{ "data": { "a": { "slug": "auth0-ai-agents", "name": "Auth0 for AI Agents (Token Vault)", "vendor": "Auth0 by Okta", "vendorUrl": "https://auth0.com/ai", "kind": "http-api", "category": "agent-auth", "summary": "Auth0's identity and authorisation tools for AI agents, built on its identity platform.", "url": "https://www.anchorterminal.com/tools/auth0-ai-agents", "markdownUrl": "https://www.anchorterminal.com/tools/auth0-ai-agents.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/auth0-ai-agents.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/auth0-ai-agents.json", "dns": "auth0-ai-agents.grade.anchorterminal.com", "repo": "https://github.com/auth0/auth0-ai-js", "license": "Apache-2.0 (SDKs), platform closed", "transports": [ "http", "stdio" ], "remoteUrl": "https://{tenant}.auth0.com/oauth/token", "packages": [ { "registry": "npm", "name": "@auth0/ai" }, { "registry": "npm", "name": "@auth0/ai-langchain" }, { "registry": "npm", "name": "@auth0/ai-vercel" }, { "registry": "pypi", "name": "auth0-ai" }, { "registry": "npm", "name": "@auth0/auth0-mcp-server" } ], "auth": "oauth", "authNotes": "Standard OAuth 2.0 and OIDC against your tenant. The app exchanges the user's Auth0 refresh token or access token at /oauth/token with the grant type `urn:auth0:params:oauth:grant-type:token-exchange:federated-connection-access-token` and gets back the external provider's access token. Backend workers can use a signed JWT (privileged worker exchange). DPoP can bind Auth0 tokens to the client. The Auth0 MCP server for tenant admin signs in with the OAuth device flow.", "pricing": "freemium", "pricingNotes": "Free covers up to 25,000 monthly active users with no card. Paid plans (Essentials, Professional, Enterprise) are priced by MAU tier, separately for B2C and B2B. Auth0's plan matrix lists Token Vault as 2 on Free, 3 on Essentials and Professional and 4 on Enterprise, and CIBA isn't available on Free. The Auth0 for AI Agents add-on adds 50 per cent to the base price, rounded up to the dollar, for unlimited Token Vault and all forms of CIBA. Yearly billing is 11 times the monthly price. Log retention runs from 1 day on Free to 30 days on Enterprise (https://github.com/auth0/docs-v2/blob/main/main/.mintlify/skills/auth0/references/feature-audit-pricing/index.md, https://auth0.com/pricing). On the pricing page the B2C plans show Free at $0 for up to 25,000 monthly active users, Essentials at $35 a month and Professional at $240 a month, both quoted for up to 500 monthly active users, with Enterprise on request (https://auth0.com/pricing).", "priceSummary": "Freemium", "where": "both", "x402": { "level": "no", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 16, "npmWeekly": 3114, "pypiWeekly": null, "asOf": "2026-09-30" }, "docsUrl": "https://auth0.com/ai/docs", "llmsTxt": "https://auth0.com/docs/llms.txt", "openapi": "https://auth0.com/docs/oas/authentication/authentication-api-oas.json", "registryName": "com.auth0/mcp", "capabilities": [ "auth.oauth", "auth.tokens", "auth.consent", "auth.agent-identity", "hitl.approve" ], "tags": [ "hosted", "freemium", "free-tier", "no-card", "oauth", "typescript", "python", "enterprise", "mcp" ], "lastRelease": "2026-10-30", "graded": true, "anchor": { "graded": true, "score": 74.3, "grade": "BB", "agentReady": true, "rank": 88, "ranked": true, "rankOf": 1510, "categoryRank": 6, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 71, "maintenance": 74, "payments": 30, "reliability": 80, "schema": 85, "security": 88, "transparency": 84 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-01" }, "negative": 0, "verdict": "Standard grants throughout, RFC 8693 token exchange, CIBA with RAR and DPoP, and the Authentication API now has a public OpenAPI file. Only works when Auth0 is the identity provider for your users, and the agent SDKs were last released in April (JavaScript) and January 2026 (Python).", "bestFor": "Best when Auth0 already runs login and the agent needs a handful of the user's Google, Microsoft, Slack or GitHub tokens, or a second-device approval before a payment or delete.", "strengths": [ "Standard grants throughout, RFC 8693 token exchange, CIBA with RAR and DPoP", "Human approval on a second device for sensitive actions, showing the exact payee or amount", "Free plan up to 25,000 monthly active users with no card", "Public OpenAPI 3.1 file for the Authentication API, with 400, 401, 403 and 429 examples on /oauth/token", "Bugcrowd programmes, security.txt valid to 1 January 2027 and an Enterprise SLA of 99.99 per cent" ], "weaknesses": [ "Only works when Auth0 is the identity provider for your users", "Two Token Vault connections on Free and three on Essentials and Professional without the add-on", "Log retention of 1 day on Free and 5 days on