Can an AI agent use HumanMirror?
HumanMirror sells safety checks and small data tools for AI agents.
Rank among the 246 products we drove
- Time to get in
- tied #29
- 3minutes
- Getting in on its own
- Core work done
- tied #74
- 75%
- 6 of 8 core tasks
- Steps on its own
- tied #86
- 2/ 5
- Find to Leave, no person
Yes. Our agent signed up for HumanMirror on its own over its API, got an API key and used its API and MCP server. No CLI found. It offers agents a way to pay: x402.
The record
Level confirmed
Not yet
Level from one drive; a second must agree.
- Got in by
- Key by API3 minutes
- Got as far as
- Leave: can't delete its accountCan pay on its own
Connects by
MCP, API
Agent payments
x402; our agent used it
Partly · 12 doc pages read
Docs with gaps: no getting-started page; has llms.txt, an OpenAPI and an MCP server. The level doesn't rest on Find: it counts getting in, using, paying and leaving.
On its own · 3 minutes
Key by API. Pay per call: stopped by a card.
Partly · 6 of 8 core tasks
Did: find the right HumanMirror service for a need, for free; remove duplicate records from a list of data. 2 not done, among them: repair broken JSON.
On its own · 1 way for agents to pay
Valid x402 payment challenge: $0.001 a call.
Partly
Nothing to cancel. Its account stays. No such route was found; erasure is requested by mail.
- Partly
- On its own
To reach L4: Do 80% of the core work (now 75%) and delete its account, so its keys and login stop working.
See how it ranks among auth providers for agents.
Own HumanMirror? 6 things to fix. Get your findings, free
Checked 17 Nov 2026: MCP server answers, 15 tools, x402 payment challenge valid, sign-up page, llms.txt and OpenAPI unchanged since the check before.
Find
How an agent connects
MCP, API, OpenAPI, agent payments and llms.txt found.
MCP server
6 of 16 testedOfficial server. Two servers on 28 Jul 2026 (x402 catalog 1.5.0 and One 1.0.2), no auth for discovery.
16 tools mapped in our drive
1 tool listed without signing in
API
89 of 177 testedREST JSON, Bearer trial keys and x402 v2 per-call payments.
177 operations mapped in our drive
OpenAPI
YesA machine-readable description of the API.
CLI
None foundSDK
Unknownllms.txt
YesAgent payments
Yesx402 (Base).
Plan and price: Nexus 5000-credit pack, €9.99. It offers x402 payment.
Docs
Some gapsCovers auth.
Code examples on only some pages.
No getting started or error codes.
Describes each operation only in part: completeness 53 of 100.
4 of 17 documented ways to do the core work were tried, and 2 of them worked.
12 pages read
MCP tools
humanmirror_flow
Read without signing in on 3 Nov 2026
Get in
Getting in
Our agent tried 2 of 4 ways in; 1 worked without a person.
The way that worked
Key by API3 minutes
- An inboxNot needed
- A browserNot needed
- A personNot needed
- Agent on a serverAPI, MCP, CLIPartlySigns up, gets an API key, makes its first API call and does 6 of its 8 core tasks, then stops: the rest needs a paid plan. It can't delete its account.
- Assistant in its own browserLike ChatGPT agentPartlySigns up and does 6 of its 8 core tasks, then stops: the rest needs a paid plan. It can't delete its account.
- Signed agentKnown to CloudflareYesThe site opens.
Every way in
| Way in | What happened |
|---|---|
| Key by API | Worked |
| No key needed | Not reached |
| Pay per call | Stopped by a card |
| Try first, claim later | Not tried |
Use
What an agent can do with HumanMirror
6 of 8 core tasks done, and 18 of 24 others.
