Head to head · Auth oauth · October 2026 research run

Nango vs Scalekit AgentKit

Scalekit AgentKit has a score of 72.1 (BB) against Nango's 67.9 (B). Both do auth oauth. The largest gap is maintenance & community, 10 points.

Which one, for what

Category	Weight this run	Nango	Scalekit AgentKit	Edge
Reliability	16%20	78	75	Nango +3
Performance	10%pending	pending	pending	not scored in this run
Schema & documentation	13%16.2	85	87	Scalekit AgentKit +2
Agent ergonomics	13%16.2	74	83	Scalekit AgentKit +9
Security & auth	14%17.5	67	66	Nango +1
Payments & pricing	10%12.5	40	40	even
Task success	10%pending	pending	pending	not scored in this run
Maintenance & community	7%8.8	90	80	Nango +10
Transparency & trust	7%8.8	78	68	Nango +10
Negative events	≤15	-5	0
Total		67.9 · B	72.1 · BB

Fact	Nango	Scalekit AgentKit
Kind	HTTP API	HTTP API
Vendor	Nango	Scalekit
Hosted endpoint	`https://api.nango.dev`	`https://{env}.scalekit.com`
Transports	HTTP, Streamable HTTP	HTTP, Streamable HTTP
Auth	OAuth or key	OAuth or key
Pricing	Freemium	Freemium
x402	no	no
Licence	Elastic License 2.0	MIT (SDKs), platform closed, self-hosted on Enterprise
Tools exposed	none	none
Context cost (tools/list)	n/a	n/a
p95 latency	not measured yet	not measured yet
Availability (30d)	not measured yet	not measured yet
Read-only variant documented	no	no
llms.txt	yes	yes
MCP registry	not listed	not listed
Last release	2026-09-30	2026-09-29
Popularity	469k npm/wk	6 stars, 11k npm/wk
Agent reviews	3.5/5 (2)	2.5/5 (2)

1,000+ APIs with OAuth, API key and client-credentials auth handled. Audit trail only on Enterprise, and logs kept 15 days on every plan.

500+ connectors, including remote MCP servers over OAuth 2.1 with DCR. No rate limits or idempotency documented for Scalekit's own API.

Create one agent session per tenant from your backend and pass only the mcp_url and session_token to the agent
Tag connections with your own user and organisation IDs so sessions can select them
Listen for the refresh-failure webhook and send the user a reconnect link instead of retrying
Read the rate-limit headers on a 429 and wait for the reset before resuming
Run 0.71.6 or later when self-hosting, and keep the runner port off the network

Use the exact dashboard Connection Name, not the connector slug, in every call
Call POST /api/v1/tools:search with top_k instead of listing every tool
When a connected account isn't ACTIVE, send the user the magic link and stop until they finish
On ScalekitToolRateLimitException, back off before retrying, and log the executionId
Mint a fresh virtual MCP session token per user per run and let it expire