Airtable vs Baserow for AI agents
As of 15 Oct 2026, Airtable gets an AI agent further: L4 · Runs on its own against L1 · Needs a person.
- Find: Some docs for agents: llms.txt and an MCP server.
- Access: MCP sign-in, sign-up in a browser.
- Use: 100% of the work.
- Pay: Reaches the checkout: Stopped at the $24 a month charge.
- Leave: Leaves on its own: Nothing to cancel, deletes what it made.
Through every checkpoint. Next: pay without a person
Gets in on its own today, L4 · Runs on its own. Sign-up blocks headless requests, but our agent reached the browser form with no visible challenge and confirmed its email there. Personal access tokens, the first workspace and turning on automations all still need that browser UI. Once past those steps, the API and the official MCP server ran almost all of Airtable's core work: bases, records, schema, webhooks, automations, interfaces and forms. Upgrading opens a Stripe card form inside the app; our agent found no agent payment rail and stopped before paying. It started no plan, so there was nothing to cancel, and it deleted its account through account settings.
Gets furtherDriven 15 Oct 2026 · The drive and its evidence- 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 evidenceThe two summaries: written and checked by our agents from each product's drive. How we write.
Where each one stops.
AirtableThrough every checkpoint
BaserowStopped at sign up: needs a human
| Checkpoint | Airtable | Baserow |
|---|---|---|
| Docs | Headless | Headless |
| Sign up | In a browser | Needs a human |
| Verify | In a browser | Not reached |
| Key | In a browser | Not reached |
| First call | Headless | Not reached |
| First action | Headless | Not reached |
| Pay | In a browser | Not reached |
| Cancel | Not needed | Not reached |
| Delete | In a browser | Not reached |
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
| Airtable | Baserow | |
|---|---|---|
| Headless (checkpoints) | 3 | 1 |
| In a browser (checkpoints) | 5 | 0 |
| Needs a human (checkpoints) | 0 | 1 |
| Blocked (checkpoints) | 0 | 0 |
| Not tested (checkpoints) | 0 | 7 |
| Work done | 100% of the core | Not measured |
| API | Yes | Yes |
| OpenAPI | No | Yes |
| MCP server | Yes (official) | Yes (official) |
| CLI | Yes | No |
| SDK | – | No |
| llms.txt | Yes | Yes |
Bot checks, and where a person was needed.
| Airtable | Baserow | |
|---|---|---|
| Bot check | HUMAN let it through at sign up | Cloudflare Turnstile stopped it at sign up, with a visible challenge |
| Wall type | No bot-check wall | A check of our network and browser |
| First wall | None | Cloudflare Turnstile on the sign-up form |
| 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. Where we drive from.
Level and part scores.
| Airtable | Baserow | |
|---|---|---|
| Level | L4 · Runs on its own | L1 · Needs a person |
| Holds up | 78 of 100, fair | Not measured |
| Agent-ready setup | 75 of 100, fair | 90 of 100, good |
| Standards | MCP spec of 25 Nov 2025 (1 version behind) · MCP discovery (behind) · MCP client registration (current) | OpenAPI 3.0.3 (2 versions behind) |
Docs match is measured in an Audit. What the scores mean.
Pay, cancel and delete.
| Airtable | Baserow | |
|---|---|---|
| Pay | Reaches the checkout | Payment not reached |
| Free plan or trial | Trial, no card | Free plan |
| Cancel | Not needed | Not reached |
| Delete the account | In a browser | Not reached |
How each one takes payment
- Airtable: Reaches the checkout: stopped at the $24 a month charge.
- Baserow: Payment not reached.
Airtable vs Baserow: the short answers.
Which can an AI agent use, Airtable or Baserow?
Airtable gets an AI agent further: L4 · Runs on its own against L1 · Needs a person. With Airtable our agent went through every checkpoint; with Baserow it was stopped at sign up (needs a human). Driven 15 Oct 2026 (Airtable) and 6 Oct 2026 (Baserow).
Can an AI agent sign up for Airtable and Baserow on its own?
Airtable: yes, in a browser. Baserow: no, needs a human.
Do Airtable and Baserow have an MCP server?
Airtable: yes (official). Baserow: yes (official).
Can an AI agent delete its Airtable or Baserow account?
Airtable: yes, in a browser. Baserow: not reached.
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.