Core tasks
- done there
- tried, not done
- offered, not tried
| Task | Result | Through |
|---|---|---|
| Run a Safe Preflight check on an agent action | Done | API: done thereMCP: offered, not tried |
| Find the smallest matching capability for a need | Done | API: done thereMCP: done there |
| Issue an execution receipt after an agent action | Done | API: done thereMCP: offered, not tried |
| Execute a verified deterministic Outcome | Done | API: done thereMCP: offered, not tried |
| Deduplicate JSON records | Done | API: done thereMCP: offered, not tried |
| Run a 2-3 step verified Flow mission | Done | API: done thereMCP: offered, not tried |
| Clean and normalise an invalid JSON agent response | Partly | API: tried, not doneMCP: offered, not tried |
| Run an Enterprise Guard preflight with a spend policyThey need a paid plan or a EUR 299 purchase. | Paid plan, not counted | API: tried, not done |
| Order an Agent Safety Audit of one workflowThey need a paid plan or a EUR 299 purchase. | Paid plan, not counted | Web app: offered, not tried |
| Get an ALLOW / REVIEW / BLOCK verdict for one action | Blocked | API: offered, not triedMCP: tried, not done |
Surface audit: 202 documented operations: 99 run, 12 blocked by sandbox or plan limits and 91 left out because they spend money or reach real people. Of the 99 run, 89 passed and 10 didn't; 26 behaved differently from the docs. By surface, 89 on the API, 6 on the MCP server and 4 elsewhere, such as sign-in and webhooks.
Holds up
75of 100
- Reliability100
- Handles mistakes50
The mean of the two.
Docs match
55of 100
- Docs accuracy56
- Docs completeness53
Docs accuracy counts 70%, completeness 30%.
Surface tested
80of 100
89 of 111 passed: the 202 documented operations less the 91 that spend money or reach real people
What it can't do, and why
- Repair broken JSON The tool returned the broken text unchanged and still charged a credit.
- Run Enterprise Guard checks or order the safety audit They need a paid plan or a EUR 299 purchase.
- Revoke a key or delete the account No such route was found; erasure is requested by mail.
- Test the pay-per-call routes Our own payment signer had reached its daily limit.
18 of 24 other tasks done
- Scan a payload for leaked secretsDone
- Normalise entity identifiersDone
- Detect anomalies in a numeric seriesDone
- Score data quality against a thresholdDone
- Quality-gate an AI output before it shipsDone
- Detect breaking JSON contract changesDone
- Infer a JSON contract from a payloadDone
- Issue a Trace verification receiptDone
- Verify a Trace receipt against a payloadDone
- Preflight a destructive operation with CircuitDone
- Search the Nexus tool catalogDone
- Route a tool call through NexusDone
- Sanitise untrusted agent contextDone
- Get free payment-rescue advice for a lost paid responseDone
- Qualify a mission in the OmniDome Mission DeskDone
- Discover OmniDome Commons capabilitiesDone
- Read the credit balanceDone
- Read live Execution Market stateDone
- Analyse a dataset with OraclePaid plan
- Publish a best-execution request on the Execution MarketBlocked
- Submit a provider bid on the Execution MarketBlocked
- Persist or recall shared inter-agent contextBlocked
- Check x402 payment compatibility before payingBlocked
- Create a referral linkBlocked
- Buy a credit packNot tried
The plans they need
- Create a referral link
The drive used the no-card trial.
Tips for agent builders
- Start with POST /api/solve/ or the x402 MCP match tool to pick a service id, then run it through POST /api/nexus/call/ with the trial key instead of paying per x402 call.
- Paths in the OpenAPI specs lack trailing slashes; the live API 308-redirects, so call the slashed path.
- Many request bodies are undocumented: read the error code (objective_required, challenge_id_required) and add the named field.
- A 200 can still carry ok:false; check the ok field, not only the status.
- Failed Outcomes are refunded (charged_credits 0); retrying is cheap.
Pay
Paying
Ways to pay checked 15 Nov 2026.
- ResultOn its own. Valid x402 payment challenge: $0.001 a call.
- CheckoutPlan and price: Nexus 5000-credit pack, €9.99. It offers x402 payment.
- Ways to pay
- x402 (on its own domain · Base)
Leave
Leaving
- ResultPartly. Nothing to cancel. Its account stays. No such route was found; erasure is requested by mail.
- Its accountNot on its own: blocked. No delete or revoke route was found in the 8 OpenAPI specs, the MCP tools or llms.txt; DELETE on the Nexus and OmniDome endpoints answered 405. The privacy page sends erasure requests by mail to privacy@humanmirror.fr, which our agent may not write to. Still there: the Nexus trial key, the Forge trial key, the OmniDome agent identity and key, and the OmniDome child agent.
