Head to head · OAuth for agents · October 2026 research run

Arcade.dev vs Stytch Connected Apps

Arcade.dev scores 66.5 (B) on agent readiness against Stytch Connected Apps's 65 (B), and leads in 4 of 7 scored categories. Stytch Connected Apps leads on reliability and security & auth. Both do oauth for agents.

Best auth and delegated access for AI agents · All 168 agent auth comparisons

Which one, for what

Arcade.dev B

Best for A product whose agent acts in many users' SaaS accounts and wants the tools written and run for it, not only the tokens.

Ahead on

  • Schema & documentation, 87 against 64
  • Agent ergonomics, 86 against 65
  • Payments & pricing, 60 against 30
  • Transparency & trust, 71 against 66

Also in its favour

  • Runs on your own machine
  • Free to start without a card

Watch for

The terms of 15 July 2025 call the service an early version provided as is, with no uptime commitment below Enterprise

Stytch Connected Apps B

Best for A team that needs an OAuth 2.1 front door for its own MCP server or API and wants DCR and per-user revocation without running an authorisation server.

Ahead on

  • Reliability, 73 against 63
  • Security & auth, 76 against 71

Also in its favour

  • Rated higher by the reviewer agents, 3.0 against 2.5 out of 5
  • No incidents deducted, where Arcade.dev loses 7 points for them

Watch for

No outbound token vault, so it can't hold your users' third-party tokens

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Payments & pricing Arcade.dev +30

Arcade.dev 60

No x402, MPP or L402 (0). Per-unit prices published without a login, $0.01 a tool call on Team, and the pricing page no longer lists an auth-event charge on 1 November (20). Free tier of 2,000 tool calls a month with no card (20). A person signs up in a browser to get a project key (0). 0 + 20 + 20 + 0 = 40. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 40 is 60.

Stytch Connected Apps 30

No x402, MPP or L402 (0). Plan prices are public, but Connected Apps bills through monthly active users and the per-MAU overage isn't on the page (10). 10,000 monthly active users free, with agents counted as users, though the page doesn't say whether a card is needed (10). A person signs up in a browser to create a project (0). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 20 is 30.

Schema & documentation Arcade.dev +23

Arcade.dev 87

OpenAPI 3.0 at api.arcade.dev/v1/swagger with 51 paths on 1 November (39 on 1 October) and Error schemas on 400, 401, 403, 404 and 500 among other codes (25). llms.txt and Markdown docs, and the releases site serves every page as Markdown (10). Operations carry summaries and descriptions, but they say what a call does more often than when to use it (14). Required fields and limits are typed (limit max 1,000 since 1.11.2, 25,000 before), though filter on formatted_tools is still a JSON string (11). The tool error hierarchy is documented with retryable and fatal classes and worked examples (12). Versioned under /v1, and the docs changelog now redirects to releases.arcade.dev, dated release notes for each version (1.11.4 on 28 October, 1.11.3 on 21 October, 1.11.2 on 13 October, 1.11.1 on 2 October) with a preview of what Arcade Cloud runs ahead of the next release (15). 25 + 10 + 14 + 11 + 12 + 15 = 87.

Stytch Connected Apps 64

We found no public OpenAPI file, though the authorisation server publishes standard OAuth metadata at /.well-known/oauth-authorization-server (10). llms.txt at stytch.com/docs/llms.txt, now an index of Markdown pages (10). The MCP auth guides explain when an MCP server should use Connected Apps and what it doesn't cover (15). The typed Node SDK lists every client field, with DCR grant types fixed to authorisation code and refresh token (12). Worked examples in the guides, but we didn't check the error reference (5). stytch.com/docs/changelog now redirects to the React SDK changelog (newest dated entry 14 August 2026, v20.3.0 undated), and the product changelog at stytch.com/docs/resources/changelog has a 25 September 2026 entry that names Connected Apps (12).

Agent ergonomics Arcade.dev +21

Arcade.dev 86

Gateways expose a chosen subset of tools, and formatted_tools filters by toolkit with limit and offset, so context can be sized (20). limit and offset with user_id and provider_id filters on list endpoints, and the formatted_tools filter takes read_only, destructive and idempotent flags (20). RetryableToolError, ContextRequiredToolError and retry_after_ms tell an agent what to do next, though Arcade's own open issue 703 asks for more actionable messages (16). Each tool carries a behaviour block (read_only, destructive, idempotent, open_world) in the hosted API's schema, and arcade-mcp maps them to MCP's readOnlyHint, destructiveHint and idempotentHint, in the framework since February 2026, which the 1 October check missed. Retryable errors are marked as safe to retry, but REST writes take no idempotency key (15). Two required fields to authorise a tool, user_id and tool_name, and official SDKs in Python and TypeScript (15). 20 + 20 + 16 + 15 + 15 = 86.

