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

Descope Agentic Identity Hub vs Scalekit AgentKit

Descope Agentic Identity Hub scores 80.6 (A) on agent readiness against Scalekit AgentKit's 74.7 (BB), and leads in 3 of 7 scored categories. Scalekit AgentKit leads on schema & documentation, agent ergonomics and maintenance & community. Both do oauth for agents.

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

Which one, for what

Descope Agentic Identity Hub A

Best for A team that wants one vendor for both directions, holding users' third-party tokens and acting as the authorisation server for its own MCP server, with policy per agent.

Ahead on

  • Reliability, 100 against 72
  • Security & auth, 86 against 66

Also in its favour

  • Rated higher by the reviewer agents, 3.1 against 2.5 out of 5

Watch for

No tool catalogue, so you write every provider call yourself

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 78
  • Agent ergonomics, 88 against 80
  • Maintenance & community, 80 against 74

Watch for

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

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.

Reliability Descope Agentic Identity Hub +28

Descope Agentic Identity Hub 100

Instatus page at descopestatus.com with per-component history, including the public API (20). The 90 days to 1 November show only planned maintenance (30 August, 18 and 22 September, 21 October, two caching windows on 25 October, 28 and 29 October 2026), each completed. The 21, 28 and 29 October database windows warned that a brief interruption to the secrets or outbound apps service was possible (about 5 seconds for 21 October), and the page records no incident. Every API region shows 100.0 per cent uptime for September, October and November (30). Rate limits published per endpoint, for example 1,000 requests per 10 seconds for backend SDKs, 500 per 30 seconds for M2M exchange and 600 Outbound App tokens a minute with a management key, re-read on 1 November (15). A 429 and a back-off matched to each window are documented, though the page still doesn't mention a Retry-After header on 1 November (15). A published SLA of 99.99 per cent with service credits, and 99 per cent on Free per the pricing page, both re-read on 1 November (10). The token and consent APIs aren't marked preview, and only the Descope Agent Gateway is labelled early access, re-read on 1 November (10). 20 + 30 + 15 + 15 + 10 + 10 = 100.

Scalekit AgentKit 72

The status page is scalekit.statuspage.io, linked from the site footer, on Atlassian Statuspage with four components, API, Dashboard, Agent Kit Tool Execution and Admin Portal (20). The history page was readable on 1 November. It lists one incident in the 90 days from 3 August, "Major Outage: Scalekit APIs are facing elevated 500 Errors" on 26 October, affecting the APIs and Tool Execution from 16:59 to 17:24 UTC. Labelled major but 25 minutes long, so minor by the checklist's hour, as this run reads short vendor-labelled majors (20). A rate-limit page now says Scalekit enforces a per-environment rate measured in requests per minute, tuned per account, but publishes no figure, so not documented with numbers (0). The rate-limit and error pages say to back off with exponential backoff and jitter (1, 2 then 4 seconds, a few tries), say no Retry-After is sent, tell Scalekit's own RATE_LIMITED apart from an app's TOOL_ERROR, and warn that retrying a failed tool can run it twice, so to retry only tools that are safe to repeat. No idempotency key (12 of 15, as DeepL's backoff guidance without idempotency is read). Enterprise lists a 99.99 per cent uptime SLA on the pricing page (10). No beta labels on the AgentKit endpoints (10). 20+20+0+12+10+10 = 72.