Essentials is short for an audit trail", "The Token Vault grant type isn't in the Authentication API's OpenAPI file", "Agent SDKs last released in April 2026 (JavaScript) and January 2026 (Python)" ], "agentNotes": [ "Turn off refresh token rotation on the application before using the refresh token exchange", "Treat a 401 from the exchange as a missing connected account and send the user through the Connected Accounts flow", "Pass login_hint when a user has linked two accounts from the same provider", "Use CIBA for purchases or deletes and wait for the approval instead of asking in chat", "Read x-ratelimit-reset on a 429 and back off until then" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 3.5, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "BB", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 74.3 } ], "editorialScores": { "ergonomics": 71, "maintenance": 74, "payments": 30, "reliability": 80, "schema": 85, "security": 88, "transparency": 70 }, "provenanceScore": 97, "checked": { "categories": { "ergonomics": "2026-11-01", "maintenance": "2026-11-01", "payments": "2026-11-01", "reliability": "2026-11-01", "schema": "2026-11-01", "security": "2026-11-01", "transparency": "2026-11-01" }, "last": "2026-11-01", "lastMoved": "2026-11-01", "oldest": "2026-11-01", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "npm install @auth0/ai", "http": "curl -X POST \"https://$AUTH0_DOMAIN/oauth/token\" \\\n -d grant_type=urn:auth0:params:oauth:grant-type:token-exchange:federated-connection-access-token \\\n -d subject_token_type=urn:ietf:params:oauth:token-type:refresh_token \\\n -d subject_token=\"$AUTH0_REFRESH_TOKEN\" \\\n -d requested_token_type=http://auth0.com/oauth/token-type/federated-connection-access-token \\\n -d connection=google-oauth2 \\\n -d client_id=\"$AUTH0_CLIENT_ID\" -d client_secret=\"$AUTH0_CLIENT_SECRET\"", "config": { "mcpServers": { "auth0": { "args": [ "-y", "@auth0/auth0-mcp-server", "run" ], "command": "npx" } } } }, "letme": { "capability": "https://letme.dev/auth.oauth", "tool": "https://letme.dev/auth0-ai-agents" }, "area": "agent-runtime", "provenance": { "legalEntity": "Okta, Inc.", "domain": "auth0.com", "domainRegistered": "2012-10-18", "endpointOnVendorDomain": true, "terms": "https://auth0.com/legal", "privacy": "https://www.okta.com/privacy-policy/", "statusPage": "https://status.auth0.com", "changelog": "https://auth0.com/changelog", "securityTxt": "valid", "checked": "2026-11-01", "notes": [ "auth0.com's robots.txt disallows /legal, so we don't read the terms page.", "The Auth0 MCP server (@auth0/auth0-mcp-server, version 0.1.0-beta.19, tagged 13 August 2026) manages your tenant. It isn't how an agent gets user tokens." ], "score": 97 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/auth0-ai-agents.json", "live": { "slug": "auth0-ai-agents", "probe": { "target": "https://{tenant}.auth0.com/oauth/token", "method": "get", "lastAt": "2026-11-07T23:26:19.635668473Z", "lastOk": false, "lastStatus": 0, "lastMs": 0, "lastNote": "invalid character \"{\" in host name", "authRequired": false, "uptime24h": 0, "uptime30d": 0, "p50ms24h": 0, "p95ms24h": 0, "samples24h": 243, "samples30d": 7961, "days": [ { "date": "2026-10-07", "probes": 272, "ok": 0 }, { "date": "2026-10-08", "probes": 268, "ok": 0 }, { "date": "2026-10-09", "probes": 250, "ok": 0 }, { "date": "2026-10-10", "probes": 247, "ok": 0 }, { "date": "2026-10-11", "probes": 247, "ok": 0 }, { "date": "2026-10-12", "probes": 247, "ok": 0 }, { "date": "2026-10-13", "probes": 248, "ok": 0 }, { "date": "2026-10-14", "probes": 249, "ok": 0 }, { "date": "2026-10-15", "probes": 253, "ok": 0 }, { "date": "2026-10-16", "probes": 252, "ok": 0 }, { "date": "2026-10-17", "probes": 253, "ok": 0 }, { "date": "2026-10-18", "probes": 256, "ok": 0 }, { "date": "2026-10-19", "probes": 255, "ok": 0 }, { "date": "2026-10-20", "probes": 252, "ok": 0 }, { "date": "2026-10-21", "probes": 253, "ok": 0 }, { "date": "2026-10-22", "probes": 253, "ok": 0 }, { "date": "2026-10-23", "probes": 248, "ok": 0 }, { "date": "2026-10-24", "probes": 251, "ok": 0 }, { "date": "2026-10-25", "probes": 250, "ok": 0 }, { "date": "2026-10-26", "probes": 252, "ok": 0 }, { "date": "2026-10-27", "probes": 249, "ok": 0 }, { "date": "2026-10-28", "probes": 251, "ok": 0 }, { "date": "2026-10-29", "probes": 249, "ok": 0 }, { "date": "2026-10-30", "probes": 248, "ok": 0 }, { "date": "2026-10-31", "probes": 251, "ok": 0 }, { "date": "2026-11-01", "probes": 249, "ok": 0 }, { "date": "2026-11-02", "probes": 250, "ok": 0 }, { "date": "2026-11-03", "probes": 248, "ok": 0 }, { "date": "2026-11-04", "probes": 246, "ok": 0 }, { "date": "2026-11-05", "probes": 185, "ok": 0 }, { "date": "2026-11-06", "probes": 241, "ok": 0 }, { "date": "2026-11-07", "probes": 238, "ok": 