# Can an AI agent use SuperTokens? L4 · Runs on its own

**L4 · Runs on its own** · [What the levels mean](https://agentdrives.com/method/levels?via=md)

Rank among the 246 products we drove:

- Holds up: 92 / 100, tied #15 (Reliability under errors)
- Steps on its own: 4 / 5, tied #3 (Find to Leave, no person)
- Core work done: 100%, tied #1 (10 of 10 core tasks)
- Time to get in: 8 minutes, tied #83 (Getting in on its own)

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

- Level confirmed: Not yet (Level from one drive; a second must agree)
- Got in by: Sign-up in a browser (8 minutes)
- Got as far as: Pay: ready to pay (Payment not yet proven; stopped at the pay button of the $0.02 charge)

Category: Auth and identity · Connects by: API, CLI, SDK · Agent payments: None found · Driven: 3 Nov 2026

**How to connect**
- CLI install: `npm install -g create-supertokens-app` (documented). Source: https://supertokens.com/
- Docs page: `https://supertokens.com/docs` (tested in our drive). Source: https://supertokens.com/docs

Checked 17 Nov 2026: llms.txt changed since the check before; sign-up page unchanged since the check before.

See [how it ranks among auth providers for agents](https://agentdrives.com/research/best-auth-providers-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. (430 doc pages read)
2. **Get in**: On its own. No key needed, runs locally, sign-up in a browser. (8 minutes)
3. **Use**: On its own. Did: create, list, find, update and delete end users; create, check and revoke sessions. (10 of 10 core tasks)
4. **Pay**: Partly. Ready to pay. Payment not yet proven; stopped at the pay button of the $0.02 charge. First stop.
5. **Leave**: On its own. Nothing to cancel. It deletes its account.

To reach L5: Pay without a person.

## How an agent connects

API, CLI, SDK and llms.txt found.

- **MCP server**: All tested. A server for searching the docs only. (4 tools mapped in our drive)
- **API**: 192 of 205 tested. Core Driver Interface (REST, api-key header) plus the Frontend Driver Interface served by the backend SDKs; 205 operations on the docs reference. (205 operations mapped in our drive)
- **OpenAPI**: Unknown.
- **CLI**: All tested. supertokens CLI manages a self-hosted core process (start, list, stop, uninstall). (5 commands mapped in our drive)
- **SDK**: All tested. supertokens-node 24.1.0; Python and Go backend SDKs documented. Packages: npm [supertokens-node](https://www.npmjs.com/package/supertokens-node), npm [supertokens-auth-react](https://www.npmjs.com/package/supertokens-auth-react), npm [supertokens-web-js](https://www.npmjs.com/package/supertokens-web-js), PyPI [supertokens-python](https://pypi.org/project/supertokens-python/), npm [@supertokens/rownd-react](https://www.npmjs.com/package/@supertokens/rownd-react). (12 methods mapped in our drive)
- **llms.txt**: Yes. https://supertokens.com/llms.txt
- **Agent payments**: None found. Walked to the last click ("Deploy Production Core") and stopped: Production core (usage-based), $0.02 a call. It checks out through Stripe Checkout. No CAPTCHA at checkout.
- **Docs**: In part. Covers getting started, auth, error codes and code examples. Describes each operation only in part: completeness 50 of 100. 10 of 10 documented ways to do the core work worked. https://supertokens.com/docs (430 of 530 pages read)

**Changed since it was driven** (checked daily)
- llms.txt: 9 links added, 268 removed and 4 sections changed, 17 Nov

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

## Getting in

Our agent tried 3 of 4 ways in; 3 worked without a person.

The way that worked: **Sign-up in a browser**, 8 minutes. Needs an inbox and a browser. No person needed.

- Agent on a server (API, MCP, CLI): Partly. Gets in without a browser (runs locally) and does 2 of its 10 core tasks that way. For a full account, it stops at sign-up: it works only in a browser.
- Assistant in its own browser (Like ChatGPT agent): Partly. Signs up and does all of the core work. Payment: ready to pay, payment not yet proven; stopped at the pay button of the $0.02 charge.
- Signed agent (Known to Cloudflare): Yes. The site opens.

| Way in | What happened |
|---|---|
| Sign-up in a browser | Worked |
| Runs locally | Worked: Part of the work done |
| No key needed | Worked |
| Company single sign-on | Not tried: Not part of this drive |

## What an agent can do with SuperTokens

All 10 core tasks done, and 21 of 22 others.

