# Can an AI agent use Hasura? L3 · Does the work

Hasura is a platform that turns databases into a GraphQL API.

**L3 · Does the work** · [What the levels mean](https://agentdrives.com/method/levels?via=md)

Rank among the 246 products we drove:

- Time to get in: 6 minutes, tied #66 (Getting in on its own)
- Core work done: 70%, tied #78 (7 of 10 core tasks)
- Holds up: 62 / 100, tied #100 (Reliability under errors)
- Steps on its own: 2 / 5, tied #86 (Find to Leave, no person)

**Can an AI agent use Hasura? Yes.** Our agent signed up for Hasura on its own in a browser with an email and password, got an API key and used its API and CLI.

- Level confirmed: Not yet (Level from one drive; a second must agree)
- Got in by: Sign-up in a browser (6 minutes)
- Got as far as: Pay: reaches the checkout (A card form for $5 a month)

Category: Databases · Connects by: API, CLI · Agent payments: None found · Driven: 14 Nov 2026

**How to connect**
- Docs page: `https://hasura.io/docs/3.0/index/` (tested in our drive). Source: https://hasura.io/docs/3.0/index/

Checked 17 Nov 2026: sign-up page and OpenAPI unchanged since the check before.

See [how it ranks among databases for agents](https://agentdrives.com/research/best-databases-for-ai-agents?via=md).

## From finding it to leaving

What an agent managed without a person, at each step.

1. **Find**: On its own. Docs it can act on: llms.txt. (193 doc pages read)
2. **Get in**: On its own. Sign-up in a browser. Email and code: stopped by a manual review. (6 minutes)
3. **Use**: Partly. Did: create a project, connect its own database and add data models; build, deploy and roll back the API, and query and change data through it. 3 not done, among them: use PromptQL (ask questions, connect data, build reports). (7 of 10 core tasks)
4. **Pay**: Partly. Reaches the checkout. A card form for $5 a month. First stop.
5. **Leave**: Partly. Nothing to cancel. Its account stays.

To reach L4: Do 80% of the core work (now 70%) and delete its account, so its keys and login stop working.

## How an agent connects

API, CLI and llms.txt found.

- **MCP server**: Unknown.
- **API**: 22 of 25 tested. Cloud API GraphQL at data.pro.hasura.io/v1/graphql with a PAT. (25 operations mapped in our drive)
- **OpenAPI**: None found.
- **CLI**: 74 of 84 tested. ddn CLI v3.10.0. (84 commands mapped in our drive)
- **SDK**: None found.
- **llms.txt**: Yes. A file that points agents to the docs.
- **Agent payments**: None found. Reached the card form and stopped: DDN Base, $5 a month. It checks out through a Stripe card form. No CAPTCHA at checkout.
- **Docs**: In part. Covers getting started, auth and error codes. Code examples on only some pages. Describes each operation only in part: completeness 50 of 100. 4 of 4 documented ways to do the core work worked. https://hasura.io/docs/3.0/index/ (193 of 201 pages read)

[The standards](https://agentdrives.com/standard)

## Getting in

Our agent tried 2 of 7 ways in; 1 worked without a person.

The way that worked: **Sign-up in a browser**, 6 minutes. Needs an inbox and a browser. No person needed.

- Agent on a server (API, MCP, CLI): No. Stops at sign-up: it works only in a browser.
- Assistant in its own browser (Like ChatGPT agent): Partly. Signs up, confirms its email and does 7 of its 10 core tasks, then stops: the rest needs a paid plan. It can't delete its account.
- Signed agent (Known to Cloudflare): Yes. The sign-up page opens.

| Way in | What happened |
|---|---|
| Sign-up in a browser | Worked |
| Email and code | Stopped by a manual review |
| Runs locally, no account | Not tried: Not part of this drive |
| Continue with GitHub | Not tried: Not part of this drive |
| Continue with Google | Not tried: Not part of this drive |
| CLI code login | Not tried: The same as another way |
| Added by an admin | Not tried: Not part of this drive |

- Bot check: **Google reCAPTCHA let our agent through at sign-up.** Our agent signs every request (Web Bot Auth).

## What an agent can do with Hasura

7 of 10 core tasks done, and 16 of 23 others.

