Rank among the 246 products we drove
- Time to get in
- tied #13
- 2minutes
- Getting in on its own
- Steps on its own
- tied #3
- 4/ 5
- Find to Leave, no person
- Core work done
- tied #1
- 100%
- 8 of 8 core tasks
Yes. Our agent got into Axiom on its own, got an API key and used its API, MCP server and CLI.
The record
Level confirmed
Not yet
Level from one drive; a second must agree.
- Got in by
- Sign-up in a browser2 minutes
- Got as far as
- Pay: reaches the checkoutA card form for $25 a month
Connects by
MCP, API, CLI, SDK
Agent payments
None found
On its own · 600 doc pages read
Docs it can act on: llms.txt, an OpenAPI and an MCP server.
On its own · 2 minutes
Try first, claim later, MCP sign-in, sign-up in a browser.
On its own · 8 of 8 core tasks
Did: create datasets, send events and search them by API, MCP or command line; build dashboards and alert monitors and get an alert email.
Partly
Reaches the checkout. A card form for $25 a month.
On its own · 24 hours, then gone
Nothing to cancel. What it made expires.
- On its own
- Partly
To reach L5: Pay without a person.
See how it ranks in the observability category.
Own Axiom? 8 things to fix. Get your findings, free
Checked 18 Nov 2026: MCP server asks for a sign-in, llms.txt and OpenAPI unchanged since the check before.
Find
How an agent connects
MCP, API, OpenAPI, CLI, SDK and llms.txt found.
MCP server
34 of 38 testedOfficial server. 39 tools when driven, 7 prompts, the 28 Jul 2026 MCP spec.
38 tools mapped in our drive
28 tools named in its docs
API
94 of 106 testedREST v1 and v2 plus edge ingest, query and HEC APIs.
106 operations mapped in our drive
OpenAPI
Yes5 specs: v1 3.0.1, v2 and edge 3.0.0.
CLI
21 of 23 testedaxiom 0.21.0.
23 commands mapped in our drive
SDK
All tested@axiomhq/js 2.0.0.
14 methods mapped in our drive
llms.txt
YesAgent payments
None foundReached the card form and stopped: Axiom Cloud, $25 a month. It checks out through Stripe Checkout. An invisible bot check loaded at checkout. It offers Apple Pay and Link.
Docs
In partCovers getting started, auth, error codes and code examples.
Describes each operation only in part: completeness 53 of 100.
15 of 15 documented ways to do the core work worked.
600 of 735 pages read
MCP tools
Read without signing in on 3 Nov 2026
queryDatasetgetSavedQuerieslistDatasetsgetDatasetFieldscreateDatasetlistMetricslistMetricTagsgetMetricTagValuessearchMetricsqueryMetricslistDashboardsgetDashboardexportDashboardcreateDashboardupdateDashboardupdateDashboardChartdeleteDashboardcheckMonitorsgetMonitorgetMonitorHistorylistNotifierscreateMonitorupdateMonitordeleteMonitor
4 more tools20 more toolsShow fewer
searchMetricsqueryMetricslistDashboardsgetDashboardexportDashboardcreateDashboardupdateDashboardupdateDashboardChartdeleteDashboardcheckMonitorsgetMonitorgetMonitorHistorylistNotifierscreateMonitorupdateMonitordeleteMonitorcreateNotifierupdateNotifierdeleteNotifiersendFeedback
Get in
Getting in
3 of 3 ways in worked without a person.
The way that worked
Sign-up in a browser2 minutes
- An inboxNeeded
- A browserNeeded
- A personNot needed
- Agent on a serverAPI, MCP, CLIPartlyWithout an account (try first, claim later) it gets an API key, makes its first API call and does all of the core work, then stops at payment: paying takes a checkout page in a browser.
- Assistant in its own browserLike ChatGPT agentNot checkedSign-up wasn't tried in this drive.