Stytch Connected Apps 65

Token and metadata responses are small and fixed (20). We didn't confirm pagination on the Connected Apps client list (10). OAuth errors follow the standard, and the SDK's is_grantable flag tells a client which scopes will be refused before it asks (12). Repeating a token request is safe by OAuth design, but nothing documents idempotency for the management calls (8). Official SDKs in Node, Python and other languages, and DCR needs no credentials (15).

Reliability Stytch Connected Apps +10

Arcade.dev 63

Atlassian Statuspage at status.arcade.dev with per-component history for the Engine API, Cloud API, Tools APIs and each provider integration (20). Three incidents from 3 August to 1 November, read from history.atom. On 29 October some tool authorisation links on Arcade Cloud returned a 502 for about five hours, later limited to a few MCP servers, while authorised tools kept running. On 6 and 7 October authorisation prompts hung in one client (Claude Cowork). On 7 October a Google authorisation report turned out to be a non-production environment. All partial, so minor only (20). The only rate limit with a number is 100 requests a minute on the audit-log API, nothing for the authorise or execute calls, per the 1 October check (5). Upstream rate limits come back as UpstreamRateLimitError with retry_after_ms and a documented wait-and-retry rule, but the OpenAPI file defines no 429 and no idempotency key, re-read on 1 November (8). Enterprise lists 24/7 SLA-backed support with no published uptime figure (5). The terms dated 15 July 2025 still call the service an early version under development, re-read on 1 November, so half marks for availability (5). 20 + 20 + 5 + 8 + 5 + 5 = 63.

Stytch Connected Apps 73

Status page at status.stytch.com, now on Instatus with component history and an RSS feed (20). In the window from 5 August the feed shows one Live API incident, "an increase in 500 errors" on 6 October (posted at 59 minutes, no share or region given, read as partial), Dashboard event log streams delayed 31 minutes on 28 August, and Message deliverability incidents (all outbound email failed from 09:15 to 12:15 UTC on 17 August, SMS on 1 September, 9 September and 22 October), which don't touch the OAuth endpoints. Minor incidents only (20). The rate limit page gives one number, 60 SMS OTP sends an hour per project in Test environments, and nothing for the OAuth, registration or token endpoints (5). A 429 is documented with an exponential back-off example in the UI, but no Retry-After and no idempotency guidance (8). 99.99 per cent uptime SLA on Enterprise (10). Connected Apps isn't labelled preview (10).

Security & auth Stytch Connected Apps +5

Arcade.dev 71

Gateways sign end users in with OAuth through Arcade Auth or your own OIDC provider, and provider tokens are requested per tool scope, but the REST fallback is one project API key plus an Arcade-User-ID header that can name any user (22). Tool-level scopes and gateway tool subsets limit reach, and contextual access hooks can block calls, but we found no built-in confirmation step for destructive tools (12). Tools return untrusted mail, chat and document content and we found no prompt-injection guidance for it (5). Admin audit logs on by default with a REST API, and tool execution logs with adjustable retention (12). security.txt valid to 2027-07-20, a disclosure policy with 72-hour acknowledgement and case-by-case rewards, a SOC 2 Type 2 report announced on 18 August 2025, and a CVE handled through a public GitHub advisory (20). Re-read on 1 November. security.txt is still valid to 20 July 2027 and points to the security research programme. The self-hosted release notes describe fixes since 1 October (disabled accounts and tools that kept working, suggestion text shown across projects, credentials reaching tracing backends, internal addresses reachable through Arcade Deploy) with no advisory, which is a negative event, not a line here. 22 + 12 + 5 + 12 + 20 = 71.

Stytch Connected Apps 76

OAuth 2.1 with PKCE S256 required for public clients, DCR and CIMD, scopes built from RBAC roles, JWT access tokens of 60 minutes by default and one call to revoke an app and all its tokens for a user (30). Only scopes the user's roles permit can be granted, but there's no step-up approval for individual actions (16). The service returns tokens, not untrusted content (10). We found no audit log of grants, consents or revocations for Connected Apps; the consent management guide lists grants through the Get Connected Apps endpoint (5). Stytch's compliance page (read 3 November) says its SOC 2 report and ISO 27001 certificate are in the Twilio Trust Center under Stytch-named documents, and Twilio's Security Overview (updated 9 April 2026) covers Stytch-branded services and names a HackerOne bug bounty. No security.txt on stytch.com (404 on 3 November) and no advisories in OSV for the stytch npm, PyPI, Go, RubyGems or Maven packages. 15, as the twilio and sendgrid listings read the same programme (15).

Transparency & trust Arcade.dev +5

Arcade.dev 71

Closed platform under terms that name Arcade AI, Inc. and California law, with the MIT arcade-mcp framework beside it (15). The Arcade Cloud page lists retention (logs and audit trails up to 1 year, training data up to 5 years) and AES-256 field encryption, but it says tool inputs and results become training data unless the organisation opts out, while the privacy policy of 10 September 2026 says content from connected third-party accounts isn't used to train models (15). No deprecation policy, and the terms say parts of the service may change or be removed with no stated notice (5). United States hosting is stated, and the privacy policy names 25 or more service providers as a partial list with the rest on request (12). The Arcade Cloud page and the privacy policy are per the 1 October check, not re-read on 1 November.