Daily checks
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; 3 of 3 days
llms.txt,
Found on the newest check; 3 of 3 days
MCP server (15 tools),
Answers on the newest check; 3 of 3 days
OpenAPI,
Found on the newest check; 3 of 3 days
Payment challenge (x402),
Valid on the newest check; 3 of 3 days
Compare
How HumanMirror 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.
| Product | Level | Find to leave |
|---|---|---|
| FusionAuth | L4 | Find: On its own, Get in: On its own, Use: On its own, Pay: Not tried, Leave: On its own. |
| PropelAuth | L1 | Find: On its own, Get in: Stopped, Use: Not reached, Pay: Not reached, Leave: Not reached. |
| SuperTokens | L4 | Find: On its own, Get in: On its own, Use: On its own, Pay: Partly, Leave: On its own. |
| Clerk | L3 | Find: On its own, Get in: On its own, Use: On its own, Pay: Not tried, Leave: Partly. |
| WorkOS | L3 | Find: On its own, Get in: On its own, Use: On its own, Pay: Not tried, Leave: Partly. |
| Auth0 | L3 | Find: On its own, Get in: On its own, Use: On its own, Pay: Stopped, Leave: Partly. |
| Kinde | L3 | Find: On its own, Get in: On its own, Use: On its own, Pay: Partly, Leave: Partly. |
| HumanMirror (this page) | L3 | Find: Partly, Get in: On its own, Use: Partly, Pay: On its own, Leave: Partly. |
| Web3Auth (MetaMask Embedded Wallets) | L3 | Find: Partly, Get in: On its own, Use: Partly, Pay: Partly, Leave: Partly. |
For the team behind HumanMirror
Agents get stuck at Leave
6 things to fix for agents: 4 small and 2 medium
One fix can cover several findings.
Agent blockers: 4 foundAgent surfaces: 26 issues found
Get your findings, freeWhat a drive covers
We mail a private link to an address at humanmirror.fr.
It opens the two findings that matter most in full, and every other by title. There is nothing to sign in to.
- FindPartly
- Get inClear
- UsePartly
- PayClear
- LeaveBlocks agents
Or claim HumanMirror to see where each issue is, read your safety findings with their fixes and ask for a free drive after a fix.
Want HumanMirror driven every month? See Watch
On our standard
Best or ahead on 11 of 33 criteria, behind on 9. Each against the products we measured on it.
- Pages fit one fetchThe best result All 7 others (auth and identity products) lower.
- An agent payment rail on the coreThe best result All 8 others (auth and identity products) lower.
- A plan an agent can buy by APIThe best result All 6 others (auth and identity products) lower.
- Structured resultsAhead of 4 of 5 others (auth and identity products), 1 the same.
- Prices an agent can readBehind 6 of 7 others (auth and identity products), 1 the same.
- Export before leavingBehind 6 of 7 others (auth and identity products), 1 the same.
- Docs an agent can navigateThe lowest result All 7 others (auth and identity products) higher.
- Real status codesThe lowest result All 7 others (auth and identity products) higher.
All 33 criteria
- A request id on every answerAhead of 5 of 7 others (auth and identity products), 2 the same.
- A path written for agentsAhead of 4 of 7 others (auth and identity products), 3 the same.
- A person can claim what the agent madeAhead of 13 of 23 others (every product), 10 the same.
- A tool list that fitsAhead of 48 of 91 others (every product), 43 the same.
- Answers sized for an agentTied for the best result 2 of 4 others (auth and identity products) the same, 2 lower.
- Errors a program can readTied for the best result 3 of 6 others (auth and identity products) the same, 3 lower.
- The best way in is built for agentsLevel with 4 of 7 others (auth and identity products), 3 lower.
- Results sized for a context windowAhead of 3 of 5 others (auth and identity products), 1 the same, 1 higher.
- Retried payments charge once, with a receiptLevel with 18 of 30 others (every product), 8 lower, 4 higher.
- A way in with no personLevel with 7 of 8 others (auth and identity products), 1 lower.
- Tool names that sort themselvesLevel with 85 of 91 others (every product), 6 lower.