- Holds up: 92 of 100 (Reliability 100, Handles mistakes 83). The mean of the two, 91.5, with a half rounded to the even number.
- Docs match: 82 of 100 (Docs accuracy 96, Docs completeness 50). Docs accuracy counts 70%, completeness 30%.
- Surface tested: 94 of 100. 210 of 224 passed: the 230 documented operations less the 6 that spend money or reach real people

Core tasks:

| Task | Result | Done through |
|---|---|---|
| Register an end user in your app with email and password | Done | API |
| Send an end user a passwordless magic link or OTP code | Done | API |
| Configure a social or enterprise login provider for your app | Done | API |
| Create a session for an end user | Done | API |
| Revoke an end user's sessions | Done | API |
| List and look up your app's end users | Done | API |
| Delete an end user | Done | API |
| Create a role with permissions and assign it to an end user | Done | API |
| Create a tenant for an organisation | Done | API |
| Enrol an end user in TOTP multi-factor authentication | Done | API |

21 of 22 other tasks done:

- Verify an end user's email address: Done
- Reset an end user's password: Done
- Link two end user accounts into one: Done
- Store custom metadata on an end user: Done
- Register a passkey for an end user: Done
- Import users from another auth provider: Done
- Map an external user ID to an end user: Done
- Register an OAuth2 client for unified login: Done
- Issue a machine-to-machine access token: Done
- Create a signed JWT: Done
- Add a SAML connection for a tenant: Done
- Ban or unban an end user: Done
- Impersonate an end user for support: Done
- Customise the prebuilt sign-in and sign-up forms: Done
- Send auth emails through your own SMTP server: Done
- Add login to an agent tool server you host: Done
- Read active user counts: Done
- Add a dashboard admin user: Done
- Create an app in a multi-app setup: Done
- Restrict core access by IP address: Done
- Start or stop a self-hosted core instance: Done
- Detect suspicious sign-ins with the Attack Protection Suite: Paid plan. It is a paid add-on, switched off on the free test server.
- Export auth traces with OpenTelemetry: Not tried

The plans they need:

- Enrol an end user in TOTP multi-factor authentication: MFA add-on ($0.01/MAU, minimum $100/month per pricing)

The drive used the free plan.

What it can't do, and why:

- Sign up for SuperTokens Cloud without a browser: Only a web form was found; no documented sign-up API.
- Create or revoke Cloud API keys through a documented API: The agent did it in the dashboard; no documented API or CLI for keys was found.
- Switch on paid-style features like MFA from code: The feature switches were only found in the dashboard.
- Use the Attack Protection Suite: It is a paid add-on, switched off on the free test server.
- Pay for a production core without a person: No agent payment route or documented billing API was found.
- Delete the account through an API: The agent deleted it in the dashboard; no documented delete API was found.

**Surface audit:** 230 documented operations: 216 run, 8 blocked by sandbox or plan limits and 6 left out because they spend money or reach real people. Of the 216 run, 210 passed and 6 didn't; 8 behaved differently from the docs. By surface, 192 on the API, 12 in the SDK, 5 in the CLI, 4 on the MCP server and 3 elsewhere, such as sign-in and webhooks.

## Tips for agent builders

- Self-host the core image (supertokens/supertokens-postgresql) for a no-account sandbox with an in-memory database.
- On Cloud, do sign-up and key retrieval once in the browser, then drive everything over the CDI with the api-key header.
- Send the rid header (emailpassword, passwordless, thirdparty) on the shared /recipe/user paths.
- Call /recipe/oauth/auth on the core as POST with a params object, and send access_token and id_token objects to /recipe/oauth/token.
- Switch on MFA, account linking, SSO and M2M in the dashboard's Features page: they are free in development.
- For FDI WebAuthn routes, use the paths the SDK serves (/webauthn/options/register, /webauthn/options/signin).

## Paying

Ways to pay checked 3 Nov 2026.

- Result: Partly. Ready to pay. Payment not yet proven; stopped at the pay button of the $0.02 charge.
- Checkout: Walked to the last click ("Deploy Production Core") and stopped: Production core (usage-based), $0.02 a call. It checks out through Stripe Checkout. No CAPTCHA at checkout.
- Trial: It has a free plan.

## Leaving

- Result: On its own. Nothing to cancel. It deletes its account.
- Its account: Yes, in a browser, without a human. The agent deleted the account in the browser (Delete Account, typed confirmation). Sign-in then answered 'Account Deletion in Progress' and within minutes the core host stopped resolving. No documented API to delete an account was found.

## 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; 15 of 15 days
- llms.txt, found on the newest check; 15 of 15 days
- MCP server, answers with an error on the newest check; 4 of 15 days
- OpenAPI, found on the newest check; 1 of 15 days

## How SuperTokens compares

In Auth and identity: None of the 9 products we drove in Auth and identity is higher; 1 other shares L4. As of 15 Nov 2026.