0 } ] }, "vendorStatus": { "page": "https://status.auth0.com", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-11-07T04:47:08.036668275Z" }, "versions": [ { "registry": "github", "name": "auth0/auth0-ai-js", "version": "@auth0/ai-vercel-v5.1.1", "released": "2026-04-22", "seenAt": "2026-11-06T23:08:20.917851841Z" }, { "registry": "mcp-registry", "name": "com.auth0/mcp", "version": "0.1.0-beta.10", "seenAt": "2026-11-07T18:16:28.95801333Z" }, { "registry": "npm", "name": "@auth0/ai", "version": "6.0.2", "seenAt": "2026-11-06T23:08:14.720900254Z" }, { "registry": "npm", "name": "@auth0/ai-langchain", "version": "5.0.2", "seenAt": "2026-11-06T23:08:14.931814236Z" }, { "registry": "npm", "name": "@auth0/ai-vercel", "version": "5.1.1", "seenAt": "2026-11-06T23:08:16.935766493Z" }, { "registry": "npm", "name": "@auth0/auth0-mcp-server", "version": "0.1.0-beta.19", "seenAt": "2026-11-06T23:08:20.285007111Z" }, { "registry": "pypi", "name": "auth0-ai", "version": "1.0.2", "released": "2026-01-20", "seenAt": "2026-11-06T23:08:18.914981149Z" } ], "githubStars": 16, "npmWeekly": 790, "pypiWeekly": 525, "securityTxt": { "url": "https://auth0.com/.well-known/security.txt", "state": "valid", "expires": "2027-01-01T08:00:00.000Z", "checkedAt": "2026-11-07T16:01:41.276508373Z" }, "llmsTxt": { "url": "https://auth0.com/docs/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:31:38.292966833Z" }, "domain": { "domain": "auth0.com", "registered": "2012-10-18", "source": "https://rdap.verisign.com/com/v1/domain/auth0.com", "checkedAt": "2026-11-01T14:12:03.643485071Z" }, "pages": [ { "url": "https://auth0.com/changelog", "kind": "changelog", "status": 200, "checkedAt": "2026-11-07T13:59:46.827322806Z", "changedAt": "2026-11-05T12:24:21.850876782Z", "fingerprint": "0e926e285b3c" }, { "url": "https://auth0.com/pricing", "kind": "pricing", "status": 304, "checkedAt": "2026-11-07T13:59:50.489746464Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "8730de5a8d15" }, { "url": "https://raw.githubusercontent.com/auth0/docs-v2/main/main/.mintlify/skills/auth0/references/feature-audit-pricing/index.md", "kind": "pricing", "status": 304, "checkedAt": "2026-11-07T14:20:05.938778377Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "d3bbfc00df65" }, { "url": "https://www.okta.com/privacy-policy/", "kind": "privacy", "status": 200, "checkedAt": "2026-11-07T14:32:14.022519162Z", "changedAt": "2026-10-29T05:25:40.562487906Z", "fingerprint": "a34f11f53046" }, { "url": "https://auth0.com/legal", "kind": "terms", "status": 0, "checkedAt": "2026-11-07T13:59:50.48972292Z", "changedAt": "0001-01-01T00:00:00Z", "blockedByRobots": true } ], "github": { "repo": "auth0/auth0-ai-js", "checkedAt": "2026-11-02T08:32:40.274731372Z", "stars": 16, "archived": false, "issuesEnabled": true, "pushedAt": "2026-11-02T02:12:08Z", "openIssues": 4, "openPRs": 50, "issuesOpened90d": 1, "issuesClosed90d": 2, "prsMerged90d": 3, "ci": { "branch": "main", "runs": 27, "success": 27, "failure": 0, "other": 0, "latest": "success", "latestAt": "2026-08-28T17:28:02Z" }, "advisories": [ { "ghsa": "GHSA-x84v-v9q4-j9fr", "cve": "CVE-2025-55182", "severity": "critical", "published": "2025-12-05T15:41:50Z" } ], "replies": { "sampled": 7, "unanswered": 4, "medianDays": 560.2 } }, "updatedAt": "2026-11-07T23:26:19.635668473Z" } }, "answer": "Auth0 for AI Agents (Token Vault) scores 74.3 (BB) on agent readiness against Clerk MCP server's 61.9 (C), and leads in 5 of 7 scored categories. Clerk MCP server leads on payments \u0026 pricing.", "b": { "slug": "clerk-mcp", "name": "Clerk MCP server", "vendor": "Clerk, Inc.", "vendorUrl": "https://clerk.com", "kind": "mcp", "category": "agent-auth", "summary": "Clerk's hosted MCP server lets an agent manage a Clerk account, applications, users, domains and production instances, and fetch Clerk SDK snippets. Sign-in is OAuth with published scopes.", "url": "https://www.anchorterminal.com/tools/clerk-mcp", "markdownUrl": "https://www.anchorterminal.com/tools/clerk-mcp.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/clerk-mcp.