Can an AI agent use Arcade?

Arcade is an MCP gateway for running tools such as calculators and apps on behalf of users, with a REST API and a CLI.

arcade.devMCP gateways

Driven 7 Nov 2026

Evidence sha256 3ac99f91JSONMarkdownFeedCite

L3

Does the work

  1. L0
  2. L1
  3. L2
  4. L3
  5. L4
  6. L5

Rank among the 246 products we drove

Core work done
tied #1
100%
8 of 8 core tasks
Time to get in
tied #42
4minutes
Getting in on its own
Holds up
tied #65
75/ 100
Reliability under errors
Steps on its own
tied #35
3/ 5
Find to Leave, no person

Yes. Our agent signed up for Arcade on its own in a browser with an email and password, 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 browser4 minutes
Got as far as
Pay: reaches the checkoutA card form for $25 a month

Connects by

MCP, API, CLI

Agent payments

None found

  1. Find

    On its own · 322 doc pages read

    Docs it can act on: llms.txt, an OpenAPI and an MCP server.

  2. Get in

    On its own · 4 minutes

    MCP sign-in, sign-up in a browser.

  3. Use

    On its own · 8 of 8 core tasks

    Did: search the tool catalog and fetch tool definitions in OpenAI and Anthropic formats; run a tool for a user and read the run back from the history.

  4. PayFirst stop

    Partly

    Reaches the checkout. A card form for $25 a month.

  5. Leave

    Partly

    Nothing to cancel. Its account stays.

  • On its own
  • Partly

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

Checked 18 Nov 2026: MCP server asks for a sign-in, sign-up page, llms.txt and OpenAPI unchanged since the check before.

Find

How an agent connects

MCP, API, OpenAPI, CLI and llms.txt found.

  • MCP server

    All tested

    Official server. Site MCP (4 read-only tools, no auth); per-project gateways with OAuth (CIMD/DCR, PKCE), 7-9 tools when driven. Sign‑in needed to see its tools.

    api.arcade.dev/mcp/arcade

    10 tools mapped in our drive

  • API

    58 of 60 tested

    REST at api.arcade.dev, OpenAPI 3.0.0.

    60 operations mapped in our drive

  • OpenAPI

    Yes

    A machine-readable description of the API.

  • CLI

    27 of 28 tested

    arcade-mcp 1.17.3 on PyPI: login, new, deploy, server, secret, evals, and more.

    28 commands mapped in our drive

  • SDK

    None found
  • llms.txt

    Yes
  • Agent payments

    None found

    Reached the card form and stopped: Growth, $25 a month. It checks out through a Stripe card form. 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.

    6 of 8 documented ways to do the core work worked.

    docs.arcade.dev/en/home

    322 of 384 pages read

Get in

Getting in

Our agent tried 3 of 9 ways in; 3 worked without a person.

The way that worked

Sign-up in a browser4 minutes

  • An inboxNeeded
  • A browserNeeded
  • A personNot needed
  • Agent on a serverAPI, MCP, CLINoStops at sign-up: it works only in a browser.
  • Assistant in its own browserLike ChatGPT agentPartlySigns up, confirms its email and does all of the core work, then stops: its account stays. It can't delete its account.
  • Signed agentKnown to CloudflareYesThe sign-up page opens.

Every way in

Every way in and what happened
Way inWhat happenedWhy
Sign-up in a browserWorked
MCP sign-inWorked
Sign-up in a browserWorkedPart of the work done
Runs locally, no accountNot triedNot part of this drive
Continue with GitHubNot triedNot part of this drive
Continue with GoogleNot triedNot part of this drive
Continue with MicrosoftNot triedNot part of this drive
Company single sign-onNot triedNeeds a person's account
A key from a personNot triedThe same as another way

Use

What an agent can do with Arcade

All 8 core tasks done, and 15 of 20 others.

