# Can an AI agent use Auth0? L3 · Does the work

Auth0 is an identity service that handles logins for apps.

**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: 3 minutes, tied #29 (Getting in on its own)
- Holds up: 80 / 100, tied #45 (Reliability under errors)
- Core work done: 90%, tied #50 (9 of 10 core tasks)
- Steps on its own: 3 / 5, tied #35 (Find to Leave, no person)

**Can an AI agent use Auth0? Yes.** Our agent signed up for Auth0 on its own in a browser through a device login, got an API key and used its API, MCP server and CLI. It offers agents a way to pay: Stripe Projects.

- Level confirmed: Not yet (Level from one drive; a second must agree)
- Got in by: Sign-up in a browser (3 minutes)
- Got as far as: Use: 9 of 10 core tasks (A person has to buy)

Category: Auth and identity · Connects by: MCP, API, CLI, SDK · Agent payments: Stripe Projects; our agent didn't try it · Driven: 2 Nov 2026

**How to connect**
- Docs page: `https://auth0.com/blog/developers/` (tested in our drive). Source: https://auth0.com/blog/developers/

Checked 17 Nov 2026: sign-up page, llms.txt and OpenAPI 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, an OpenAPI and an MCP server. (584 doc pages read)
2. **Get in**: On its own. No key needed, sign-up in a browser. Email and code: stopped by a CAPTCHA. (3 minutes)
3. **Use**: On its own. Did: create and manage applications, APIs, connections, users, roles and organizations; write an access model and check who may see what in the fine-grained authorization product. (9 of 10 core tasks)
4. **Pay**: Stopped. Needs a person to buy. Plans are sold only in the Dashboard, behind a visible human check. (1 way for agents to pay) First stop. [The page it saw](https://agentdrives.com/stops/auth0.png)
5. **Leave**: Partly. Nothing to cancel. It deletes its data, but the login stays.

To reach L4: Delete its account, so its keys and login stop working.

## How an agent connects

MCP, API, OpenAPI, CLI, SDK, agent payments and llms.txt, all found.

- **MCP server**: 22 of 23 tested. Official server. Local stdio Auth0 MCP server 0.1.0-beta.19 (23 tools, answers the 25 Nov 2025 MCP spec); keyless docs MCP at /docs/mcp on the 28 Jul 2026 spec. (23 tools mapped in our drive)
- **API**: 326 of 506 tested. Management API v2; clear JSON errors with errorCode. (506 operations mapped in our drive)
- **OpenAPI**: Yes. A machine-readable description of the API.
- **CLI**: 171 of 286 tested. Auth0 CLI 1.39.0 with an agent mode (JSON output, device or client-credentials login), 286 commands. (286 commands mapped in our drive)
- **SDK**: All tested. Node SDK auth0 7.6.0 (ManagementClient). Packages: npm [auth0-guardian-js](https://www.npmjs.com/package/auth0-guardian-js), npm [@auth0/auth0-spa-js](https://www.npmjs.com/package/@auth0/auth0-spa-js), PyPI [auth0-python](https://pypi.org/project/auth0-python/). (9 methods mapped in our drive)
- **llms.txt**: Yes. https://auth0.com/llms.txt
- **Agent payments**: Listed, not tested. Stripe Projects. The checkout wasn't reached. Stripe Directory lists it as @auth0, with Stripe Projects and a Stripe App. [Stripe Docs, 10 Nov 2026](https://docs.stripe.com/directory)
- **Docs**: In part. Covers getting started, auth and error codes. Code examples on only some pages. Describes each operation only in part: completeness 70 of 100. 14 of 14 documented ways to do the core work worked. https://auth0.com/blog/developers/ (584 of 7,832 pages read)

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

## Getting in

Our agent tried 3 of 6 ways in; 2 worked without a person.

The way that worked: **Sign-up in a browser**, 3 minutes. No inbox, browser or person needed.

