route for deleting the account.
Driven 6 Oct 2026 · The drive and its evidence- Find: Docs for agents: llms.txt, an OpenAPI and an MCP server; a docs page for each core task.
- Access: Signs up sometimes.
- Use: 100% of the work.
- Pay: Needs a person to buy: A CAPTCHA at checkout.
- Leave: Nothing to cancel: Deletes its data, but the login stays.
Got in; first wall at pay (blocked). Next: let an agent get in on its own in every drive
Supabase is a backend platform for databases, user accounts, file storage and serverless functions. Once the agent signed in with GitHub, it could do almost everything on its own through code: create a database, add users, store files, run functions, and more. It stopped at the very first step: creating an account by email showed a puzzle test it couldn't solve, so it had to use a GitHub sign-in instead, and upgrading to a paid plan hit the same kind of puzzle.
Gets furtherDriven 16 Oct 2026 · The drive and its evidenceThe two summaries: written by our agents from each product's drive. How we write.
Where each one stops.
BaserowStopped at sign up: needs a human
SupabaseGot in; first wall at pay (blocked)
| Checkpoint | Baserow | Supabase |
|---|---|---|
| Docs | Headless | Headless |
| Sign up | Needs a human | In a browser |
| Verify | Not reached | Not needed |
| Key | Not reached | In a browser |
| First call | Not reached | Headless |
| First action | Not reached | Headless |
| Pay | Not reached | Blocked |
| Cancel | Not reached | Not needed |
| Delete | Not reached | Blocked |
Headless or in a browser.
How our agent passed each checkpoint, and what each product offers an agent.
Checkpoints by route, API, MCP, CLI and SDK
| Baserow | Supabase | |
|---|---|---|
| Headless (checkpoints) | 1 | 3 |
| In a browser (checkpoints) | 0 | 2 |
| Needs a human (checkpoints) | 1 | 0 |
| Blocked (checkpoints) | 0 | 2 |
| Not tested (checkpoints) | 7 | 0 |
| Work done | Not measured | 100% of the core |
| API | Yes | Yes |
| OpenAPI | Yes | Yes |
| MCP server | Yes (official) | Yes (official) |
| CLI | No | Yes |
| SDK | No | – |
| llms.txt | Yes | Yes |
Bot checks, and where a person was needed.
| Baserow | Supabase | |
|---|---|---|
| Bot check | Cloudflare Turnstile stopped it at sign up, with a visible challenge | A challenge on the form stopped one way in (Email and password) |
| Wall type | A check of our network and browser | A challenge on the form |
| First wall | Cloudflare Turnstile on the sign-up form | Got in; first wall at pay (blocked) |
| A person helped | No | No |
A check of our network and browser: It judged where our agent connects from and its browser, not a person. An agent that works on its own from a data center doesn't get through unless the owner lets signed agents in. How agents in a person's own browser fare isn't measured yet. A challenge on the form: It asks every visitor to prove they are human. It stops every agent on any network, and a signature doesn't help: a person does this step, or the owner opens it for agents. Where we drive from.
Level and part scores.
| Baserow | Supabase | |
|---|---|---|
| Level | L1 · Needs a person | L1 · Needs a person |
| Holds up | Not measured | 82 of 100, fair |
| Agent-ready setup | 90 of 100, good | 100 of 100, good |
| Standards | OpenAPI 3.0.3 (2 versions behind) | MCP spec of 28 Jul 2026 (current) · MCP discovery (current) · MCP client registration (behind) · OpenAPI 3.0.0 (2 versions behind) |
| Security | No review in this drive | Reported privately to the owner |
Docs match is measured in an Audit. What the scores mean.
Pay, cancel and delete.
| Baserow | Supabase | |
|---|---|---|
| Pay | Payment not reached | Needs a person to buy |
| Free plan or trial | Free plan | Free plan |
| Cancel | Not reached | Not needed |
| Delete the account | Not reached | Blocked |
How each one takes payment
- Baserow: Payment not reached.
- Supabase: A person has to buy: a CAPTCHA at checkout.
Baserow vs Supabase: the short answers.
Which can an AI agent use, Baserow or Supabase?
Both reach L1 · Needs a person. Our agent got further with Supabase: with Supabase it got in and met its first wall at pay (blocked), with Baserow it was stopped at sign up (needs a human). Driven 6 Oct 2026 (Baserow) and 16 Oct 2026 (Supabase).
Can an AI agent sign up for Baserow and Supabase on its own?
Baserow: no, needs a human. Supabase: yes, in a browser, but a later step stopped it.
Do Baserow and Supabase have an MCP server?
Baserow: yes (official). Supabase: yes (official).
Can an AI agent delete its Baserow or Supabase account?
Baserow: not reached. Supabase: blocked.
The drives and the category.
Put your own shortlist side by side.
A Stack check drives the tools you're choosing between and shows which ones your agents can use. $490 for three tools, ready in 24 hours.