- Signed agentKnown to CloudflareNot checkedNot checked: the robots.txt on app.axiom.co asks crawlers to stay off the sign-up page.
Every way in
| Way in | What happened |
|---|---|
| Sign-up in a browser | Worked |
| MCP sign-in | Worked |
| Try first, claim later | Worked |
- CrawlersThe robots.txt on auth.axiom.co asks crawlers to stay off sign-up. Nothing to fix.
Use
What an agent can do with Axiom
All 8 core tasks done, and 12 of 15 others.
Core tasks
- done there
| Task | Result | Through |
|---|---|---|
| Send event data to Axiom via ingest API or SDK | Done | API: done thereMCP: done thereCLI: done there |
| Query datasets with APL in the query editor | Done | API: done thereMCP: done thereCLI: done there |
| Query data via the REST API | Done | API: done thereMCP: done thereCLI: done there |
| Explore and filter data with the visual query Builder | Done | Web app: done there |
| Live-tail streaming events in the Stream tab | Done | Web app: done there |
| Create and configure dashboards with chart elements | Done | API: done thereMCP: done there |
| Create threshold, match or anomaly monitors for alerting | Done | API: done thereMCP: done there |
| Create and manage datasets, including retention | Done | API: done thereMCP: done thereCLI: done there |
Surface audit: 187 documented operations: 168 run, 12 blocked by sandbox or plan limits and 7 left out because they spend money or reach real people. Of the 168 run, 167 passed and 1 didn't; 4 behaved differently from the docs. By surface, 94 on the API, 34 on the MCP server, 21 in the CLI, 14 in the SDK and 5 elsewhere, such as sign-in and webhooks.
Holds up
82of 100
- Reliability90
- Handles mistakes73
The mean of the two, 81.5, with a half rounded to the even number.
Docs match
84of 100
- Docs accuracy98
- Docs completeness53
Docs accuracy counts 70%, completeness 30%.
Surface tested
93of 100
167 of 180 passed: the 187 documented operations less the 7 that spend money or reach real people
What it can't do, and why
- Create notifiers in an agent-created org The product refuses until a person claims the org.
- Use the service map Not enabled on the free plan.
- Set up roles, single sign-on or directory sync Paid add-ons the drive did not buy.
- Delete an org or account without the web console No such call found in the API specs, CLI or MCP tools.
- Pay for the Cloud plan Only a card checkout exists; we has no card.
12 of 15 other tasks done
- Configure notifiers (Slack, email, webhook, PagerDuty, etc.)Done
- Explore distributed traces in a waterfall viewDone
- Query metrics with MPL against MetricsDBDone
- Generate an APL query from a natural-language descriptionDone
- Use Spotlight to find differences vs baseline dataDone
- Define virtual fields derived at query timeDone
- Save and share queries with team membersDone
- Create views as reusable filtered virtual tablesDone
- Annotate dashboard charts to mark events in timeDone
- Capture GenAI spans with auto-provisioned LLM observability dashboardsDone
- Read the organization's audit logDone
- Create API tokens and personal access tokensDone
- Export a dashboard as a JSON documentPartly
- Set hourly or daily query cost limits for AI agent tokensPartly
- View the service dependency map and its changesPaid plan
- Set Role-Based Access Control permissionsPaid plan
- Configure Single Sign-On (SAML SSO)Paid add-ons the drive did not buy.Paid plan
- Provision users automatically with Directory SyncPaid add-ons the drive did not buy.Paid plan
- Connect third-party integrations (OpenTelemetry, Vector, Cribl, AWS, Vercel, etc.)Not tried
The plans they need
- plan with service map
- Enterprise / RBAC add-on
- Axiom Cloud SSO add-on
- Axiom Cloud Directory Sync add-on
The drive used the free plan (Personal) and an unclaimed agent-created org.
