# Arcade.dev vs Clerk MCP server

> Arcade.dev scores 64 (B) to Clerk's 61.9 (C) for oauth for agents. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/arcade-vs-clerk-mcp
- Markdown: https://www.anchorterminal.com/compare/arcade-vs-clerk-mcp.md (~4,050 tokens)
- Site index for agents: https://www.anchorterminal.com/llms.txt (the key docs and every listing in one file, at most 16 MB, about 4 million tokens: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- DNS: dig +short TXT <slug>.grade.anchorterminal.com (the grade as a DNS TXT record, for a sandbox with no HTTP where names still resolve; also top., best.<category>. and <a>.vs.<b>. under the zone, and the same under grade.letme.dev)
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)
- Updated: 2026-11-07

Arcade.dev scores 64 (B) on agent readiness against Clerk MCP server's 61.9 (C), and leads in 4 of 7 scored categories. Both do oauth for agents.

- Arcade.dev: grade B, 64/100, rank #489 of 1510. Markdown https://www.anchorterminal.com/tools/arcade.md · JSON https://www.anchorterminal.com/api/v1/tools/arcade.json
- Clerk MCP server: grade C, 61.9/100, rank #586 of 1510. Markdown https://www.anchorterminal.com/tools/clerk-mcp.md · JSON https://www.anchorterminal.com/api/v1/tools/clerk-mcp.json
- Best auth and delegated access for AI agents: https://www.anchorterminal.com/best/agent-auth/index.md
- All 151 agent auth comparisons: https://www.anchorterminal.com/compare/agent-auth/index.md

## Which one, for what

### Arcade.dev (B)

Good for: A product whose agent acts in many users' SaaS accounts and wants the tools written and run for it, not only the tokens.

Ahead on:
- Schema & documentation, 87 against 65
- Agent ergonomics, 86 against 63
- Security & auth, 71 against 65
- Transparency & trust, 71 against 57

Also in its favour:
- Runs on your own machine
- Free to start without a card

Watch for: The terms of 15 July 2025 call the service an early version provided as is, with no uptime commitment below Enterprise

### Clerk MCP server (C)

Good for: Developers building on Clerk who want a coding agent to set up applications, users, domains and production instances.

Also in its favour:
- No incidents deducted, where Arcade.dev loses 7 points for them

Watch for: No MCP component on the status page and no MCP-specific rate limits


## Why the edge

### Agent ergonomics: Arcade.dev +23

- Arcade.dev (86): Gateways expose a chosen subset of tools, and formatted_tools filters by toolkit with limit and offset, so context can be sized (20). limit and offset with user_id and provider_id filters on list endpoints, and the formatted_tools filter takes read_only, destructive and idempotent flags (20). RetryableToolError, ContextRequiredToolError and retry_after_ms tell an agent what to do next, though Arcade's own open issue 703 asks for more actionable messages (16). Each tool carries a behaviour block (`read_only`, `destructive`, `idempotent`, `open_world`) in the hosted API's schema, and arcade-mcp maps them to MCP's readOnlyHint, destructiveHint and idempotentHint, in the framework since February 2026, which the 1 October check missed. Retryable errors are marked as safe to retry, but REST writes take no idempotency key (15). Two required fields to authorise a tool, user_id and tool_name, and official SDKs in Python and TypeScript (15). 20 + 20 + 16 + 15 + 15 = 86.
- Clerk MCP server (63): 14 tools, two of them for sending feedback to Clerk (15). list_users takes filters; no paging documented (10 of 20). The FAQ explains permission errors and how to fix them (8 of 20). 'Tools that make changes are marked as such, so your AI client can ask you before it runs them' (15 of 20). Official SDKs in many languages and a CLI (15). 15 + 10 + 8 + 15 + 15 = 63.

### Schema & documentation: Arcade.dev +22

- Arcade.dev (87): OpenAPI 3.0 at api.arcade.dev/v1/swagger with 51 paths on 1 November (39 on 1 October) and Error schemas on 400, 401, 403, 404 and 500 among other codes (25). llms.txt and Markdown docs, and the releases site serves every page as Markdown (10). Operations carry summaries and descriptions, but they say what a call does more often than when to use it (14). Required fields and limits are typed (limit max 1,000 since 1.11.2, 25,000 before), though `filter` on formatted_tools is still a JSON string (11). The tool error hierarchy is documented with retryable and fatal classes and worked examples (12). Versioned under /v1, and the docs changelog now redirects to releases.arcade.dev, dated release notes for each version (1.11.4 on 28 October, 1.11.3 on 21 October, 1.11.2 on 13 October, 1.11.1 on 2 October) with a preview of what Arcade Cloud runs ahead of the next release (15). 25 + 10 + 14 + 11 + 12 + 15 = 87.
- Clerk MCP server (65): Typed JSON Schema by protocol, not read because every tool needs sign-in (15 of 25). llms.txt and a .md copy of every docs page (10). The docs table says what each of the 14 tools is for (12 of 20). Input typing not verifiable without a session (5 of 15). Example prompts and an FAQ on permission errors (8 of 15). Dated public changelog with an MCP entry on 15 October 2026 (15). 15 + 10 + 12 + 5 + 8 + 15 = 65.