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/clerk-mcp.json", "dns": "clerk-mcp.grade.anchorterminal.com", "transports": [ "streamable-http" ], "remoteUrl": "https://mcp.clerk.com/mcp", "packages": [], "auth": "oauth", "authNotes": "OAuth sign-in with the Clerk dashboard account, choosing one workspace. Published scopes include user:org:read, applications:read and :manage, users:read and :manage, application_domains:read and :manage. The server can only do what the workspace role allows.", "pricing": "freemium", "pricingNotes": "The MCP server is free with a Clerk account. Clerk plans: Hobby free with no card (up to 50,000 monthly retained users per app), Pro $25 a month ($20 yearly) with 50,000 retained users included and $0.02 each after, Business $300 a month, Enterprise custom (checked 2026-11-07).", "priceSummary": "Freemium", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 on the MCP docs or pricing page (checked 2026-11-07).", "endpoints": [] }, "toolCount": 14, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-07" }, "docsUrl": "https://clerk.com/docs/guides/ai/mcp/clerk-mcp-server", "llmsTxt": "https://clerk.com/llms.txt", "registryName": "io.github.clerk/mcp-server", "capabilities": [ "auth.oauth", "auth.audit", "code.docs", "agent.tools" ], "tags": [ "official", "hosted", "mcp", "remote-mcp", "oauth", "freemium", "free-tier", "status-page", "soc2", "llms-txt", "mcp-registry" ], "graded": true, "anchor": { "graded": true, "score": 61.9, "grade": "C", "agentReady": false, "rank": 586, "ranked": true, "rankOf": 1510, "categoryRank": 15, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 63, "maintenance": 77, "payments": 40, "reliability": 65, "schema": 65, "security": 65, "transparency": 57 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-07" }, "negative": 0, "verdict": "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.", "bestFor": "Developers building on Clerk who want a coding agent to set up applications, users, domains and production instances.", "strengths": [ "OAuth with a published scope table, one workspace per connection, bounded by the user's role", "Write tools are marked so clients ask before running them", "llms.txt and a Markdown copy of every docs and changelog page", "SOC 2 Type 2, HIPAA, a disclosure policy with safe harbour and published postmortems", "Free Hobby plan with no card" ], "weaknesses": [ "No MCP component on the status page and no MCP-specific rate limits", "No read-only mode; write scopes are requested on every connection", "No audit log of agent calls found", "The registry entry (0.1.0, March 2026) predates the October revamp" ], "agentNotes": [ "Call whoami first to see the workspace and granted permissions", "A permission error means the workspace role or a missing scope; reconnect to grant it", "Treat user names and agent feedback returned by list tools as untrusted text", "Results include publishable keys; secret keys aren't returned" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 61.9 } ], "editorialScores": { "ergonomics": 63, "maintenance": 77, "payments": 40, "reliability": 65, "schema": 65, "security": 65, "transparency": 40 }, "provenanceScore": 74, "checked": { "categories": { "ergonomics": "2026-11-07", "maintenance": "2026-11-07", "payments": "2026-11-07", "reliability": "2026-11-07", "schema": "2026-11-07", "security": "2026-11-07", "transparency": "2026-11-07" }, "last": "2026-11-07", "oldest": "2026-11-07", "stale": false, "staleAfterDays": 90 } }, "connect": { "claudeCode": "claude mcp add clerk --transport http https://mcp.clerk.com/mcp", "config": { "mcpServers": { "clerk": { "url": "https://mcp.clerk.com/mcp" } } } }, "letme": { "capability": "https://letme.dev/auth.oauth", "tool": "https://letme.dev/clerk-mcp" }, "area": "agent-runtime", "unitPrices": [ { "item": "Monthly retained user over 50,000 (Pro)", "unit": "user-month", "usd": 0.02, "note": "Pro plan" } ], "provenance": { "legalEntity": "Clerk, Inc.", "domain": "clerk.com", "domainRegistered": "", "domainNote": "Not looked up: RDAP isn't requested under the 1 November 2026 rules.", "endpointOnVendorDomain": true, "terms": "https://clerk.com/legal/terms", "privacy": "https://clerk.com/legal/privacy", "statusPage": "https://status.clerk.com", "changelog": "https://clerk.com/changelog", "securityTxt": "valid", "checked": "2026-11-07", "notes": [ "Terms last updated 1 October 2026 naming Clerk, Inc.", "security.txt points to the vulnerability disclosure policy and security@clerk.dev, expiring 1 December 2026." ], "score": 74 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/clerk-mcp.json", "live": { "slug": "clerk-mcp", "probe": { "target": "https://mcp.clerk.com/mcp", "method": "mcp-initialize", "lastAt": "2026-11-07T23:26:24.547451095Z", "lastOk": true, "lastStatus": 401, "lastMs": 55, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 90, "p95ms24h": 179, "samples24h": 48, "samples30d": 48, "days": [ { "date": "2026-11-07", "probes": 48, "ok": 48 } ] }, "vendorStatus": { "page": "https://status.clerk.com", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-11-07T23:31:13.237574084Z" }, "updatedAt": "2026-11-07T23:31:13.237574084Z" } }, "edges": [ { "by": 27, "category": "transparency", "leads": "auth0-ai-agents", "name": "Transparency \u0026 trust", "reasons": { "a": "Closed platform under Okta's terms with Apache-2.0 SDKs (15). Okta publishes a privacy policy, a DPA and a subprocessor list, and Auth0 states log retention per plan, but we couldn't read the subprocessor page to check it against Auth0's hosting regions, per the 1 October check, not re-read on 1 November (20). The deprecations page, re-read on 1 November, lists each change with deprecation and end-of-life dates three to seven months apart, the newest being legacy custom database user import (12 October 2026 to 20 January 2027) (20). Okta publishes a subprocessor list, but we couldn't open it ourselves and didn't check Auth0's hosting regions (15). 