- Agent on a server (API, MCP, CLI): Partly. Gets in without a browser (no key needed) and does 0 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, confirms its email and does 9 of its 10 core tasks, then stops: deletes its data, but the login stays.
- Signed agent (Known to Cloudflare): Yes. The sign-up page opens.

| Way in | What happened |
|---|---|
| Sign-up in a browser | Worked |
| No key needed | Worked: Part of the work done |
| Email and code | Stopped by a CAPTCHA |
| Identity assertion | Not tried: Needs a person's account |
| Company single sign-on | Not tried: Needs a person's account |
| Added by an admin | Not tried: Needs a person's account |

- Crawlers: **The robots.txt on auth0.auth0.com asks crawlers to stay off sign-up.** Nothing to fix.

[How agents get past bot checks](https://agentdrives.com/guides/let-signed-agents-past-your-bot-check.md?via=md)

## What an agent can do with Auth0

9 of 10 core tasks done, and 21 of 23 others.

- Holds up: 80 of 100 (Reliability 83, Handles mistakes 77). The mean of the two.
- Docs match: 88 of 100 (Docs accuracy 95, Docs completeness 70). Docs accuracy counts 70%, completeness 30%.
- Surface tested: 62 of 100. 506 of 819 passed: the 882 documented operations less the 63 that spend money or reach real people

Core tasks:

| Task | Result | Done through | Tried, not done |
|---|---|---|---|
| Register an application for login | Done | API, MCP, CLI | – |
| Configure sign-in methods (social, database, passwordless, enterprise connections) | Done | API | – |
| Create a user | Done | API, CLI | – |
| Update or block a user | Done | API, CLI | – |
| Delete a user | Done | API | – |
| Register an API and its scopes | Done | API, MCP, CLI | – |
| Create roles and assign permissions to users | Done | API | – |
| Create an organization and invite a member | Done | API | – |
| Define a fine-grained authorization model and check access | Done | API | – |
| Let an AI agent call third-party APIs for a user with Token Vault | Partly | – | API |

21 of 23 other tasks done:

- Turn on multi-factor authentication for logins: Done
- Write and deploy an Action on a login trigger: Done
- Build a Form for the login flow: Done
- Authorize a machine-to-machine client for an API: Done
- Customise the Universal Login page branding: Done
- Customise an email template: Done
- Send auth emails through your own email provider: Done
- Read tenant logs: Done
- Stream logs to an external service: Done
- Send events to a webhook with Event Streams: Done
- Import users from a file: Done
- Export users to a file: Done
- Configure attack protection (brute force, suspicious IP, breached passwords): Done
- Let a customer admin set up their own SSO (self-service SSO): Done
- Provision app users from a directory with inbound SCIM: Done
- Revoke a user's sessions: Done
- Link two user accounts: Done
- Connect a custom domain: Done
- Change tenant settings: Done
- Restrict tenant access by IP address: Done
- Read active-user statistics: Done
- Request a user's approval asynchronously with CIBA: Partly
- Register an AI agent as an identity: Blocked. The agents API is Early Access and its scopes are not offered on a free tenant.
- Invite a dashboard admin to the tenant: Blocked. Dashboard-only, behind the same visible check.

What it can't do, and why:

- Buy or change a plan: Plans are sold only in the Dashboard, behind a visible human check.
- Delete the tenant or the account: Only the Dashboard or Support offers it; the Dashboard shows a visible check.
- Connect a third-party account to Token Vault: The drive had no Google or other provider account to connect.
- Register an agent identity: The agents API is Early Access and its scopes are not offered on a free tenant.
- Approve a CIBA request: Push approval needs an enrolled phone; the email channel needs a paid plan.
- Invite a dashboard admin: Dashboard-only, behind the same visible check.

Needs a paid plan:

- Request a user's approval asynchronously with CIBA: paid (email/my-account async approval channels)

The drive used the free plan.