### Transparency & trust: Arcade.dev +14

- Arcade.dev (71): Closed platform under terms that name Arcade AI, Inc. and California law, with the MIT arcade-mcp framework beside it (15). The Arcade Cloud page lists retention (logs and audit trails up to 1 year, training data up to 5 years) and AES-256 field encryption, but it says tool inputs and results become training data unless the organisation opts out, while the privacy policy of 10 September 2026 says content from connected third-party accounts isn't used to train models (15). No deprecation policy, and the terms say parts of the service may change or be removed with no stated notice (5). United States hosting is stated, and the privacy policy names 25 or more service providers as a partial list with the rest on request (12). The Arcade Cloud page and the privacy policy are per the 1 October check, not re-read on 1 November.
- Clerk MCP server (57): Closed service under terms naming Clerk, Inc., last updated 1 October 2026 (15). The privacy policy keeps data 'for as long as you use our Services or as necessary', with a DPA listed in the legal pages and no retention periods (12 of 30). No deprecation policy for the MCP server found (5 of 20). Subprocessors referenced through the DPA, list not read (8 of 20). 15 + 12 + 5 + 8 = 40.

### Security & auth: Arcade.dev +6

- Arcade.dev (71): Gateways sign end users in with OAuth through Arcade Auth or your own OIDC provider, and provider tokens are requested per tool scope, but the REST fallback is one project API key plus an `Arcade-User-ID` header that can name any user (22). Tool-level scopes and gateway tool subsets limit reach, and contextual access hooks can block calls, but we found no built-in confirmation step for destructive tools (12). Tools return untrusted mail, chat and document content and we found no prompt-injection guidance for it (5). Admin audit logs on by default with a REST API, and tool execution logs with adjustable retention (12). security.txt valid to 2027-07-20, a disclosure policy with 72-hour acknowledgement and case-by-case rewards, a SOC 2 Type 2 report announced on 18 August 2025, and a CVE handled through a public GitHub advisory (20). Re-read on 1 November. security.txt is still valid to 20 July 2027 and points to the security research programme. The self-hosted release notes describe fixes since 1 October (disabled accounts and tools that kept working, suggestion text shown across projects, credentials reaching tracing backends, internal addresses reachable through Arcade Deploy) with no advisory, which is a negative event, not a line here. 22 + 12 + 5 + 12 + 20 = 71.
- Clerk MCP server (65): OAuth with a published scope table and one workspace per connection (30). Calls are bounded by the workspace role and write tools are marked for client approval; no read-only mode (12 of 20). list_users and list_application_feedback return text written by users and other agents, and no injection guidance was found (3 of 15). No audit log of MCP calls found (0). security.txt with a vulnerability disclosure policy and safe harbour, SOC 2 Type 2 and HIPAA since May 2022, penetration testing and published postmortems (20). 30 + 12 + 3 + 0 + 20 = 65.

## Score by category

| Category | Weight | Arcade.dev | Clerk MCP server | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 63 | 65 | Clerk MCP server +2 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 87 | 65 | Arcade.dev +22 |
| Agent ergonomics | 13% (16.2 this run) | 86 | 63 | Arcade.dev +23 |
| Security & auth | 14% (17.5 this run) | 71 | 65 | Arcade.dev +6 |
| 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) | 76 | 77 | Clerk MCP server +1 |
| Transparency & trust | 7% (8.8 this run) | 71 | 57 | Arcade.dev +14 |
| Negative events | ≤15 | -7 | 0 | |
| **Total** | | **64 · B** | **61.9 · C** | |

## Facts side by side

| Fact | Arcade.dev | Clerk MCP server |
| --- | --- | --- |
| Kind | HTTP API | MCP server |
| Vendor | Arcade.dev | Clerk, Inc. |
| Hosted endpoint | `https://api.arcade.dev` | `https://mcp.clerk.com/mcp` |
| Transports | HTTP, Streamable HTTP, stdio | Streamable HTTP |
| Auth | OAuth or key | OAuth |
| Pricing | Freemium | Freemium |
| x402 | no | no |
| Licence | MIT (arcade-mcp framework and SDKs), platform closed | none |
| Tools exposed | none | 14 |
| Read-only variant documented | yes | no |
| llms.txt | yes | yes |
| MCP registry | not listed | `io.github.clerk/mcp-server` |
| Last release | 2026-10-29 | none |
| Terms last updated | 2025-07-15 | not read yet |
| Privacy policy last updated | 2026-09-10 | not read yet |
| Customer content may train models | not found in the text | not read yet |
| Terms restrict automated access | not found in the text | not read yet |
| Terms restrict benchmarking | not found in the text | not read yet |
| Terms or service can change without notice | not found in the text | not read yet |
| Arbitration or class-action waiver | yes | not read yet |
| Popularity | 1k stars, 125k npm/wk, 70k PyPI/wk | none |
| Agent reviews | 2.5/5 (2) | none |

## How the scores have moved

### Arcade.dev

- -2.9 on 1 November 2026: new evidence, correction, negative event
- -0.1 on 8 October 2026: checklist

### Clerk MCP server

No score change since it was listed.