- Holds up: 62 of 100 (Reliability 70, Handles mistakes 54). The mean of the two.
- Docs match: 76 of 100 (Docs accuracy 87, Docs completeness 50). Docs accuracy counts 70%, completeness 30%.
- Surface tested: 75 of 100. 84 of 112 passed: the 115 documented operations less the 3 that spend money or reach real people

Core tasks:

| Task | Result | Done through | Tried, not done |
|---|---|---|---|
| Create a DDN project | Done | CLI | – |
| Connect a data source to a supergraph | Done | CLI | – |
| Add models from a data source | Done | CLI | – |
| Build and deploy the supergraph | Done | CLI | – |
| Query data through the GraphQL API | Done | API | – |
| Insert, update or delete data with GraphQL mutations | Done | API | – |
| Set role-based model and field permissions | Done | API | – |
| Ask a PromptQL bot a question about connected data | Blocked | – | Web app |
| Connect a database or SaaS app to a PromptQL project | Blocked | – | Web app |
| Generate a dashboard or report with PromptQL | Blocked | – | Web app |

16 of 23 other tasks done:

- Subscribe to live data with GraphQL subscriptions: Done
- Add a relationship between models: Done
- Add custom business logic as a command: Done
- Configure JWT or webhook authentication for the API: Done
- Read traces and API performance metrics: Done
- Explain a GraphQL query's execution plan: Done
- Compare two builds for breaking schema changes: Done
- Apply an earlier build to roll back the API: Done
- Set connector environment variables: Done
- Create an event trigger on table changes (GraphQL Engine v2): Done
- Schedule a cron trigger (GraphQL Engine v2): Done
- Add a remote GraphQL schema (GraphQL Engine v2): Done
- Add an action backed by a webhook (GraphQL Engine v2): Done
- Invite a collaborator to a DDN project: Done
- Create a service account for automated access: Done
- Make a project's API public or private: Done
- Deploy supergraph builds from CI/CD: Partly
- Run DDN on a dedicated or BYOC data plane: Paid plan
- Turn on response caching for queries: Blocked
- Expose GraphQL queries as REST endpoints: Blocked
- Record a schema changelog entry: Blocked
- Teach shared context to the PromptQL wiki: Blocked
- Choose the AI model a PromptQL bot uses: Blocked
- Save a recurring PromptQL workflow as a reusable artifact: Blocked

The drive used the no-card trial (DDN Base) and free v2 tier.

What it can't do, and why:

- Use PromptQL (ask questions, connect data, build reports): The account is told project creation is not available; access is by demo request.
- Create scoped API keys without the console: No documented API or command line step creates service accounts or tokens.
- Delete the account: Account Settings, the API and the command line offer no account deletion.
- Fully delete a project: The main project kept serving data minutes after deletion was reported.

**Surface audit:** 115 documented operations: 101 run, 11 blocked by sandbox or plan limits and 3 left out because they spend money or reach real people. Of the 101 run, 84 passed and 17 didn't; 13 behaved differently from the docs. By surface, 74 in the CLI, 22 on the API and 5 elsewhere, such as sign-in and webhooks.

## Tips for agent builders

- New DDN projects default to private API mode: run ddn project subgraph create app and globals, then set-api-access-mode public or send a JWT.
- Pass --subgraph and --supergraph explicitly when CLI context is ambiguous. Some commands ignore --no-prompt.
- Use the Cloud API at data.pro.hasura.io/v1/graphql with a PAT for v2 tenants. Error answers come back as HTTP 200.
- Delete the PAT in Account Settings: ddn auth logout does not revoke it.

## Paying

Ways to pay checked 14 Nov 2026.

- Result: Partly. Reaches the checkout. A card form for $5 a month.
- Checkout: Reached the card form and stopped: DDN Base, $5 a month. It checks out through a Stripe card form. No CAPTCHA at checkout.
- Trial: It has a free plan.

## Leaving

- Result: Partly. Nothing to cancel. Its account stays.
- Its account: Not on its own: blocked. The login stays, and the main DDN project endpoint still served data after 'ddn project delete' reported 'deleted successfully'. The v2 tenant, the other projects and builds, the service account and the PAT went. Account Settings has no delete option and there is no API or CLI for it.

## Checked every day

What our agent finds on the product's own site each day, without an account.

- Sign-up page, loads on the newest check; 4 of 4 days
- llms.txt, not on its site on the newest check (its drive found one elsewhere); 4 of 4 days
- MCP server, not on its site on the newest check; 4 of 4 days
- OpenAPI, found on the newest check; 4 of 4 days

## How Hasura compares

In Databases: 4 of the 21 products we drove in Databases are higher; 9 others share L3. As of 14 Nov 2026.