15 + 20 + 20 + 15 = 70.", "b": "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." }, "scores": { "a": 84, "b": 57 } }, { "by": 23, "category": "security", "leads": "auth0-ai-agents", "name": "Security \u0026 auth", "reasons": { "a": "OAuth 2.0 and OIDC with RFC 8693 token exchange, DPoP binding and scoped provider tokens, less a little because the refresh-token exchange needs refresh token rotation turned off (28). CIBA with RAR asks the user to approve the exact action on a second device, a scope subset can be requested and FGA filters what a RAG agent can read (20). Token Vault returns tokens, not untrusted content (10). Tenant logs stream to Datadog, Splunk, EventBridge and others, but retention is 1 day on Free and 5 on Essentials (10). Valid security.txt, Bugcrowd programmes for Okta and Auth0, and SDK advisories published on GitHub (20).", "b": "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." }, "scores": { "a": 88, "b": 65 } }, { "by": 20, "category": "schema", "leads": "auth0-ai-agents", "name": "Schema \u0026 documentation", "reasons": { "a": "The Authentication API, where the token exchange happens, now has a public OpenAPI 3.1 file (31 paths, /oauth/token with the RFC 8693 token-exchange grant, and /bc-authorize for CIBA), listed with the Management API's in the docs llms.txt. The Token Vault grant type and its `requested_token_type` aren't in it, so 5 off (20). The agent docs moved from auth0.com/ai/docs/llms.txt, which answered 404 on 1 November, into auth0.com/docs/llms.txt, whose AI Agents and MCP section lists 86 pages (10). The agent docs explain when to use Token Vault, CIBA or FGA and what each is for (16). The token exchange reference lists required and optional parameters with their fixed URN values, and marks the scope subset as Early Access (12). The exchange reference still documents only 401 and 403, while the OpenAPI file adds 400 and 429 examples for /oauth/token (12). Dated public changelog and semver SDKs (15). 20 + 10 + 16 + 12 + 12 + 15 = 85.", "b": "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." }, "scores": { "a": 85, "b": 65 } }, { "by": 15, "category": "reliability", "leads": "auth0-ai-agents", "name": "Reliability", "reasons": { "a": "Auth0's own status page at status.auth0.com with per-region, per-component history (20). Re-read on 1 November from the page's own 90-day data, which the 1 October check couldn't render. Nine incidents since 3 August. Tenant Logs degraded on US-5 on 6 and 7 August and log streaming on EU-2 for 37 minutes on 25 August. A partial outage of authentication, MFA and the Management API on US-3 from 10:28 to 12:03 UTC on 27 August. Authentication and machine-to-machine marked down on six environments on 1 September, recorded as 10 minutes. A partial outage on US-5 for 49 minutes on 16 September. Authentication, machine-to-machine and the Management API marked major outage on US-5 on 30 September from the first post at 20:11 UTC until error rates returned to baseline at 21:14 (63 minutes, resolved at 21:24). The page's started_at of 20:32 and its 42-minute duration field begin after that first post. Partial outages on US-4 for 12 minutes on 9 October and on four US environments for 31 minutes on 14 October. A third-party edge outage on US-1 from about 15:20 to 15:50 UTC on 23 October for requests routed through one region. 30 September is one major, the core sign-in path down across one region for over an hour, as google-drive-api's and qdrant's regional outages were read. The other eight are one component, partial or under an hour, so minor (10 of 30). Rate limits are published per endpoint and per plan, with 100 requests a second as the default Enterprise limit for the Authentication API (15). 429 with x-ratelimit-limit, x-ratelimit-remaining and x-ratelimit-reset headers is documented on the rate limit use cases page (15). 99.99 per cent SLA on Enterprise, listed on the pricing page (10). Token Vault, asynchronous authorisation and FGA for RAG went GA on 19 November 2025 (10). 