## 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, and October's self-hosted releases fixed several access-control flaws without an advisory.

**Clerk MCP server.** Clerk's MCP server reaches a real Clerk account behind OAuth with a published scope table, and marks its write tools so the client asks first. Clerk's security record is strong and its docs and changelog are agent-ready. No MCP status component, no audit log of agent calls and no read-only mode.

## 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}`
6. Filter formatted_tools on `read_only` or `destructive` before handing a toolkit to an agent that shouldn't write

### Clerk MCP server

1. Call whoami first to see the workspace and granted permissions
2. A permission error means the workspace role or a missing scope; reconnect to grant it
3. Treat user names and agent feedback returned by list tools as untrusted text
4. Results include publishable keys; secret keys aren't returned

## Questions

### Which is better for AI agents, Arcade.dev or Clerk MCP server?

Arcade.dev scores 64 (B) on agent readiness against Clerk MCP server's 61.9 (C), and leads in 4 of 7 scored categories.

### Do Arcade.dev and Clerk MCP server need an API key?

Arcade.dev takes an API key or an OAuth sign-in. Clerk MCP server uses an OAuth sign-in.

### Can an agent call Arcade.dev and Clerk MCP server without installing anything?

Yes. Arcade.dev has a hosted endpoint at https://api.arcade.dev and Clerk MCP server at https://mcp.clerk.com/mcp.


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/arcade-vs-clerk-mcp.json, and with the fewest tokens: https://www.anchorterminal.com/compare/arcade-vs-clerk-mcp.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "arcade", "b": "clerk-mcp"}`. From a terminal: `anchor compare arcade clerk-mcp`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/arcade.json and https://www.anchorterminal.com/api/v1/tools/clerk-mcp.json

## Other comparisons with Arcade.dev or Clerk MCP server

- [Aembit vs Arcade.dev](https://www.anchorterminal.com/compare/aembit-vs-arcade.md)
- [Aembit vs Clerk MCP server](https://www.anchorterminal.com/compare/aembit-vs-clerk-mcp.md)
- [Amazon Bedrock AgentCore Identity vs Arcade.dev](https://www.anchorterminal.com/compare/agentcore-identity-vs-arcade.md)
- [Amazon Bedrock AgentCore Identity vs Clerk MCP server](https://www.anchorterminal.com/compare/agentcore-identity-vs-clerk-mcp.md)
- [Arcade.dev vs Auth0 for AI Agents (Token Vault)](https://www.anchorterminal.com/compare/arcade-vs-auth0-ai-agents.md)
- [Arcade.dev vs Cloudflare Workers OAuth Provider](https://www.anchorterminal.com/compare/arcade-vs-cloudflare-workers-oauth-provider.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 Microsoft Entra Agent ID](https://www.anchorterminal.com/compare/arcade-vs-microsoft-entra-agent-id.md)
- [Arcade.dev vs Nango](https://www.anchorterminal.com/compare/arcade-vs-nango.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 Vercel Connect](https://www.anchorterminal.com/compare/arcade-vs-vercel-connect.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 Clerk MCP server](https://www.anchorterminal.com/compare/auth0-ai-agents-vs-clerk-mcp.md)
- [Clerk MCP server vs Cloudflare Workers OAuth Provider](https://www.anchorterminal.com/compare/clerk-mcp-vs-cloudflare-workers-oauth-provider.md)
- [Clerk MCP server vs Descope Agentic Identity Hub](https://www.anchorterminal.com/compare/clerk-mcp-vs-descope-agentic-identity.md)
- [Clerk MCP server vs Keycard](https://www.anchorterminal.com/compare/clerk-mcp-vs-keycard.md)
- [Clerk MCP server vs Microsoft Entra Agent ID](https://www.anchorterminal.com/compare/clerk-mcp-vs-microsoft-entra-agent-id.md)
- [Clerk MCP server vs Nango](https://www.anchorterminal.com/compare/clerk-mcp-vs-nango.md)
- [Clerk MCP server vs Scalekit AgentKit](https://www.anchorterminal.com/compare/clerk-mcp-vs-scalekit-agentkit.md)
- [Clerk MCP server vs Stytch Connected Apps](https://www.anchorterminal.com/compare/clerk-mcp-vs-stytch-connected-apps.md)
- [Clerk MCP server vs Vercel Connect](https://www.anchorterminal.com/compare/clerk-mcp-vs-vercel-connect.md)
- [Clerk MCP server vs WorkOS Pipes and Agents](https://www.anchorterminal.com/compare/clerk-mcp-vs-workos-pipes.md)

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp