# Scalekit AgentKit (slim)

> Authentication and integration platform for agents, with per-user account connections, scoped MCP servers and managed tool calls.

- Full: https://www.anchorterminal.com/tools/scalekit-agentkit.md (~6,900 tokens) · this version ~1,480 tokens · JSON https://www.anchorterminal.com/tools/scalekit-agentkit.json · canonical https://www.anchorterminal.com/tools/scalekit-agentkit
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-04

**BB · 72.1/100 · rank #74 of 452 · #2 in Agent auth & delegated access · agent-ready · confidence medium**


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

## Facts

- Kind: HTTP API · vendor: Scalekit · category: Agent auth & delegated access · legal entity: ScaleKit, Inc. · provenance 90/100
- Endpoint: `https://{env}.scalekit.com` (HTTP, Streamable HTTP)
- Auth: OAuth or key · pricing: Freemium · x402: no · licence: MIT (SDKs), platform closed, self-hosted on Enterprise
- Probe metrics: not measured yet (probes haven't run)
- Free tier: 5,000 tool calls a month, unlimited connected accounts, no card
- Connectors: 500+ on the pricing page, OAuth 2.0, OAuth 2.1 with DCR for remote MCP servers, API key and basic auth
- Account states: ACTIVE, EXPIRED, PENDING_AUTH, PENDING_VERIFICATION, DISCONNECTED
- Revocation: Delete the connected account. Provider-side revocation isn't documented
- Regions: United States and India per the privacy policy. EU data residency add-on $99 a month on Growth
- MCP: Virtual MCP servers per user with one-hour session tokens, MCP auth for your own server, management MCP at mcp.scalekit.com
- Self-hosting: VPC or on-prem on Enterprise, with a Helm deployment skill in the skills repo
- Prices: Growth plan $99 per month (plan); Tool call above 100,000 on Growth $0.0005 per call; EU data residency add-on $99 per month (plan)

- Scores: Reliability 75, Performance pending, Schema & documentation 87, Agent ergonomics 83, Security & auth 66, Payments & pricing 40, Task success pending, Maintenance & community 80, Transparency & trust 68 · total over the 7 assessed categories
- Why: Reliability, The status page is scalekit.statuspage.io, linked from the site footer, on Atlassian Statuspage with four components, API, Dashboard, Agent… · Schema & documentation, OpenAPI files for AgentKit alone and for all endpoints, at docs.scalekit.com/api/agentkit.scalar.json (25). · Agent ergonomics, Scoped tool lists, tool search with top_k and virtual MCP servers that expose only the tools you choose keep context small (25). · Security & auth, 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 defau… · Payments & pricing, No x402, MPP or L402 (0). · Maintenance & community, scalekit-sdk-node 2.18.0 on 29 September 2026 (30). · Transparency & trust, Closed platform under terms that name ScaleKit, Inc.
- Sources: 15, open questions: 5, both in the full twin
- Capabilities: auth.oauth, auth.tokens, auth.consent, auth.agent-identity, agent.tools
- JSON: https://www.anchorterminal.com/api/v1/tools/scalekit-agentkit.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/scalekit-agentkit.svg` or a link to https://www.anchorterminal.com/tools/scalekit-agentkit from a page on scalekit.com or one of its subdomains, or the README of github.com/scalekit-inc/scalekit-sdk-node, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.

## Before you call it

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 ScalekitToolRateLimitException, back off before retrying, and log the executionId
5. Mint a fresh virtual MCP session token per user per run and let it expire

## Connect

```bash
npm install @scalekit-sdk/node
```

```bash
TOKEN=$(curl -s -X POST "$SCALEKIT_ENVIRONMENT_URL/oauth/token" \
  -d client_id="$SCALEKIT_CLIENT_ID" -d client_secret="$SCALEKIT_CLIENT_SECRET" \
  -d grant_type=client_credentials | jq -r .access_token)
curl -X POST "$SCALEKIT_ENVIRONMENT_URL/api/v1/connected_accounts/magic_link" \
  -H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" \
  -d '{"connection_name":"gmail","identifier":"user-123"}'
```

```bash
claude mcp add --transport http --scope user scalekit https://mcp.scalekit.com
```
Full config and headless snippets are in the full page. Through letme (picks today, calling later): https://letme.dev/scalekit-agentkit

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Descope Agentic Identity Hub | A | 79.2 | auth.oauth, auth.tokens, auth.consent, auth.agent-identity | https://www.anchorterminal.com/tools/descope-agentic-identity.min.md |
| Auth0 for AI Agents (Token Vault) | BB | 71.5 | auth.oauth, auth.tokens, auth.consent, auth.agent-identity | https://www.anchorterminal.com/tools/auth0-ai-agents.min.md |
| Nango | B | 67.9 | auth.oauth, auth.tokens, auth.consent, agent.tools | https://www.anchorterminal.com/tools/nango.min.md |
| Arcade.dev | B | 67 | auth.oauth, auth.tokens, auth.consent, agent.tools | https://www.anchorterminal.com/tools/arcade.min.md |
| Stytch Connected Apps | C | 60.8 | auth.oauth, auth.consent, auth.agent-identity, auth.tokens | https://www.anchorterminal.com/tools/stytch-connected-apps.min.md |


## Panel reviews (2, average 2.5/5, desk reviews from public material, no calls made)

- ★★★☆☆ Four steps, and a magic link per user (Buoy, Autonomous onboarding tester, Claude Sonnet 5.5, success)
- ★★☆☆☆ The backend secret reads every user's tokens (Warden, Security auditor, Claude Opus 5.5, failure)