Core tasks

  • done there
Core tasks of Arcade: the result and the surfaces they went through
TaskResultThrough
Run a tool action on behalf of a userDoneAPI: done thereMCP: done there
Authorize a user's account for a tool (OAuth consent)DoneAPI: done there
Browse and search the tool catalogDoneAPI: done thereMCP: done there
Create a tool gateway that federates selected toolsDoneAPI: done thereMCP: done there
Change or delete a tool gatewayDoneAPI: done there
Build and deploy a custom tool server to ArcadeDoneAPI: done thereCLI: done there
Register a remote tool server in a projectDoneAPI: done there
Add a contextual access hook to enforce policy on tool callsDoneAPI: done there

Surface audit: 105 documented operations: 99 run, 3 blocked by sandbox or plan limits and 3 left out because they spend money or reach real people. Of the 99 run, 90 passed and 9 didn't; 25 behaved differently from the docs. By surface, 58 on the API, 27 in the CLI, 10 on the MCP server and 4 elsewhere, such as sign-in and webhooks.

  • Holds up

    75of 100

    • Reliability83
    • Handles mistakes67

    The mean of the two.

  • Docs match

    68of 100

    • Docs accuracy75
    • Docs completeness50

    Docs accuracy counts 70%, completeness 30%.

  • Surface tested

    88of 100

    90 of 102 passed: the 105 documented operations less the 3 that spend money or reach real people

  • What it can't do, and why

    • Pay for the Growth plan Only a card form in the dashboard; no API or agent payment option.
    • Delete the account No delete control or endpoint; the privacy policy says to email support.
    • Schedule a tool run for later The API refuses it as removed, although the OpenAPI still lists it.
    • Call an LLM through Arcade The documented chat endpoint answers 404.
    • Deploy more than one hosted server at a time The free plan refuses a second deployment.
    • Finish OAuth for prebuilt GitHub and Google tools Consent needs a person's GitHub or Google account.

15 of 20 other tasks done

  • Review tool execution historyDone
  • Check a tool's unmet authorization requirementsDone
  • Get tool definitions formatted for an LLMDone
  • Get a user's provider token to call a third-party API directlyDone
  • Add a custom OAuth auth providerDone
  • Store a secret for toolsDone
  • Revoke a user's connected accountDone
  • Set user verification for the auth flowDone
  • Turn on tool recommendation for a gatewayDone
  • Scaffold and run a tool server locallyDone
  • Read a deployed server's logsDone
  • Answer end users' capability requests in the private registryDone
  • Read the audit logDone
  • Count tool calls for usageDone
  • Create an organization or projectDone
  • Configure SSO for the Arcade organizationPaid plan
  • Set a member's role (RBAC)Paid plan
  • Schedule a tool execution for laterThe API refuses it as removed, although the OpenAPI still lists it.Blocked
  • Run evaluations on toolsBlocked
  • Call an LLM through ArcadeBlocked
  • Connect an identity provider for gateway end usersNot tried
  • Self-host Arcade in your own cloud with HelmNot tried

The plans they need

  • Build and deploy a custom tool server to Arcadepaid (free plan allows one managed deployment at a time)

The drive used the free plan.

Tips for agent builders

From this drive

8 tips
  • After sign-up, set up the authenticator-app second factor: the setup key is shown as text, so you can compute TOTP codes yourself.
  • Prefer the MCP gateway at https://api.arcade.dev/mcp/arcade: it supports CIMD and PKCE and needs one consent click.
  • Use the org-scoped paths /v1/orgs/{org}/projects/{project}/plugins and /hooks: the flat /v1/plugins and /v1/hooks in openapi.json answer 404.
  • Run arcade deploy -e src/<pkg>/server.py from the package root, not from the src folder the scaffold's next steps point to.
  • Delete a user connection with its connection_id (ac_...), not the list item's id (at_...).
  • Read tool_executions with the te_ id from the execute response; the tc_ execution_id is refused.
  • When authorizing for a user_id, sign in to the consent browser as that same Arcade user: the default user verification refuses others with user_mismatch.
  • Custom OAuth providers need authorize_request.params with {{client_id}} and {{redirect_uri}}, or the consent fails with unknown_client.

Pay

Paying

Ways to pay checked 7 Nov 2026.

  • ResultPartly. Reaches the checkout. A card form for $25 a month.
  • CheckoutReached the card form and stopped: Growth, $25 a month. It checks out through a Stripe card form. No CAPTCHA at checkout.
  • TrialNo card needed to start.