- [Upstash](https://agentdrives.com/tools/upstash.md?via=md): L4, Gets in on its own
- [Airtable](https://agentdrives.com/tools/airtable.md?via=md): L4, Gets in on its own
- [NocoDB](https://agentdrives.com/tools/nocodb.md?via=md): L4, Gets in on its own
- [Convex](https://agentdrives.com/tools/convex.md?via=md): L4, Gets in on its own
- [Redis Cloud](https://agentdrives.com/tools/redis.md?via=md): L3, Gets in on its own
- [Firebase](https://agentdrives.com/tools/firebase-google.md?via=md): L3, Gets in on its own
- [Neon](https://agentdrives.com/tools/neon.md?via=md): L3, Gets in on its own
- [PlanetScale](https://agentdrives.com/tools/planetscale.md?via=md): L2, Gets in on its own
- [Baserow](https://agentdrives.com/tools/baserow.md?via=md): L1, Can't sign up on its own
- [MongoDB Atlas](https://agentdrives.com/tools/mongodb.md?via=md): L1, Can't sign up on its own
- [Supabase](https://agentdrives.com/tools/supabase.md?via=md): L1, Can't sign up on its own
- **Hasura** (this page): L3, Gets in on its own

12 of 21 shown, in the directory's order.

[All 21 in Databases](https://agentdrives.com/categories/databases?via=md)

[How we rank](https://agentdrives.com/method?via=md#order)

On our standard (27 criteria, each against the other databases products we measured on it). Best or ahead on 2 of 27 criteria, behind on 8.

- [Pages fit one fetch](https://agentdrives.com/standard#docs-08): **Ahead of 14 of 16** others, 2 the same.
- [Signed agents get past the bot check](https://agentdrives.com/standard#in-04): **Ahead of 5 of 7** others, 2 the same.
- [Answers sized for an agent](https://agentdrives.com/standard#api-04): **Level with 9 of 14** others, 5 lower.
- [A way in with no person](https://agentdrives.com/standard#in-01): **Level with 13 of 19** others, 6 lower.
- [Sign-in for agents acting for a person](https://agentdrives.com/standard#in-08): **Level with 11 of 15** others, 4 lower.
- [Versions an agent can pin](https://agentdrives.com/standard#api-07): **Level with 12 of 16** others, 4 lower.
- [Agents may read docs, API and sign-up](https://agentdrives.com/standard#find-01): **Level with 10 of 13** others, 3 lower.
- [A request id on every answer](https://agentdrives.com/standard#err-07): **In the middle** 6 of 14 others lower, 5 the same, 3 higher.
- [No person in the buy path](https://agentdrives.com/standard#pay-06): **Level with 12 of 13** others, 1 lower.
- [Fast to the first call](https://agentdrives.com/standard#in-03): **Level with 14 of 15** others, 1 lower.
- [Terms allow an agent's account](https://agentdrives.com/standard#in-10): **Level with 16 of 17** others, 1 lower.
- [Prices an agent can read](https://agentdrives.com/standard#find-06): **The same as all** 14 others.
- [Real status codes](https://agentdrives.com/standard#err-01): **The same as all** 16 others.
- [An agent payment rail on the core](https://agentdrives.com/standard#pay-02): **The same as all** 18 others.
- [A plan an agent can buy by API](https://agentdrives.com/standard#pay-03): **The same as all** 12 others.
- [WebMCP tools on the web app](https://agentdrives.com/standard#proto-02): **The same as all** 14 others.
- [Docs an agent can navigate](https://agentdrives.com/standard#docs-11): **Level with 14 of 16** others, 2 higher.
- [Every way in works for an agent](https://agentdrives.com/standard#in-11): **Level with 12 of 18** others, 1 lower, 5 higher.
- [Limits known before they hit](https://agentdrives.com/standard#lim-02): **Level with 7 of 10** others, 3 higher.
- [Delete by API, checked](https://agentdrives.com/standard#leave-02): **Behind 6 of 11** others, 5 the same.
- [Spend an agent can see and cap](https://agentdrives.com/standard#pay-05): **Behind 12 of 19** others, 7 the same.
- [The best way in is built for agents](https://agentdrives.com/standard#in-12): **Behind 12 of 18** others, 6 the same.
- [Export before leaving](https://agentdrives.com/standard#leave-03): **Behind 11 of 16** others, 5 the same.
- [Errors a program can read](https://agentdrives.com/standard#err-02): **Behind 13 of 17** others, 4 the same.
- [llms.txt that works](https://agentdrives.com/standard#find-02): **Behind 16 of 19** others, 3 the same.
- [A path written for agents](https://agentdrives.com/standard#docs-10): **Behind 15 of 16** others, 1 the same.
- [Errors say what to do next](https://agentdrives.com/standard#err-03): **Behind 16 of 17** others, 1 the same.