Tips for agent builders
- Start with POST https://api.axiom.co/v2/orgs/provision {} and store the token immediately; it is shown once
- Hand the claimUrl to your human within 24 h or the org and its data are deleted
- Pass MCP documents as JSON strings (monitorJson, notifierJson, dashboardJson)
- Use personal tokens (xapt-) only for /v2/user and /v2/orgs; axiom auth login creates one
- Quote dotted MPL metric names in backticks and pass the time range via startTime/endTime
Pay
Paying
Ways to pay checked 1 Nov 2026.
- ResultPartly. Reaches the checkout. A card form for $25 a month.
- CheckoutReached the card form and stopped: Axiom Cloud, $25 a month. It checks out through Stripe Checkout. An invisible bot check loaded at checkout. It offers Apple Pay and Link.
- TrialNo card needed to start.
Leave
Leaving
- ResultOn its own. Nothing to cancel. What it made expires.
- Its accountYes, over the API, without a browser. The email account was deleted in the console (org first, then account); its PAT is refused afterwards.
Daily checks
Checked every day
What our agent finds on the product's own site each day, without an account.
Sign-up page,
Stopped on the newest check; 17 of 17 days
llms.txt,
Found on the newest check; 17 of 17 days
MCP server,
Asks for a sign-in on the newest check; 17 of 17 days
OpenAPI,
Found on the newest check; 4 of 17 days
Compare
How Axiom compares
In Observability
None of the 2 products we drove in Observability is higher; 1 other shares L4. As of 1 Nov 2026.
| Product | Level | Find to leave |
|---|---|---|
| Axiom (this page) | L4 | Find: On its own, Get in: On its own, Use: On its own, Pay: Partly, Leave: On its own. |
| Sentry | L4 | Find: On its own, Get in: On its own, Use: On its own, Pay: Partly, Leave: On its own. |
For the team behind Axiom
Agents get stuck at Pay
8 things to fix for agents: 4 small, 3 medium and 1 large
One fix can cover several findings.
Agent blockers: 2 foundAgent surfaces: 8 issues found
Get your findings, freeWhat a drive covers
We mail a private link to an address at axiom.co.
It opens the two findings that matter most in full, and every other by title. There is nothing to sign in to.
- FindClear
- Get inClear
- UseClear
- PayBlocks agents
- LeaveClear
Or claim Axiom to see where each issue is, read your safety findings with their fixes and ask for a free drive after a fix.
Want Axiom driven every month? See Watch
On our standard
Best or ahead on 8 of 37 criteria, behind on 4. Each against every product we measured on it.
- A path written for agentsAhead of 140 of 187 others, 47 the same.
- Every way in works for an agentAhead of 134 of 193 others, 59 the same.
- The best way in is built for agentsAhead of 135 of 196 others, 61 the same.
- Docs an agent can navigateAhead of 128 of 187 others, 59 the same.
- One way to page through listsBehind 66 of 114 others, 48 the same.
- Structured resultsBehind 57 of 78 others, 21 the same.
- Agents may read docs, API and sign-upBehind 130 of 160 others, 30 the same.
- Tool names that sort themselvesBehind 86 of 91 others, 5 the same.
All 37 criteria
- Limits known before they hitAhead of 58 of 90 others, 32 the same.
- Spend an agent can see and capAhead of 106 of 159 others, 46 the same, 7 higher.
- A person can claim what the agent madeAhead of 13 of 23 others, 10 the same.
- A way in with no personAhead of 137 of 243 others, 106 the same.
- Sign-in for agents acting for a personLevel with 83 of 158 others, 75 lower.
- Versions an agent can pinLevel with 73 of 127 others, 54 lower.
- Delete by API, checkedIn the middle 46 of 97 others lower, 43 the same, 8 higher.
- Answers sized for an agentLevel with 85 of 116 others, 31 lower.
- Prices an agent can readLevel with 117 of 153 others, 36 lower.
- Errors a program can readLevel with 82 of 145 others, 47 lower, 16 higher.