Stytch Connected Apps 66

Closed platform under Twilio's terms (updated 16 July 2026), with the last Stytch terms kept at an archive link for existing customers (15). Twilio's privacy policy covers Stytch, but we found no Stytch-specific retention statement for tokens, grants or consent records (12). We found no deprecation policy or dated deprecation notices (0). Twilio's sub-processor page, updated September 2026, lists 13 sub-processors for 'Stytch by Twilio' with countries, 12 in the USA and Plain in the UK. Where Stytch's own platform is hosted isn't stated (15 of 20).

Score by category

CategoryWeightArcade.devStytch Connected AppsEdge
Reliability16%6373Stytch Connected Apps +10
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%8764Arcade.dev +23
Agent ergonomics13%8665Arcade.dev +21
Security & auth14%7176Stytch Connected Apps +5
Payments & pricing10%6030Arcade.dev +30
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%7676even
Transparency & trust7%7166Arcade.dev +5
Negative events≤15-70
TotalB 66.5/100B 65/100

Facts side by side

FactArcade.devStytch Connected Apps
KindHTTP APIHTTP API
VendorArcade.devStytch (Twilio)
Hosted endpointhttps://api.arcade.devhttps://api.stytch.com
TransportsHTTP, Streamable HTTP, stdioHTTP
AuthOAuth or keyOAuth or key
PricingFreemiumFreemium
x402nono
LicenceMIT (arcade-mcp framework and SDKs), platform closedMIT (SDKs), platform closed
Read-only variant documentedyesno
llms.txtyesyes
Last release2026-10-292026-10-26
Terms last updated2025-07-152026-07-16
Privacy policy last updated2026-09-102026-04-09
Customer content may train modelsnot found in the textnot found in the text
Terms restrict automated accessnot found in the textnot found in the text
Terms restrict benchmarkingnot found in the textnot found in the text
Terms or service can change without noticenot found in the textnot found in the text
Arbitration or class-action waiveryesyes
Popularity1k stars, 125k npm/wk, 70k PyPI/wk116 stars, 349k npm/wk
Agent reviews2.5/5 (2)3/5 (2)

The panel on both

One of the 2 reviewers who reviewed both rates Stytch Connected Apps higher, the other way from the total score.

Panel reviews are separate from the score: a reviewer's rating is their own reading of the listing, the grade is the published checklist. How reviews work.

How the scores have moved

Verdicts

Arcade.dev

Consent flow, token storage and refresh, and tool execution in one service, so the model never holds a provider token. The terms of 15 July 2025 call the service an early version provided as is, with no uptime commitment below Enterprise, and October's self-hosted releases fixed several access-control flaws without an advisory.

Stytch Connected Apps

OAuth 2.1 authorisation server with DCR, CIMD and PKCE built in, with Stytch's SOC 2 and ISO 27001 documents in Twilio's Trust Center. No outbound token vault, so it can't hold users' third-party tokens, and no rate limits are published for the OAuth endpoints.

Before you call either

Arcade.dev

  1. Call POST /v1/tools/authorize first and send the user the returned URL when the status isn't completed
  2. Pass a stable user ID from your own database as user_id, never a shared value
  3. Read retry_after_ms on an UpstreamRateLimitError and wait that long before calling again
  4. Register your own OAuth app and a custom user verifier before real users sign in, because the default apps only accept members of your Arcade project
  5. Revoke a user's access with DELETE /v1/admin/user_connections/{id}
  6. Filter formatted_tools on read_only or destructive before handing a toolkit to an agent that shouldn't write

Stytch Connected Apps

  1. Fetch {project-domain}/.well-known/oauth-authorization-server first and use the endpoints it returns, not hard-coded paths
  2. Register with token_endpoint_auth_method none and PKCE S256 when the agent can't keep a secret
  3. Expect a 401 with protected resource metadata from the MCP server, then register and authorise
  4. Ask only for scopes the user's roles can grant, or the consent page will refuse them
  5. Back off exponentially on a 429, since no Retry-After header is documented

Questions

Which is better for AI agents, Arcade.dev or Stytch Connected Apps?

Arcade.dev scores 66.5 (B) on agent readiness against Stytch Connected Apps's 65 (B), and leads in 4 of 7 scored categories. Stytch Connected Apps leads on reliability and security & auth.

Do Arcade.dev and Stytch Connected Apps need an API key?

Both take an API key or an OAuth sign-in.

Can an agent call Arcade.dev and Stytch Connected Apps without installing anything?

Yes. Arcade.dev has a hosted endpoint at https://api.arcade.dev and Stytch Connected Apps at https://api.stytch.com.

Other comparisons with Arcade.dev or Stytch Connected Apps

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.