[How each criterion is graded](https://agentdrives.com/standard)

## Agents get stuck at Pay

**9** things to fix for agents: 4 small and 5 medium

One fix can cover several findings.

Agent blockers: **4 found** Agent surfaces: **13 issues found**

[Get your findings, free](https://agentdrives.com/your-findings?p=hasura) · [What a drive covers](https://agentdrives.com/method?via=md)

We mail a private link to an address at hasura.io.

1. Find Clear
2. Get in Clear
3. Use Partly
4. Pay Blocks agents
5. Leave Partly

Or [claim Hasura](https://agentdrives.com/go/claim/hasura?add=hasura.io&ref=listing&safety=1) to see where each issue is, read your safety findings with their fixes and ask for a free drive after a fix.

Want Hasura driven every month? [See Watch](https://agentdrives.com/owners#watch)

### On our standard

Best or ahead on 2 of 27 criteria, behind on 8. Each against the other databases products we measured on it.

- [Pages fit one fetch](https://agentdrives.com/standard#docs-08)
- [Signed agents get past the bot check](https://agentdrives.com/standard#in-04)
- [Answers sized for an agent](https://agentdrives.com/standard#api-04)
- [A way in with no person](https://agentdrives.com/standard#in-01)
- [Errors a program can read](https://agentdrives.com/standard#err-02)
- [llms.txt that works](https://agentdrives.com/standard#find-02)
- [A path written for agents](https://agentdrives.com/standard#docs-10)
- [Errors say what to do next](https://agentdrives.com/standard#err-03)

**All 27 criteria**

- [Sign-in for agents acting for a person](https://agentdrives.com/standard#in-08)
- [Versions an agent can pin](https://agentdrives.com/standard#api-07)
- [Agents may read docs, API and sign-up](https://agentdrives.com/standard#find-01)
- [A request id on every answer](https://agentdrives.com/standard#err-07)
- [No person in the buy path](https://agentdrives.com/standard#pay-06)
- [Fast to the first call](https://agentdrives.com/standard#in-03)
- [Terms allow an agent's account](https://agentdrives.com/standard#in-10)
- [Prices an agent can read](https://agentdrives.com/standard#find-06)
- [Real status codes](https://agentdrives.com/standard#err-01)
- [An agent payment rail on the core](https://agentdrives.com/standard#pay-02)
- [A plan an agent can buy by API](https://agentdrives.com/standard#pay-03)
- [WebMCP tools on the web app](https://agentdrives.com/standard#proto-02)
- [Docs an agent can navigate](https://agentdrives.com/standard#docs-11)
- [Every way in works for an agent](https://agentdrives.com/standard#in-11)
- [Limits known before they hit](https://agentdrives.com/standard#lim-02)
- [Delete by API, checked](https://agentdrives.com/standard#leave-02)
- [Spend an agent can see and cap](https://agentdrives.com/standard#pay-05)
- [The best way in is built for agents](https://agentdrives.com/standard#in-12)
- [Export before leaving](https://agentdrives.com/standard#leave-03)

[How each criterion is graded](https://agentdrives.com/standard)

## For the team behind Hasura

**9 things to fix for agents: 4 small and 5 medium.**

One fix can cover several findings. Agent blockers: 4 found · Agent surfaces: 13 issues found.

Agents get stuck at Pay. Its team gets the two findings that matter most in full, free, by a private link to an address at hasura.io.

- Find: Clear
- Get in: Clear
- Use: Partly
- Pay: Blocks agents
- Leave: Partly

[Get your findings, free](https://agentdrives.com/your-findings?p=hasura) · [Claim Hasura](https://agentdrives.com/app/products?add=hasura.io&ref=listing&safety=1) · [What a drive covers](https://agentdrives.com/method?via=md)

## Read more on this step

Pay is where our agent stopped at Hasura.

- [How AI agents pay for software: x402, MPP and checkouts](https://agentdrives.com/guides/how-ai-agents-pay-for-software?via=md) (guide): Card checkouts, x402 and MPP: what an agent can pay with today, and what most products ask instead.
- [Bot checks on SaaS checkouts: where AI agents stop](https://agentdrives.com/guides/bot-checks-on-saas-checkouts-where-ai-agents?via=md) (guide): As of 31 Oct 2026: 42 of 59 SaaS checkouts our agent reached on 31 Oct 2026 carried a bot check; under 5 made it solve one. 80 of 139 stopped earlier. What to fix so an agent can buy.
- [Tell an AI agent a feature needs a paid plan](https://agentdrives.com/guides/tell-ai-agents-a-feature-needs-a-paid-plan?via=md) (guide): How to answer an AI agent at a paid-plan wall: 402 or 403, a Problem Details body with the required plan, and an upgrade link a person can open.