- No person in the buy pathLevel with 114 of 138 others, 24 lower.
- Export before leavingIn the middle 73 of 189 others lower, 74 the same, 42 higher.
- Fast to the first callLevel with 118 of 135 others, 17 lower.
- Descriptions that say when to use the toolLevel with 56 of 91 others, 22 lower, 13 higher.
- Terms allow an agent's accountLevel with 179 of 189 others, 10 lower.
- Real status codesLevel with 161 of 168 others, 7 lower.
- Errors say what to do nextLevel with 107 of 145 others, 22 lower, 16 higher.
- Typed, tight input schemasLevel with 59 of 91 others, 17 lower, 15 higher.
- llms.txt that worksLevel with 127 of 239 others, 57 lower, 55 higher.
- WebMCP tools on the web appLevel with 133 of 136 others, 3 higher.
- An agent payment rail on the coreLevel with 205 of 216 others, 11 higher.
- A plan an agent can buy by APILevel with 157 of 170 others, 13 higher.
- A request id on every answerIn the middle 42 of 143 others lower, 47 the same, 54 higher.
- Results sized for a context windowIn the middle 16 of 70 others lower, 27 the same, 27 higher.
- Truthful annotationsIn the middle 24 of 91 others lower, 25 the same, 42 higher.
- Agents pick the right toolLevel with 72 of 91 others, 19 higher.
- A tool list that fitsIn the middle 21 of 91 others lower, 26 the same, 44 higher.
- Pages fit one fetchLevel with 118 of 187 others, 69 higher.
- All validation problems at onceLevel with 33 of 57 others, 24 higher.
Where Axiom fits
- Category
- Tasks
- Topics
- MCP serversFind step
- Docs and llms.txtFind step
- MCP sign-inGet in step
- MCP and APIUse step
- Card checkoutPay step
- Delete the accountLeave step
- Rivals
- SentryL4
History
Level by drive
One drive so far, on 1 Nov 2026.
One drive so far.
Read more on this step
Pay is where our agent stopped at Axiom.
- Guide · 18 Nov 2026Let AI agents pay you per call: x402 and MPPx402 or MPP on a paid endpoint, your prices where agents read them, and plans an agent can buy by API or MCP.Read
- Guide · 31 Oct 2026Bot checks on SaaS checkouts: where AI agents stopAs 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.Read
- Guide · 28 Oct 2026Tell an AI agent a feature needs a paid planHow 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.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 Axiom
- Can an AI agent create an Axiom account on its own?
- It needs none: Axiom works without an account. Our agent got into Axiom without signing up. Its way in: Try first, claim later, in under a minute.
- Does Axiom have an MCP server, and can an agent connect to it?
- Yes. Axiom has an official MCP server. The server lists 39 tools and speaks the 28 Jul 2026 MCP spec. A new agent can get in on its own: in the drive of 1 Nov 2026, our agent got working access without signing up. Through the MCP server, our agent tried 11 tasks and did 10.
- How does an AI agent get an Axiom API key?
- In the drive of 1 Nov 2026, our agent got its Axiom API key over the API, without a browser or a person.
- Can an AI agent delete its Axiom account?
- Yes, over the API, without a browser. The email account was deleted in the console (org first, then account); its PAT is refused afterwards.
- Can an AI agent pay for Axiom?
- Partly. Our agent reached a card form for $25 a month. No card needed to start.
Cite this page
The page as a reference, in plain text, APA and BibTeX.
Cite this
AgentDrives, “Axiom: AI agent test drive”, 1 November 2026, https://agentdrives.com/tools/axiom. CC BY 4.0.
AgentDrives. (2026, November 1). Axiom: AI agent test drive. https://agentdrives.com/tools/axiom
@misc{agentdrives_axiom_2026,
author = {{AgentDrives}},
title = {Axiom: AI agent test drive},
year = {2026},
month = nov,
url = {https://agentdrives.com/tools/axiom},
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.