- [FusionAuth](https://agentdrives.com/tools/fusionauth.md?via=md): L4, Gets in on its own
- [PropelAuth](https://agentdrives.com/tools/propelauth.md?via=md): L1, Can't sign up on its own
- **SuperTokens** (this page): L4, Gets in on its own
- [Clerk](https://agentdrives.com/tools/clerk.md?via=md): L3, Gets in on its own
- [WorkOS](https://agentdrives.com/tools/workos.md?via=md): L3, Gets in on its own
- [Auth0](https://agentdrives.com/tools/auth0.md?via=md): L3, Gets in on its own
- [Kinde](https://agentdrives.com/tools/kinde.md?via=md): L3, Gets in on its own
- [HumanMirror](https://agentdrives.com/tools/humanmirror.md?via=md): L3, Gets in on its own
- [Web3Auth (MetaMask Embedded Wallets)](https://agentdrives.com/tools/web3auth.md?via=md): L3, Gets in on its own

[All 9 in Auth and identity](https://agentdrives.com/categories/auth?via=md)

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

On our standard (24 criteria, each against the other auth and identity products we measured on it). Best or ahead on 4 of 24 criteria, behind on 6.

- [Every way in works for an agent](https://agentdrives.com/standard#in-11): **Ahead of 6 of 7** others, 1 the same.
- [Docs an agent can navigate](https://agentdrives.com/standard#docs-11): **Ahead of 5 of 7** others, 2 the same.
- [Versions an agent can pin](https://agentdrives.com/standard#api-07): **Ahead of 3 of 5** others, 2 the same.
- [Delete by API, checked](https://agentdrives.com/standard#leave-02): **Ahead of 5 of 7** others, 1 the same, 1 higher.
- [The best way in is built for agents](https://agentdrives.com/standard#in-12): **Level with 4 of 7** others, 3 lower.
- [Prices an agent can read](https://agentdrives.com/standard#find-06): **Level with 5 of 7** others, 2 lower.
- [Real status codes](https://agentdrives.com/standard#err-01): **Level with 6 of 7** others, 1 lower.
- [A way in with no person](https://agentdrives.com/standard#in-01): **Level with 7 of 8** others, 1 lower.
- [llms.txt that works](https://agentdrives.com/standard#find-02): **Level with 6 of 8** others, 1 lower, 1 higher.
- [Fast to the first call](https://agentdrives.com/standard#in-03): **The same as all** 6 others.
- [Terms allow an agent's account](https://agentdrives.com/standard#in-10): **The same as all** 8 others.
- [Structured results](https://agentdrives.com/standard#mcp-08): **In the middle** 2 of 5 others lower, 1 the same, 2 higher.
- [Errors say what to do next](https://agentdrives.com/standard#err-03): **The same as all** 6 others.
- [Export before leaving](https://agentdrives.com/standard#leave-03): **In the middle** 2 of 7 others lower, 3 the same, 2 higher.
- [An agent payment rail on the core](https://agentdrives.com/standard#pay-02): **Level with 7 of 8** others, 1 higher.
- [Pages fit one fetch](https://agentdrives.com/standard#docs-08): **Level with 6 of 7** others, 1 higher.
- [Spend an agent can see and cap](https://agentdrives.com/standard#pay-05): **Level with 6 of 7** others, 1 higher.
- [A request id on every answer](https://agentdrives.com/standard#err-07): **In the middle** 1 of 7 others lower, 3 the same, 3 higher.
- [One way to page through lists](https://agentdrives.com/standard#api-03): **Tied for the lowest result** 2 of 4 others the same, 2 higher.
- [Limits known before they hit](https://agentdrives.com/standard#lim-02): **Tied for the lowest result** 2 of 4 others the same, 2 higher.
- [A path written for agents](https://agentdrives.com/standard#docs-10): **Behind 4 of 7** others, 3 the same.
- [Results sized for a context window](https://agentdrives.com/standard#mcp-09): **Behind 3 of 5** others, 2 the same.
- [Errors a program can read](https://agentdrives.com/standard#err-02): **Behind 4 of 6** others, 2 the same.
- [Answers sized for an agent](https://agentdrives.com/standard#api-04): **The lowest result** All 4 others higher.

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

## Agents get stuck at Pay

**7** things to fix for agents: 3 small, 3 medium and 1 large

One fix can cover several findings.

Agent blockers: **6 found** Agent surfaces: **8 issues found**

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

We mail a private link to an address at supertokens.com.

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

Or [claim SuperTokens](https://agentdrives.com/go/claim/supertokens?add=supertokens.com&ref=listing) to see where each issue is and ask for a free drive after a fix.

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

### On our standard

Best or ahead on 4 of 24 criteria, behind on 6. Each against the other auth and identity products we measured on it.