20 + 10 + 15 + 15 + 10 + 10 = 80.", "b": "Graded as a hosted service. incident.io status page at status.clerk.com with components for authentication, sessions, webhooks and SCIM, but none for the MCP server (15). The feed shows several resolved incidents since August (an upstream SMS issue on 29 October, Apple sign-in for development instances, an incident across all components on 3 November, resolved), none read as a long core outage (20). Backend API limits published with numbers (1,000 requests per 10 seconds in production), not for the MCP server itself (10 of 15). 429 with Retry-After documented, no idempotency guidance for writes (10 of 15). No SLA found; Business support has 'No response-time SLA' (0). The MCP server isn't labelled beta (10). 15 + 20 + 10 + 10 + 0 + 10 = 65." }, "scores": { "a": 80, "b": 65 } }, { "by": 10, "category": "payments", "leads": "clerk-mcp", "name": "Payments \u0026 pricing", "reasons": { "a": "No x402, MPP or L402 (0). Plan prices are public (Essentials from $35 a month, Professional from $240 for 500 monthly active users), and the agent add-on rule (50 per cent on top of the base) is in Auth0's docs rather than on the pricing page (10). Free plan up to 25,000 monthly active users with no card (20). A person signs up in a browser and creates a tenant (0).", "b": "No x402, MPP or L402 (0). Per-unit prices are public ($0.02 per retained user over the included 50,000, $0.01 per SMS) (20). Hobby is free with no card (20). A person signs up and approves OAuth in a browser (0). 0 + 20 + 20 + 0 + 0 = 40." }, "scores": { "a": 30, "b": 40 } }, { "by": 8, "category": "ergonomics", "leads": "auth0-ai-agents", "name": "Agent ergonomics", "reasons": { "a": "The exchange returns one provider token and its expiry, so there's nothing to size (20). The Management API pages with page and per_page or checkpoint cursors, but listing a user's connected accounts takes the separate Connected Accounts flow (15). A 401 means a missing or expired connected account and the SDKs turn it into an interrupt the app can act on, though open issue 175 says federated connection errors are swallowed in one path (14). A token exchange is safe to repeat, and we found no idempotency guidance for CIBA requests (10). Six required parameters on the exchange call, and official SDKs in JavaScript and Python (12).", "b": "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." }, "scores": { "a": 71, "b": 63 } } ], "facts": [ { "a": "HTTP API", "b": "MCP server", "name": "Kind" }, { "a": "Auth0 by Okta", "b": "Clerk, Inc.", "name": "Vendor" }, { "a": "https://{tenant}.auth0.com/oauth/token", "b": "https://mcp.clerk.com/mcp", "name": "Hosted endpoint" }, { "a": "HTTP, stdio", "b": "Streamable HTTP", "name": "Transports" }, { "a": "OAuth", "b": "OAuth", "name": "Auth" }, { "a": "Freemium", "b": "Freemium", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Apache-2.0 (SDKs), platform closed", "b": "none", "name": "Licence" }, { "a": "none", "b": "14", "name": "Tools exposed" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "com.auth0/mcp", "b": "io.github.clerk/mcp-server", "name": "MCP registry" }, { "a": "2026-10-30", "b": "none", "name": "Last release" }, { "a": "couldn't be read", "b": "not read yet", "name": "Terms last updated" }, { "a": "2026-06-01", "b": "not read yet", "name": "Privacy policy last updated" }, { "a": "couldn't be read", "b": "not read yet", "name": "Customer content may train models" }, { "a": "couldn't be read", "b": "not read yet", "name": "Terms restrict automated access" }, { "a": "couldn't be read", "b": "not read yet", "name": "Terms restrict benchmarking" }, { "a": "couldn't be read", "b": "not read yet", "name": "Terms or service can change without notice" }, { "a": "couldn't be read", "b": "not read yet", "name": "Arbitration or class-action waiver" }, { "a": "16 stars, 3.1k npm/wk", "b": "none", "name": "Popularity" }, { "a": "3.5/5 (2)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "Auth0 for AI Agents (Token Vault) scores 74.3 (BB) on agent readiness against Clerk MCP server's 61.9 (C), and leads in 5 of 7 scored categories. Clerk MCP server leads on payments \u0026 pricing.", "question": "Which is better for AI agents, Auth0 for AI Agents (Token Vault) or Clerk MCP server?" }, { "answer": "Both use an OAuth sign-in.", "question": "Do Auth0 for AI Agents (Token Vault) and Clerk MCP server need an API key?" }, { "answer": "Yes. Auth0 for AI Agents (Token Vault) has a hosted endpoint at https://{tenant}.auth0.com/oauth/token and Clerk MCP server at https://mcp.clerk.com/mcp.", "question": "Can an agent call Auth0 for AI Agents (Token Vault) and Clerk MCP server without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 80 against 65", "Schema \u0026 documentation, 85 against 65", "Agent ergonomics, 71 against 63", "Security \u0026 auth, 88 against 65", "Transparency \u0026 trust, 84 against 57" ], "also": [ "Agent-ready, a grade of BB or better", "Runs on your own machine", "Free to start without a card" ], "goodFor": "Best