**Surface audit:** 882 documented operations: 552 run, 269 blocked by sandbox or plan limits and 61 left out because they spend money or reach real people. Of the 552 run, 506 passed and 46 didn't; 27 behaved differently from the docs. By surface, 326 on the API, 171 in the CLI, 22 on the MCP server, 9 in the SDK and 24 elsewhere, such as sign-in and webhooks.

## Tips for agent builders

- Run `auth0 login --agent-mode`: it prints the device URL and code as JSON. Confirm and accept on auth0.auth0.com, then create an M2M app and client grant and use client credentials from then on.
- Request only the default scopes at device login; extra --scopes can make activation fail with 'User is not authorized'.
- Create apps by API with oidc_conformant: true when you need the Token Vault grant; the API's default is false and the 400 doesn't say why.
- Start a listener on your callback port so Universal Login redirects (codes and errors) can be read.
- Without third-party credentials, configure email with the 'custom' provider: an Action on the custom-email-provider trigger, then POST /emails/provider with credentials {}.
- Use the docs MCP at https://auth0.com/docs/mcp, not the URL in its server card.

## Paying

Ways to pay checked 2 Nov 2026.

- Result: Stopped. Needs a person to buy. Plans are sold only in the Dashboard, behind a visible human check.
- Ways to pay:
  - Stripe Projects (through Stripe's catalog)
- Trial: No card needed to start.

## Leaving

- Result: Partly. Nothing to cancel. It deletes its data, but the login stays.
- Its account: Not all of it: it deletes its data, but the login stays. The Auth0 account and its empty tenant stay. Tenant deletion is Dashboard-only (docs) and the Dashboard showed a visible Cloudflare check. All data the drive made was deleted by API, the M2M key revoked and the FGA store deleted; the login still works.

## 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; 14 of 14 days
- llms.txt, found on the newest check; 14 of 14 days
- MCP server, not on its site on the newest check (its drive found one elsewhere); 14 of 14 days
- OpenAPI, found on the newest check; 4 of 14 days

## How Auth0 compares

In Auth and identity: 2 of the 9 products we drove in Auth and identity are higher; 5 others share L3. 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](https://agentdrives.com/tools/supertokens.md?via=md): 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** (this page): 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 (27 criteria, each against the other auth and identity products we measured on it). Best or ahead on 6 of 27 criteria, behind on 7.

- [Export before leaving](https://agentdrives.com/standard#leave-03): **Ahead of 6 of 7** others, 1 the same.
- [Agents may read docs, API and sign-up](https://agentdrives.com/standard#find-01): **Ahead of 4 of 5** others, 1 the same.
- [Limits known before they hit](https://agentdrives.com/standard#lim-02): **Ahead of 3 of 4** others, 1 the same.
- [A request id on every answer](https://agentdrives.com/standard#err-07): **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.
- [Errors a program can read](https://agentdrives.com/standard#err-02): **Tied for the best result** 3 of 6 others the same, 3 lower.
- [Sign-in for agents acting for a person](https://agentdrives.com/standard#in-08): **Level with 3 of 5** 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.
- [Errors say what to do next](https://agentdrives.com/standard#err-03): **The same as all** 6 others.
- [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 plan an agent can buy by API](https://agentdrives.com/standard#pay-03): **Level with 5 of 6** others, 1 higher.
- [Docs an agent can navigate](https://agentdrives.com/standard#docs-11): **In the middle** 1 of 7 others lower, 3 the same, 3 higher.
- [Every way in works for an agent](https://agentdrives.com/standard#in-11): **Level with 5 of 7** others, 2 higher.
- [Delete by API, checked](https://agentdrives.com/standard#leave-02): **Level with 4 of 7** others, 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.
- [Answers sized for an agent](https://agentdrives.com/standard#api-04): **Behind 3 of 4** others, 1 lower.
- [A path written for agents](https://agentdrives.com/standard#docs-10): **Behind 4 of 7** others, 3 the same.
- [The best way in is built for agents](https://agentdrives.com/standard#in-12): **Behind 5 of 7** others, 1 the same, 1 lower.
- [Results sized for a context window](https://agentdrives.com/standard#mcp-09): **Behind 3 of 5** others, 2 the same.
- [Structured results](https://agentdrives.com/standard#mcp-08): **Behind 4 of 5** others, 1 the same.
- [No person in the buy path](https://agentdrives.com/standard#pay-06): **The lowest result** All 5 others higher.