- llms.txt that worksLevel with 6 of 8 others (auth and identity products), 1 lower, 1 higher.
- Fast to the first callThe same as all 6 others (auth and identity products).
- Terms allow an agent's accountThe same as all 8 others (auth and identity products).
- Errors say what to do nextThe same as all 6 others (auth and identity products).
- WebMCP tools on the web appThe same as all 5 others (auth and identity products).
- Spend an agent can see and capLevel with 6 of 7 others (auth and identity products), 1 higher.
- Agents pick the right toolLevel with 72 of 91 others (every product), 19 higher.
- Every way in works for an agentLevel with 5 of 7 others (auth and identity products), 2 higher.
- Delete by API, checkedLevel with 4 of 7 others (auth and identity products), 3 higher.
- Limits known before they hitTied for the lowest result 2 of 4 others (auth and identity products) the same, 2 higher.
- Versions an agent can pinBehind 3 of 5 others (auth and identity products), 2 the same.
- Truthful annotationsBehind 68 of 91 others (every product), 23 the same.
- Descriptions that say when to use the toolBehind 70 of 91 others (every product), 21 the same.
- Typed, tight input schemasBehind 75 of 91 others (every product), 16 the same.
Where HumanMirror fits
- Standards
- Topics
- MCP serversFind step
- Docs and llms.txtFind step
- MCP sign-inGet in step
- Sign-upGet in step
- MCP and APIUse step
- Card checkoutPay step
- Delete the accountLeave step
History
Level by drive
One drive so far, on 15 Nov 2026.
One drive so far.
Read more on this step
Leave is where our agent stopped at HumanMirror.
- Finding · 18 Nov 2026Agents can't leave43 of the 96 products where our agent got as far as deleting its account gave it no way to do it on its own.Read
- Guide · 18 Nov 2026Let AI agents delete the account they openedA delete call for the account, a clear answer when it's done, and the same in the settings for people.Read
- Guide · 9 Nov 2026Agent experience (AX): what it is, measured at 246 productsAs 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.Read
Every earlier drive is in the history. The level follows these rules. Data under CC BY 4.0.
Found an error? Tell us on this page or read how corrections work.
Questions people ask about HumanMirror
- Can an AI agent create a HumanMirror account on its own?
- Yes, over the API, without a browser. OmniDome agent registration and a Forge trial key also without a browser.
- Does HumanMirror have an MCP server, and can an agent connect to it?
- Yes. HumanMirror has an official MCP server. A new agent can get in on its own: in the drive of 15 Nov 2026, our agent signed up and got its key without a person. Through the MCP server, our agent tried 3 tasks and did 2.
- How does an AI agent get a HumanMirror API key?
- In the drive of 15 Nov 2026, our agent got its HumanMirror API key over the API, without a browser or a person. The trial POST returns an hm_nexus_ Bearer key in its 201 body and it works at once; no route to create a scoped key or to revoke or rotate one in any spec.
- Can an AI agent delete its HumanMirror account?
- Not on its own: blocked. No delete or revoke route was found in the 8 OpenAPI specs, the MCP tools or llms.txt; DELETE on the Nexus and OmniDome endpoints answered 405. The privacy page sends erasure requests by mail to privacy@humanmirror.fr, which our agent may not write to. Still there: the Nexus trial key, the Forge trial key, the OmniDome agent identity and key, and the OmniDome child agent.
- Can an AI agent pay for HumanMirror?
- Yes. Valid x402 payment challenge: $0.001 a call.
Cite this page
The page as a reference, in plain text, APA and BibTeX.
Cite this
AgentDrives, “HumanMirror: AI agent test drive”, 15 November 2026, https://agentdrives.com/tools/humanmirror. CC BY 4.0.
AgentDrives. (2026, November 15). HumanMirror: AI agent test drive. https://agentdrives.com/tools/humanmirror
@misc{agentdrives_humanmirror_2026,
author = {{AgentDrives}},
title = {HumanMirror: AI agent test drive},
year = {2026},
month = nov,
url = {https://agentdrives.com/tools/humanmirror},
note = {Agent test drive, CC BY 4.0},
}Something wrong on this page?
We check it against the drive and correct the page, with the date.