when Auth0 already runs login and the agent needs a handful of the user's Google, Microsoft, Slack or GitHub tokens, or a second-device approval before a payment or delete.", "slug": "auth0-ai-agents", "watchFor": "Only works when Auth0 is the identity provider for your users" }, { "aheadOn": [ "Payments \u0026 pricing, 40 against 30" ], "also": null, "goodFor": "Developers building on Clerk who want a coding agent to set up applications, users, domains and production instances.", "slug": "clerk-mcp", "watchFor": "No MCP component on the status page and no MCP-specific rate limits" } ], "history": { "auth0-ai-agents": [ { "causes": [ "evidence" ], "date": "2026-11-01", "delta": 2.9, "from": 71.4, "fromGrade": "BB", "to": 74.3, "toGrade": "BB" }, { "causes": [ "method" ], "date": "2026-10-08", "delta": -0.1, "from": 71.5, "fromGrade": "BB", "to": 71.4, "toGrade": "BB" } ], "clerk-mcp": null }, "job": { "capability": "auth.oauth", "name": "OAuth for agents" }, "others": [ { "json": "https://www.anchorterminal.com/compare/aembit-vs-auth0-ai-agents.json", "title": "Aembit vs Auth0 for AI Agents (Token Vault)", "url": "https://www.anchorterminal.com/compare/aembit-vs-auth0-ai-agents" }, { "json": "https://www.anchorterminal.com/compare/aembit-vs-clerk-mcp.json", "title": "Aembit vs Clerk MCP server", "url": "https://www.anchorterminal.com/compare/aembit-vs-clerk-mcp" }, { "json": "https://www.anchorterminal.com/compare/agentcore-identity-vs-auth0-ai-agents.json", "title": "Amazon Bedrock AgentCore Identity vs Auth0 for AI Agents (Token Vault)", "url": "https://www.anchorterminal.com/compare/agentcore-identity-vs-auth0-ai-agents" }, { "json": "https://www.anchorterminal.com/compare/agentcore-identity-vs-clerk-mcp.json", "title": "Amazon Bedrock AgentCore Identity vs Clerk MCP server", "url": "https://www.anchorterminal.com/compare/agentcore-identity-vs-clerk-mcp" }, { "json": "https://www.anchorterminal.com/compare/arcade-vs-auth0-ai-agents.json", "title": "Arcade.dev vs Auth0 for AI Agents (Token Vault)", "url": "https://www.anchorterminal.com/compare/arcade-vs-auth0-ai-agents" }, { "json": "https://www.anchorterminal.com/compare/arcade-vs-clerk-mcp.json", "title": "Arcade.dev vs Clerk MCP server", "url": "https://www.anchorterminal.com/compare/arcade-vs-clerk-mcp" }, { "json": "https://www.anchorterminal.com/compare/auth0-ai-agents-vs-cloudflare-workers-oauth-provider.json", "title": "Auth0 for AI Agents (Token Vault) vs Cloudflare Workers OAuth Provider", "url": "https://www.anchorterminal.com/compare/auth0-ai-agents-vs-cloudflare-workers-oauth-provider" }, { "json": "https://www.anchorterminal.com/compare/auth0-ai-agents-vs-descope-agentic-identity.json", "title": "Auth0 for AI Agents (Token Vault) vs Descope Agentic Identity Hub", "url": "https://www.anchorterminal.com/compare/auth0-ai-agents-vs-descope-agentic-identity" }, { "json": "https://www.anchorterminal.com/compare/auth0-ai-agents-vs-keycard.json", "title": "Auth0 for AI Agents (Token Vault) vs Keycard", "url": "https://www.anchorterminal.com/compare/auth0-ai-agents-vs-keycard" }, { "json": "https://www.anchorterminal.com/compare/auth0-ai-agents-vs-microsoft-entra-agent-id.json", "title": "Auth0 for AI Agents (Token Vault) vs Microsoft Entra Agent ID", "url": "https://www.anchorterminal.com/compare/auth0-ai-agents-vs-microsoft-entra-agent-id" }, { "json": "https://www.anchorterminal.com/compare/auth0-ai-agents-vs-nango.json", "title": "Auth0 for AI Agents (Token Vault) vs Nango", "url": "https://www.anchorterminal.com/compare/auth0-ai-agents-vs-nango" }, { "json": "https://www.anchorterminal.com/compare/auth0-ai-agents-vs-scalekit-agentkit.json", "title": "Auth0 for AI Agents (Token Vault) vs Scalekit AgentKit", "url": "https://www.anchorterminal.com/compare/auth0-ai-agents-vs-scalekit-agentkit" }, { "json": "https://www.anchorterminal.com/compare/auth0-ai-agents-vs-stytch-connected-apps.json", "title": "Auth0 for AI Agents (Token Vault) vs Stytch Connected Apps", "url": "https://www.anchorterminal.com/compare/auth0-ai-agents-vs-stytch-connected-apps" }, { "json": "https://www.anchorterminal.com/compare/auth0-ai-agents-vs-vercel-connect.json", "title": "Auth0 for AI Agents (Token Vault) vs Vercel Connect", "url": "https://www.anchorterminal.com/compare/auth0-ai-agents-vs-vercel-connect" }, { "json": "https://www.anchorterminal.com/compare/auth0-ai-agents-vs-workos-pipes.json", "title": "Auth0 for AI Agents (Token Vault) vs WorkOS Pipes and Agents", "url": "https://www.anchorterminal.com/compare/auth0-ai-agents-vs-workos-pipes" }, { "json": "https://www.anchorterminal.com/compare/clerk-mcp-vs-cloudflare-workers-oauth-provider.json", "title": "Clerk MCP server vs Cloudflare Workers OAuth