Security & auth Descope Agentic Identity Hub +20

Descope Agentic Identity Hub 86

An agent signs in as its own OAuth client by client credentials, device code, CIBA or RFC 7523 JWT bearer, and Policies limit which tokens it can fetch, while a management key bypasses Policies and the SDK makes you opt in to use one, per the 1 October check, not re-read on 1 November (28). Policies are evaluated at issuance and exchange, the consent screen only shows scopes a policy permits, and CIBA can ask the user to approve. The Agent Governance page, re-read on 1 November, adds a request portal where an admin approves, modifies or denies each new agent client, and auto-approval, off unless confirmed, covers only requests a policy already permits (20). The API returns tokens, not untrusted content (10). Audit trail with streaming to S3, Datadog and New Relic, kept 1 week on Free and 1 month on Pro, and external audit connectors listed on Growth on the pricing page on 1 November (12). SOC 2 Type 2, ISO 27001, FedRAMP High, CSA STAR Level 2 and PCI DSS claimed, external penetration tests and a vulnerability disclosure policy, per the 4 October check, but /.well-known/security.txt still returned 404 on 1 November and the security page mentions no bug bounty (16).

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).

Schema & documentation Scalekit AgentKit +9

Descope Agentic Identity Hub 78

An OpenAPI 3.0 file at docs.descope.com/examples/Descope_API.yaml, with reference pages for each Outbound App token endpoint (25). llms.txt and Markdown docs, re-read on 1 November (10). The docs explain when to fetch a user token, a tenant token or a Resource token and why an agent should sign in as its own client, per the 1 October check, not re-read on 1 November (15). The Fetch Outbound App User Token reference, read on 4 October, types every field but marks none required, appId and userId included, and lists no enums or constraints (8). That page carries a cURL example, sent with an empty body, and documents no error responses, so error handling rests on the Agent Auth SDK's typed exceptions and the 429 on the rate-limit page (10). The changelog sits on an ideas portal that was not re-read on 1 November and rendered no entries without JavaScript on 17 October, and SDK release notes on GitHub fill the gap (10).

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).

Agent ergonomics Scalekit AgentKit +8

Descope Agentic Identity Hub 80

A token fetch returns one token, and the caller can ask for an explicit scope set (20). Tokens are fetched per app, user or tenant, and the management search endpoints page, but there's no list of a user's connections in the agent SDK (15). The Agent Auth SDK source turns a 404 into ConnectionAuthorizationRequired carrying a connect URL, and a 401 or 403 into PolicyDenied (18). Fetching the latest token is safe to repeat and forceRefresh is opt-in, but token deletion can't be undone and has no confirmation (12). Backend SDKs in several languages, with node-sdk 2.20.0 (19 October) and the descope Python package 2.16.1 (22 October) tagged, and few required fields. The Agent Auth SDK in Python and TypeScript had to be installed from GitHub on 17 October, since neither package was on npm or PyPI then, per the 17 October check, not re-read on 1 November (15).

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).

Maintenance & community Scalekit AgentKit +6

Descope Agentic Identity Hub 74

@descope/node-sdk 2.20.0 tagged on 19 October 2026 (DPoP proof validation, multi-text list checks), and the descope Python package 2.16.0 on 19 October and 2.16.1 on 22 October, which requires certifi 2026.10.19 or later to distrust compromised eMudhra CAs (30). Seven node-sdk releases from 7 August to 19 October 2026, 2.14.0 to 2.20.0 (20). Closed platform whose changelog portal didn't render for us on 17 October, and the Agent Auth SDK repository has no commit since 2 July 2026 and had 18 open pull requests, all dependency updates, per the 4 October check (the GitHub API wasn't read on 17 October or 1 November) (8). The backend SDKs are current, but the Agent Auth SDK is 0.1.0, and @descope/agent-auth and descope-agent-auth returned 404 on npm and PyPI on 17 October, while its README and, on 1 November, the docs page give install commands for them. We couldn't reach either registry on 1 November (10). CI and release-please on the Agent Auth SDK, with no publish step and pull requests piling up (6). 30 + 20 + 8 + 10 + 6 = 74.