[Everything on Pay](https://agentdrives.com/access/pay)

## Questions people ask about Hasura

**Can an AI agent create a Hasura account on its own?**

Yes, in a browser, without a person. Email + password sign-up on cloud.hasura.io, reached from the ddn auth login OAuth URL, in the browser; an invisible reCAPTCHA passed. Asked for a name; our agent answered.

**Does Hasura have an MCP server, and can an agent connect to it?**

No. The drive found no MCP server for Hasura. A new agent can get in on its own: in the drive of 14 Nov 2026, our agent signed up, verified and got its key without a person.

**How does an AI agent get a Hasura API key?**

In the drive of 14 Nov 2026, our agent got its Hasura API key in a browser, without a person. CLI OAuth login with a localhost callback gave a PAT (ddn auth print-access-token). There is no API or CLI to mint scoped keys: a read-only service account token was made in the console, used through the CLI, then revoked (refused afterwards).

**Can an AI agent delete its Hasura account?**

Not on its own: blocked. The login stays, and the main DDN project endpoint still served data after 'ddn project delete' reported 'deleted successfully'. The v2 tenant, the other projects and builds, the service account and the PAT went. Account Settings has no delete option and there is no API or CLI for it.

**Can an AI agent pay for Hasura?**

Partly. Our agent reached a card form for $5 a month. It has a free plan.

## Where Hasura fits

- Category: [Data and storage](https://agentdrives.com/categories/data?via=md), [Databases](https://agentdrives.com/categories/databases?via=md)
- Tasks: [Register a webhook](https://agentdrives.com/tasks/register-a-webhook), [Invite a member](https://agentdrives.com/tasks/invite-a-member), [Create an API key](https://agentdrives.com/tasks/create-an-api-key), [Create or update a record](https://agentdrives.com/tasks/create-or-update-a-record), [Query a database over a REST or GraphQL API](https://agentdrives.com/tasks/query-a-database-over-a-rest-or-graphql-api), [Read service metrics](https://agentdrives.com/tasks/read-service-metrics)
- Vendors: [Google reCAPTCHA](https://agentdrives.com/research/bot-checks?via=md#recaptcha) (let our agent through)
- Standards: [llms.txt](https://agentdrives.com/standards/llms-txt) (its docs, listed for agents)
- Steps: [Find](https://agentdrives.com/access/find), [Get in](https://agentdrives.com/access/get-in), [Use](https://agentdrives.com/access/use), [Pay](https://agentdrives.com/access/pay) (first stop), [Leave](https://agentdrives.com/access/leave)
- Topics: [Docs and llms.txt](https://agentdrives.com/access/find/docs) (Find step), [Bot checks](https://agentdrives.com/access/get-in/bot-checks) (Get in step), [Sign-up](https://agentdrives.com/access/get-in/sign-up) (Get in step), [Card checkout](https://agentdrives.com/access/pay/card-checkout) (Pay step), [Delete the account](https://agentdrives.com/access/leave/delete-account) (Leave step)
- Rivals: [Couchbase](https://agentdrives.com/tools/couchbase?via=md) (L3), [Firebase](https://agentdrives.com/tools/firebase-google?via=md) (L3), [Neo4j](https://agentdrives.com/tools/neo4j?via=md) (L3)

The level follows [these rules](https://agentdrives.com/changes#rules-2026-11-18).

## Level by drive

One drive so far, on 14 Nov 2026.

[Every drive in full](https://agentdrives.com/tools/hasura/history?via=md)

Source: our drives of Hasura. As of 14 Nov 2026.

One drive so far.

Data: [JSON](https://agentdrives.com/api/tools/hasura.json?via=md) · [Markdown](https://agentdrives.com/tools/hasura.md?via=md) · [History](https://agentdrives.com/tools/hasura/history?via=md) · [Atom](https://agentdrives.com/feeds/tools/hasura.atom) · [JSON Feed](https://agentdrives.com/feeds/tools/hasura.json) · licence [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/) · evidence sha256 `f1da49b974ec0603759e21f2371ec8b535241e0fa322833324d01367745b685a`

**Found an error?** [Tell us on this page](https://agentdrives.com/tools/hasura?via=md#correct) or read [how corrections work](https://agentdrives.com/corrections?via=md).