- [Every way in works for an agent](https://agentdrives.com/standard#in-11)
- [Docs an agent can navigate](https://agentdrives.com/standard#docs-11)
- [Versions an agent can pin](https://agentdrives.com/standard#api-07)
- [Delete by API, checked](https://agentdrives.com/standard#leave-02)
- [A path written for agents](https://agentdrives.com/standard#docs-10)
- [Results sized for a context window](https://agentdrives.com/standard#mcp-09)
- [Errors a program can read](https://agentdrives.com/standard#err-02)
- [Answers sized for an agent](https://agentdrives.com/standard#api-04)

**All 24 criteria**

- [The best way in is built for agents](https://agentdrives.com/standard#in-12)
- [Prices an agent can read](https://agentdrives.com/standard#find-06)
- [Real status codes](https://agentdrives.com/standard#err-01)
- [A way in with no person](https://agentdrives.com/standard#in-01)
- [llms.txt that works](https://agentdrives.com/standard#find-02)
- [Fast to the first call](https://agentdrives.com/standard#in-03)
- [Terms allow an agent's account](https://agentdrives.com/standard#in-10)
- [Structured results](https://agentdrives.com/standard#mcp-08)
- [Errors say what to do next](https://agentdrives.com/standard#err-03)
- [Export before leaving](https://agentdrives.com/standard#leave-03)
- [An agent payment rail on the core](https://agentdrives.com/standard#pay-02)
- [Pages fit one fetch](https://agentdrives.com/standard#docs-08)
- [Spend an agent can see and cap](https://agentdrives.com/standard#pay-05)
- [A request id on every answer](https://agentdrives.com/standard#err-07)
- [One way to page through lists](https://agentdrives.com/standard#api-03)
- [Limits known before they hit](https://agentdrives.com/standard#lim-02)

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

## For the team behind SuperTokens

**7 things to fix for agents: 3 small, 3 medium and 1 large.**

One fix can cover several findings. Agent blockers: 6 found · Agent surfaces: 8 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 supertokens.com.

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

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

## Read more on this step

Pay is where our agent stopped at SuperTokens.

- [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 SuperTokens

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

Yes, in a browser, without a person. Cloud sign-up through the browser form at supertokens.com/auth (name, email, password). No CAPTCHA. Asked for a full name; our agent answered. The self-hosted core needs no account.

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

SuperTokens's docs have an MCP server for searching them. The drive found no MCP server that works the product itself. The server lists 4 tools and speaks the 25 Nov 2025 MCP spec. A new agent can get in on its own: in the drive of 3 Nov 2026, our agent signed up and got its key without a person.

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

In the drive of 3 Nov 2026, our agent got its SuperTokens API key in a browser, without a person. On Cloud the agent generated, listed and deleted core API keys in the dashboard in its own browser; no documented API for keys was found. Using the key is done without a browser. A revoked key got 401 within seconds. Self-hosted keys are set in config (API_KEYS), without a browser.

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

Yes, in a browser, without a human. The agent deleted the account in the browser (Delete Account, typed confirmation). Sign-in then answered 'Account Deletion in Progress' and within minutes the core host stopped resolving. No documented API to delete an account was found.

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

Partly. Ready to pay: payment not yet proven; stopped at the pay button of the $0.02 charge. It has a free plan.

## Where SuperTokens fits

- Category: [Developer platform](https://agentdrives.com/categories/developer?via=md), [Auth and identity](https://agentdrives.com/categories/auth?via=md)
- Tasks: [Invite a member](https://agentdrives.com/tasks/invite-a-member), [Read usage and quotas](https://agentdrives.com/tasks/read-usage-and-quotas), [Import data from a file or another tool](https://agentdrives.com/tasks/import-data-from-a-file-or-another-tool), [Sign up and sign in your app's users](https://agentdrives.com/tasks/sign-up-and-sign-in-your-app-s-users), [Restrict access by IP address](https://agentdrives.com/tasks/restrict-access-by-ip-address), [Configure sign-in methods for your app](https://agentdrives.com/tasks/configure-sign-in-methods-for-your-app)
- 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), [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: [FusionAuth](https://agentdrives.com/tools/fusionauth?via=md) (L4), [Auth0](https://agentdrives.com/tools/auth0?via=md) (L3), [Clerk](https://agentdrives.com/tools/clerk?via=md) (L3)

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

## Level by drive

One drive so far, on 3 Nov 2026.

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

Source: our drives of SuperTokens. As of 3 Nov 2026.

One drive so far.

Data: [JSON](https://agentdrives.com/api/tools/supertokens.json?via=md) · [Markdown](https://agentdrives.com/tools/supertokens.md?via=md) · [History](https://agentdrives.com/tools/supertokens/history?via=md) · [Atom](https://agentdrives.com/feeds/tools/supertokens.atom) · [JSON Feed](https://agentdrives.com/feeds/tools/supertokens.json) · licence [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/) · evidence sha256 `95e78d6d5ef7d0270cab2e70f288f8f189ad5b3afd1878d415a394af0b819807`

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