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

## Agents get stuck at Pay

**9** things to fix for agents: 4 small, 4 medium and 1 large

One fix can cover several findings.

Agent blockers: **6 found** Agent surfaces: **27 issues found**

[Get your findings, free](https://agentdrives.com/your-findings?p=auth0) · [What a drive covers](https://agentdrives.com/method?via=md)

We mail a private link to an address at auth0.com.

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

Or [claim Auth0](https://agentdrives.com/go/claim/auth0?add=auth0.com&ref=listing) to see where each issue is and ask for a free drive after a fix.

Want Auth0 driven every month? [See Watch](https://agentdrives.com/owners#watch)

### On our standard

Best or ahead on 6 of 27 criteria, behind on 7. Each against the other auth and identity products we measured on it.

- [Export before leaving](https://agentdrives.com/standard#leave-03)
- [Agents may read docs, API and sign-up](https://agentdrives.com/standard#find-01)
- [Limits known before they hit](https://agentdrives.com/standard#lim-02)
- [A request id on every answer](https://agentdrives.com/standard#err-07)
- [The best way in is built for agents](https://agentdrives.com/standard#in-12)
- [Results sized for a context window](https://agentdrives.com/standard#mcp-09)
- [Structured results](https://agentdrives.com/standard#mcp-08)
- [No person in the buy path](https://agentdrives.com/standard#pay-06)

**All 27 criteria**

- [Versions an agent can pin](https://agentdrives.com/standard#api-07)
- [Errors a program can read](https://agentdrives.com/standard#err-02)
- [Sign-in for agents acting for a person](https://agentdrives.com/standard#in-08)
- [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)
- [Errors say what to do next](https://agentdrives.com/standard#err-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 plan an agent can buy by API](https://agentdrives.com/standard#pay-03)
- [Docs an agent can navigate](https://agentdrives.com/standard#docs-11)
- [Every way in works for an agent](https://agentdrives.com/standard#in-11)
- [Delete by API, checked](https://agentdrives.com/standard#leave-02)
- [One way to page through lists](https://agentdrives.com/standard#api-03)
- [Answers sized for an agent](https://agentdrives.com/standard#api-04)
- [A path written for agents](https://agentdrives.com/standard#docs-10)

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

## For the team behind Auth0

**9 things to fix for agents: 4 small, 4 medium and 1 large.**

One fix can cover several findings. Agent blockers: 6 found · Agent surfaces: 27 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 auth0.com.

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

[Get your findings, free](https://agentdrives.com/your-findings?p=auth0) · [Claim Auth0](https://agentdrives.com/app/products?add=auth0.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 Auth0.

- [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.
- [How far does an AI agent get in a card checkout?](https://agentdrives.com/findings/card-checkout?via=md) (finding): Our agent reached the checkout at 88 of the 190 products it set out to buy from, and the card form at 68.
- [Agent experience (AX): what it is, measured at 246 products](https://agentdrives.com/guides/agent-experience?via=md) (guide): As of 9 Nov 2026: Agent experience (AX) is whether an AI agent can find, get into, use and pay for a product on its own. We drove 246 products to measure it.

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

## Questions people ask about Auth0

**Can an AI agent create an Auth0 account on its own?**

Yes, in a browser, without a person. Email code sign-up at auth0.com/signup in the browser, no CAPTCHA. Onboarding asked for a company name, company size, country and state; our agent answered.

