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

Scalekit AgentKit vs Stytch Connected Apps

Scalekit AgentKit scores 74.7 (BB) on agent readiness against Stytch Connected Apps's 65 (B), and leads in 4 of 7 scored categories. Stytch Connected Apps leads on security & auth. Both do oauth for agents.

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

Which one, for what

Scalekit AgentKit BB

Best for A team that wants per-user third-party tokens plus a hosted tool catalogue at the lowest per-call price, with a tidy virtual MCP surface for agents.

Ahead on

  • Schema & documentation, 87 against 64
  • Agent ergonomics, 88 against 65
  • Payments & pricing, 60 against 30

Also in its favour

  • Agent-ready, a grade of BB or better
  • Free to start without a card

Watch for

No published rate-limit figure and no idempotency keys for Scalekit's own API

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

  • Security & auth, 76 against 66

Also in its favour

  • Rated higher by the reviewer agents, 3.0 against 2.5 out of 5

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 Scalekit AgentKit +30

Scalekit AgentKit 60

No x402, MPP or L402 (0). Per-call price published, $0.50 per 1,000 tool calls above 100,000 on Growth, and $3 per 1,000 trigger events above 50,000 (20). Free tier of 10,000 tool calls and 10,000 trigger events a month with no card, up from 5,000 tool calls on 1 October (20). A person creates an account and copies API credentials from the dashboard (0). 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 Scalekit AgentKit +23

Scalekit AgentKit 87

OpenAPI 3.1.1 files for AgentKit alone (42 paths on 1 November) and for all endpoints, at docs.scalekit.com/api/agentkit.scalar.json (25). llms.txt with full and small variants, and a Markdown twin for each page (10). Connector pages and the API reference say what each endpoint and connector type is for (15). Filters are typed and constraints stated, for example a search query of at least 3 characters, top_k up to 50 and MCP session tokens from 60 seconds to 24 hours (13). Status codes 400, 401, 403, 404, 409 and 500 are documented, but many response examples are null placeholders (9). Versioned under /api/v1, with a dated product updates page whose newest AgentKit entry is 1 October 2026, and a CHANGELOG in the Node SDK since 9 October (15).

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 Scalekit AgentKit +23

Scalekit AgentKit 88

Scoped tool lists, tool search with top_k and virtual MCP servers that expose only the tools you choose keep context small (25). page_size and page_token on list endpoints, with filters by user, organisation, connector and connection name (20). Documented status codes, connected-account states (ACTIVE, EXPIRED, PENDING_AUTH and others), a magic-link route to reauthorise, and typed SDK exceptions carrying toolErrorCode and executionId (18). No idempotency keys. The errors page now says a retried tool call can run twice and to retry only tools that are safe to repeat, and a duplicate create returns 409 (10 of 20, as DeepL's stateless calls with backoff guidance and no idempotency key are read). Official Node and Python SDKs and few required fields (15).

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).

Security & auth Stytch Connected Apps +10

Scalekit AgentKit 66

Your backend trades a client ID and secret for a short-lived bearer token, and virtual MCP session tokens are per user with a one-hour default, but GET /api/v1/connected_accounts/auth returns a user's full OAuth tokens to any holder of the API credential (26). Virtual MCP servers expose a chosen tool subset per user, but we found no approval step for destructive tools (12). execute_tool returns third-party content and we found no prompt-injection guidance (5). The trust centre says 'Every login, token, and session event' is queryable in Auth Logs, SIEM streaming exists since 9 July 2026, and each tool call returns an executionId. We found no AgentKit-specific audit log (8 of 15). The trust centre states SOC 2 Type 2 and ISO 27001 certification without dates, annual third-party penetration tests and a disclosure address, security@scalekit.com. /.well-known/security.txt returns 404 and we found no bug bounty (15 of 20).

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).

Score by category

CategoryWeightScalekit AgentKitStytch Connected AppsEdge
Reliability16%7273Stytch Connected Apps +1
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%8764Scalekit AgentKit +23
Agent ergonomics13%8865Scalekit AgentKit +23
Security & auth14%6676Stytch Connected Apps +10
Payments & pricing10%6030Scalekit AgentKit +30
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8076Scalekit AgentKit +4
Transparency & trust7%6666even
Negative events≤1500
TotalBB 74.7/100B 65/100

Facts side by side

FactScalekit AgentKitStytch Connected Apps
KindHTTP APIHTTP API
VendorScalekitStytch (Twilio)
Hosted endpointhttps://{env}.scalekit.comhttps://api.stytch.com
TransportsHTTP, Streamable HTTPHTTP
AuthOAuth or keyOAuth or key
PricingFreemiumFreemium
x402nono
LicenceMIT (SDKs), platform closed, self-hosted on EnterpriseMIT (SDKs), platform closed
Read-only variant documentednono
llms.txtyesyes
Last release2026-10-302026-10-26
Terms last updated2026-01-012026-07-16
Privacy policy last updated2026-01-012026-04-09
Customer content may train modelsnot found in the textnot found in the text
Terms restrict automated accessyesnot found in the text
Terms restrict benchmarkingyesnot found in the text
Terms or service can change without noticenot found in the textnot found in the text
Arbitration or class-action waiveryesyes
Popularity6 stars, 11k npm/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

Scalekit AgentKit

600+ connectors, including remote MCP servers over OAuth 2.1 with DCR, and a free tier of 10,000 tool calls a month without a card. Scalekit's own rate limit has no published figure, and tool calls take no idempotency key.

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

Scalekit AgentKit

  1. Use the exact dashboard Connection Name, not the connector slug, in every call
  2. Call POST /api/v1/tools:search with top_k instead of listing every tool
  3. When a connected account isn't ACTIVE, send the user the magic link and stop until they finish
  4. On a 429, read error_code (RATE_LIMITED is Scalekit, TOOL_ERROR is the app), back off 1, 2 then 4 seconds, and log the executionId
  5. Mint a fresh virtual MCP session token per user per run and let it expire
  6. Retry a failed tool call only when the tool is safe to repeat, since a retry can run it twice

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, Scalekit AgentKit or Stytch Connected Apps?

Scalekit AgentKit scores 74.7 (BB) on agent readiness against Stytch Connected Apps's 65 (B), and leads in 4 of 7 scored categories. Stytch Connected Apps leads on security & auth.

Do Scalekit AgentKit and Stytch Connected Apps need an API key?

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

Can an agent call Scalekit AgentKit and Stytch Connected Apps without installing anything?

Yes. Scalekit AgentKit has a hosted endpoint at https://{env}.scalekit.com and Stytch Connected Apps at https://api.stytch.com.

Other comparisons with Scalekit AgentKit 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.