Leave

Leaving

  • ResultPartly. Nothing to cancel. Its account stays.
  • Its accountNot on its own: blocked. The account stays. Manage my account and the dashboard have no delete control, and the privacy policy says to email support@arcade.dev; mailing a real support desk is outside our rules. Everything we made was removed and both API keys refused afterwards (401), but the login still works.

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; 11 of 11 days

  • llms.txt,

    Found on the newest check; 11 of 11 days

  • MCP server,

    Asks for a sign-in on the newest check; 4 of 11 days

  • OpenAPI,

    Found on the newest check; 11 of 11 days

Compare

How Arcade compares

In MCP gateways

None of the 3 products we drove in MCP gateways is higher; 2 others share L3. As of 7 Nov 2026.

The products we drove in MCP gateways, in the directory's order, with Arcade
ProductLevelFind to leave
Arcade (this page)L3Find: On its own, Get in: On its own, Use: On its own, Pay: Partly, Leave: Partly.
NangoL3Find: On its own, Get in: On its own, Use: On its own, Pay: Partly, Leave: Partly.
ComposioL3Find: On its own, Get in: On its own, Use: On its own, Pay: Partly, Leave: Partly.

For the team behind Arcade

Agents get stuck at Pay

7 things to fix for agents: 4 small, 2 medium and 1 large

One fix can cover several findings.

Agent blockers: 6 foundAgent surfaces: 27 issues found

Get your findings, freeWhat a drive covers

We mail a private link to an address at arcade.dev.

  1. FindClear
  2. Get inClear
  3. UseClear
  4. PayBlocks agents
  5. LeavePartly

Or claim Arcade to see where each issue is and ask for a free drive after a fix.

Want Arcade driven every month? See Watch

On our standard

Best or ahead on 8 of 34 criteria, behind on 6. Each against every product we measured on it.

All 34 criteria
How each criterion is graded

Where Arcade fits

History

Level by drive

One drive so far, on 7 Nov 2026.

Source: our drives of Arcade. As of 7 Nov 2026.
  1. 11 Nov 2026Level L4 → L3Re-scored under method v47, drive of 7 Nov 2026

Read more on this step

Pay is where our agent stopped at Arcade.

Every earlier drive is in the history. The level follows these rules. Data under CC BY 4.0.

Found an error? or read how corrections work.

Questions people ask about Arcade

Can an AI agent create an Arcade account on its own?
Yes, in a browser, without a person. Done by the agent in its own browser at app.arcade.dev/register (account.arcade.dev): email, company, full name, nickname and password, no CAPTCHA (company and name asked; our agent answered). After email verification the dashboard requires a passkey or 2FA. The agent set up an authenticator app: the setup key is shown as text, so it computed the codes itself.
Does Arcade have an MCP server, and can an agent connect to it?
Yes. Arcade has an official MCP server. The server signs an agent in with OAuth. A new agent can get in on its own: in the drive of 7 Nov 2026, our agent signed up, verified and got its key without a person. Through the MCP server, our agent tried 3 tasks and did 3.
How does an AI agent get an Arcade API key?
In the drive of 7 Nov 2026, our agent got its Arcade API key in a browser, without a person. The agent made a project API key on the dashboard's API Keys page in its own browser (the documented route). MCP sign-in (CIMD, PKCE) and arcade login gave OAuth tokens through consent in the agent's browser. Contrary to the docs, arcade login stores a user token, not an API key.
Can an AI agent delete its Arcade account?
Not on its own: blocked. The account stays. Manage my account and the dashboard have no delete control, and the privacy policy says to email support@arcade.dev; mailing a real support desk is outside our rules. Everything we made was removed and both API keys refused afterwards (401), but the login still works.
Can an AI agent pay for Arcade?
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
Plain
AgentDrives, “Arcade: AI agent test drive”, 7 November 2026, https://agentdrives.com/tools/arcade. CC BY 4.0.
APA
AgentDrives. (2026, November 7). Arcade: AI agent test drive. https://agentdrives.com/tools/arcade
BibTeX
@misc{agentdrives_arcade_2026,
  author = {{AgentDrives}},
  title = {Arcade: AI agent test drive},
  year = {2026},
  month = nov,
  url = {https://agentdrives.com/tools/arcade},
  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.