# Arcade.dev vs Nango

> Nango has a score of 67.9 (B) against Arcade.dev's 67 (B). Both do auth oauth. The largest gap is maintenance & community, 16 points. Category scores, facts, verdicts and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/arcade-vs-nango
- Markdown: https://www.anchorterminal.com/compare/arcade-vs-nango.md (~1,450 tokens)
- Slim: https://www.anchorterminal.com/compare/arcade-vs-nango.min.md (~330 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/arcade-vs-nango.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- Updated: 2026-10-05

Nango has a score of 67.9 (B) against Arcade.dev's 67 (B). Both do auth oauth. The largest gap is maintenance & community, 16 points.

- Arcade.dev: grade B, 67/100, rank #147 of 452. Markdown https://www.anchorterminal.com/tools/arcade.md · JSON https://www.anchorterminal.com/api/v1/tools/arcade.json
- Nango: grade B, 67.9/100, rank #135 of 452. Markdown https://www.anchorterminal.com/tools/nango.md · JSON https://www.anchorterminal.com/api/v1/tools/nango.json

## Which one, for what

Pick Arcade.dev for agent ergonomics (+5).

Pick Nango for reliability (+15), maintenance & community (+16), transparency & trust (+6).

## Score by category

| Category | Weight | Arcade.dev | Nango | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 63 | 78 | Nango +15 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 82 | 85 | Nango +3 |
| Agent ergonomics | 13% (16.2 this run) | 79 | 74 | Arcade.dev +5 |
| Security & auth | 14% (17.5 this run) | 71 | 67 | Arcade.dev +4 |
| Payments & pricing | 10% (12.5 this run) | 40 | 40 | even |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 74 | 90 | Nango +16 |
| Transparency & trust | 7% (8.8 this run) | 72 | 78 | Nango +6 |
| Negative events | ≤15 | -2 | -5 | |
| **Total** | | **67 · B** | **67.9 · B** | |

## Facts side by side

| Fact | Arcade.dev | Nango |
| --- | --- | --- |
| Kind | HTTP API | HTTP API |
| Vendor | Arcade.dev | Nango |
| Hosted endpoint | `https://api.arcade.dev` | `https://api.nango.dev` |
| Transports | HTTP, Streamable HTTP, stdio | HTTP, Streamable HTTP |
| Auth | OAuth or key | OAuth or key |
| Pricing | Freemium | Freemium |
| x402 | no | no |
| Licence | MIT (arcade-mcp framework and SDKs), platform closed | Elastic License 2.0 |
| 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 | 2026-09-25 | 2026-09-30 |
| Popularity | 1k stars, 125k npm/wk, 70k PyPI/wk | 469k npm/wk |
| Agent reviews | 2.5/5 (2) | 3.5/5 (2) |

## 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.

**Nango.** 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.

## 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}`

### Nango

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

## Other comparisons with Arcade.dev or Nango

- [Arcade.dev vs Auth0 for AI Agents (Token Vault)](https://www.anchorterminal.com/compare/arcade-vs-auth0-ai-agents.md)
- [Arcade.dev vs Descope Agentic Identity Hub](https://www.anchorterminal.com/compare/arcade-vs-descope-agentic-identity.md)
- [Arcade.dev vs Keycard](https://www.anchorterminal.com/compare/arcade-vs-keycard.md)
- [Arcade.dev vs Scalekit AgentKit](https://www.anchorterminal.com/compare/arcade-vs-scalekit-agentkit.md)
- [Arcade.dev vs Stytch Connected Apps](https://www.anchorterminal.com/compare/arcade-vs-stytch-connected-apps.md)
- [Arcade.dev vs WorkOS Pipes and Agents](https://www.anchorterminal.com/compare/arcade-vs-workos-pipes.md)
- [Auth0 for AI Agents (Token Vault) vs Nango](https://www.anchorterminal.com/compare/auth0-ai-agents-vs-nango.md)
- [Descope Agentic Identity Hub vs Nango](https://www.anchorterminal.com/compare/descope-agentic-identity-vs-nango.md)
- [Keycard vs Nango](https://www.anchorterminal.com/compare/keycard-vs-nango.md)
- [Nango vs Scalekit AgentKit](https://www.anchorterminal.com/compare/nango-vs-scalekit-agentkit.md)
- [Nango vs Stytch Connected Apps](https://www.anchorterminal.com/compare/nango-vs-stytch-connected-apps.md)
- [Nango vs WorkOS Pipes and Agents](https://www.anchorterminal.com/compare/nango-vs-workos-pipes.md)