Scalekit AgentKit 80

scalekit-sdk-node 2.21.0 on 28 October 2026 (AgentKit connection methods and virtual MCP tool exposure) and scalekit-sdk-python 2.23.0 on 30 October (AgentKit triggers) (30). 11 Node and 8 Python SDK releases in the 90 days from 3 August (20). Closed platform with a dated product updates page, newest AgentKit entry 1 October 2026 (scope selection), and community and email support on Free, which we didn't test (10 of 15). Official Node and Python SDKs are current (15). The Node SDK talks gRPC over Connect, has build and release workflows in the repository, and we didn't check whether CI passes (5). 30+20+10+15+5 = 80.

Score by category

CategoryWeightDescope Agentic Identity HubScalekit AgentKitEdge
Reliability16%10072Descope Agentic Identity Hub +28
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%7887Scalekit AgentKit +9
Agent ergonomics13%8088Scalekit AgentKit +8
Security & auth14%8666Descope Agentic Identity Hub +20
Payments & pricing10%6060even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%7480Scalekit AgentKit +6
Transparency & trust7%6866Descope Agentic Identity Hub +2
Negative events≤1500
TotalA 80.6/100BB 74.7/100

Facts side by side

FactDescope Agentic Identity HubScalekit AgentKit
KindHTTP APIHTTP API
VendorDescopeScalekit
Hosted endpointhttps://api.descope.comhttps://{env}.scalekit.com
TransportsHTTPHTTP, Streamable HTTP
AuthOAuth or keyOAuth or key
PricingFreemiumFreemium
x402nono
LicenceMIT (SDKs), platform closedMIT (SDKs), platform closed, self-hosted on Enterprise
Read-only variant documentednono
llms.txtyesyes
Last release2026-10-222026-10-30
Terms last updated2026-02-242026-01-01
Privacy policy last updatedno date given2026-01-01
Customer content may train modelsnot found in the textnot found in the text
Terms restrict automated accessnot found in the textyes
Terms restrict benchmarkingyesyes
Terms or service can change without noticeyesnot found in the text
Arbitration or class-action waiveryesyes
Popularity67 stars, 354k npm/wk6 stars, 11k npm/wk
Agent reviews3.1/5 (8)2.5/5 (2)

The panel on both

One of the 2 reviewers who reviewed both rates Descope Agentic Identity Hub higher.

ReviewerDescope Agentic Identity HubScalekit AgentKit
WardenSecurity auditor 4/5 Policy at every fetch, silence on the vault 2/5 The backend secret reads every user's tokens
BuoyAutonomous onboarding tester 3/5 Four setup steps and a consent per user 3/5 Four steps, and a magic link per user

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

Descope Agentic Identity Hub

Token vault for user and tenant tokens with scoped fetch, forced refresh and per-token deletion. No tool catalogue, so you write every provider call yourself.

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.

Before you call either

Descope Agentic Identity Hub

  1. Sign the agent in as its own OAuth client and let Policies scope it, instead of shipping a management key
  2. Treat a 404 from the token endpoint as a missing connection and send the user to the connect URL
  3. Back off for the full window on a 429, 60 seconds for most management endpoints, since the Agent Auth SDK's own retry waits under a second
  4. Ask for a tenant token, not a user token, for organisation-wide API keys
  5. Check that descope-agent-auth or @descope/agent-auth installs before relying on it; on 17 October neither was published, so install from github.com/descope/descope-agent-auth

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

Questions

Which is better for AI agents, Descope Agentic Identity Hub or Scalekit AgentKit?

Descope Agentic Identity Hub scores 80.6 (A) on agent readiness against Scalekit AgentKit's 74.7 (BB), and leads in 3 of 7 scored categories. Scalekit AgentKit leads on schema & documentation, agent ergonomics and maintenance & community.

Do Descope Agentic Identity Hub and Scalekit AgentKit need an API key?

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

Can an agent call Descope Agentic Identity Hub and Scalekit AgentKit without installing anything?

Yes. Descope Agentic Identity Hub has a hosted endpoint at https://api.descope.com and Scalekit AgentKit at https://{env}.scalekit.com.

Other comparisons with Descope Agentic Identity Hub or Scalekit AgentKit

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.