**Does Auth0 have an MCP server, and can an agent connect to it?**

Yes. Auth0 has an official MCP server. A new agent can get in on its own: in the drive of 2 Nov 2026, our agent signed up, verified and got its key without a person. Through the MCP server, our agent tried 2 tasks and did 2.

**How does an AI agent get an Auth0 API key?**

In the drive of 2 Nov 2026, our agent got its Auth0 API key over the API, without a browser or a person. Without a browser through the CLI device login (agent mode, JSON device URL and code; confirm and consent on auth0.auth0.com, no check). Then a scoped M2M app and client grant were made by CLI and used, and revoked at the end (new tokens get 401). The Dashboard key pages sit behind a visible Cloudflare check.

**Can an AI agent delete its Auth0 account?**

Not all of it: it deletes its data, but the login stays. The Auth0 account and its empty tenant stay. Tenant deletion is Dashboard-only (docs) and the Dashboard showed a visible Cloudflare check. All data the drive made was deleted by API, the M2M key revoked and the FGA store deleted; the login still works.

**Can an AI agent pay for Auth0?**

No. A person has to buy: a CAPTCHA before the checkout. No card needed to start. Auth0 offers agents a way to pay: Stripe Projects.

## Where Auth0 fits

- Category: [Developer platform](https://agentdrives.com/categories/developer?via=md), [Auth and identity](https://agentdrives.com/categories/auth?via=md)
- Tasks: [Register a webhook](https://agentdrives.com/tasks/register-a-webhook), [Export data to a file](https://agentdrives.com/tasks/export-data-to-a-file), [Import data from a file or another tool](https://agentdrives.com/tasks/import-data-from-a-file-or-another-tool), [Register an OAuth app](https://agentdrives.com/tasks/register-an-oauth-app), [Set the brand logo and colours](https://agentdrives.com/tasks/set-the-brand-logo-and-colours), [Read logs](https://agentdrives.com/tasks/read-logs)
- Wall: [Bot checks](https://agentdrives.com/access/get-in/bot-checks) (our agent got in another way)
- Vendors: [Cloudflare](https://agentdrives.com/research/bot-checks?via=md#cloudflare) (on one way in)
- Standards: [MCP](https://agentdrives.com/standards/mcp) (tools an agent can call), [OpenAPI](https://agentdrives.com/standards/openapi) (its API, described), [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: [MCP servers](https://agentdrives.com/access/find/mcp-servers) (Find step), [Docs and llms.txt](https://agentdrives.com/access/find/docs) (Find step), [MCP sign-in](https://agentdrives.com/access/get-in/mcp-sign-in) (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: [Clerk](https://agentdrives.com/tools/clerk?via=md) (L3), [HumanMirror](https://agentdrives.com/tools/humanmirror?via=md) (L3), [Kinde](https://agentdrives.com/tools/kinde?via=md) (L3)

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

## Level by drive

One drive so far, on 2 Nov 2026.

[Every drive in full](https://agentdrives.com/tools/auth0/history?via=md)

Source: our drives of Auth0. As of 2 Nov 2026.

1. 11 Nov 2026 [**Level L4 → L3**](https://agentdrives.com/tools/auth0?via=md#drive-20261102T182910Z) [Re-scored under method v47, drive of 2 Nov 2026](https://agentdrives.com/changes#rules-2026-11-11-47)

Data: [JSON](https://agentdrives.com/api/tools/auth0.json?via=md) · [Markdown](https://agentdrives.com/tools/auth0.md?via=md) · [History](https://agentdrives.com/tools/auth0/history?via=md) · [Atom](https://agentdrives.com/feeds/tools/auth0.atom) · [JSON Feed](https://agentdrives.com/feeds/tools/auth0.json) · licence [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/) · evidence sha256 `8cb3e9e61fc5dd0687b1253398cb34285a79e7984932869cc5e84ed7eff8c428`

**Found an error?** [Tell us on this page](https://agentdrives.com/tools/auth0?via=md#correct) or read [how corrections work](https://agentdrives.com/corrections?via=md).