Provider", "url": "https://www.anchorterminal.com/compare/clerk-mcp-vs-cloudflare-workers-oauth-provider" }, { "json": "https://www.anchorterminal.com/compare/clerk-mcp-vs-descope-agentic-identity.json", "title": "Clerk MCP server vs Descope Agentic Identity Hub", "url": "https://www.anchorterminal.com/compare/clerk-mcp-vs-descope-agentic-identity" }, { "json": "https://www.anchorterminal.com/compare/clerk-mcp-vs-keycard.json", "title": "Clerk MCP server vs Keycard", "url": "https://www.anchorterminal.com/compare/clerk-mcp-vs-keycard" }, { "json": "https://www.anchorterminal.com/compare/clerk-mcp-vs-microsoft-entra-agent-id.json", "title": "Clerk MCP server vs Microsoft Entra Agent ID", "url": "https://www.anchorterminal.com/compare/clerk-mcp-vs-microsoft-entra-agent-id" }, { "json": "https://www.anchorterminal.com/compare/clerk-mcp-vs-nango.json", "title": "Clerk MCP server vs Nango", "url": "https://www.anchorterminal.com/compare/clerk-mcp-vs-nango" }, { "json": "https://www.anchorterminal.com/compare/clerk-mcp-vs-scalekit-agentkit.json", "title": "Clerk MCP server vs Scalekit AgentKit", "url": "https://www.anchorterminal.com/compare/clerk-mcp-vs-scalekit-agentkit" }, { "json": "https://www.anchorterminal.com/compare/clerk-mcp-vs-stytch-connected-apps.json", "title": "Clerk MCP server vs Stytch Connected Apps", "url": "https://www.anchorterminal.com/compare/clerk-mcp-vs-stytch-connected-apps" }, { "json": "https://www.anchorterminal.com/compare/clerk-mcp-vs-vercel-connect.json", "title": "Clerk MCP server vs Vercel Connect", "url": "https://www.anchorterminal.com/compare/clerk-mcp-vs-vercel-connect" }, { "json": "https://www.anchorterminal.com/compare/clerk-mcp-vs-workos-pipes.json", "title": "Clerk MCP server vs WorkOS Pipes and Agents", "url": "https://www.anchorterminal.com/compare/clerk-mcp-vs-workos-pipes" } ], "panel": null, "scores": [ { "auth0-ai-agents": 80, "by": 15, "clerk-mcp": 65, "edge": "auth0-ai-agents", "key": "reliability", "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "auth0-ai-agents": 85, "by": 20, "clerk-mcp": 65, "edge": "auth0-ai-agents", "key": "schema", "name": "Schema \u0026 documentation", "weight": 13 }, { "auth0-ai-agents": 71, "by": 8, "clerk-mcp": 63, "edge": "auth0-ai-agents", "key": "ergonomics", "name": "Agent ergonomics", "weight": 13 }, { "auth0-ai-agents": 88, "by": 23, "clerk-mcp": 65, "edge": "auth0-ai-agents", "key": "security", "name": "Security \u0026 auth", "weight": 14 }, { "auth0-ai-agents": 30, "by": 10, "clerk-mcp": 40, "edge": "clerk-mcp", "key": "payments", "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "auth0-ai-agents": 74, "by": 3, "clerk-mcp": 77, "edge": "clerk-mcp", "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7 }, { "auth0-ai-agents": 84, "by": 27, "clerk-mcp": 57, "edge": "auth0-ai-agents", "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Auth0 for AI Agents (Token Vault) scores 74.3 (BB) on agent readiness against Clerk MCP server's 61.9 (C), and leads in 5 of 7 scored categories. Clerk MCP server leads on payments \u0026 pricing. Both do oauth for agents.", "tasks": null, "tutorials": [], "verdicts": { "auth0-ai-agents": "Standard grants throughout, RFC 8693 token exchange, CIBA with RAR and DPoP, and the Authentication API now has a public OpenAPI file. Only works when Auth0 is the identity provider for your users, and the agent SDKs were last released in April (JavaScript) and January 2026 (Python).", "clerk-mcp": "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." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/auth0-ai-agents-vs-clerk-mcp", "json": "https://www.anchorterminal.com/compare/auth0-ai-agents-vs-clerk-mcp.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/auth0-ai-agents-vs-clerk-mcp.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/auth0-ai-agents-vs-clerk-mcp.min.md" }, "markdown": "Auth0 for AI Agents (Token Vault) scores 74.3 (BB) on agent readiness against Clerk MCP server's 61.9 (C), and leads in 5 of 7 scored categories. Clerk MCP server leads on payments \u0026 pricing. Both do oauth for agents.\n\n- Auth0 for AI Agents (Token Vault): grade BB, 74.3/100, rank #88 of 1510. Markdown https://www.anchorterminal.com/tools/auth0-ai-agents.md · JSON https://www.anchorterminal.com/api/v1/tools/auth0-ai-agents.json\n- 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\n- Best auth and delegated access for AI agents: https://www.anchorterminal.com/best/agent-auth/index.md\n- All 151 agent auth comparisons: https://www.anchorterminal.com/compare/agent-auth/index.md\n\n## Which one, for what\n\n### Auth0 for AI Agents (Token Vault) (BB)\n\nGood for: Best when Auth0 already runs login and the agent needs a handful of the user's Google, Microsoft, Slack or GitHub tokens, or a second-device approval before a payment or delete.\n\nAhead on:\n- Reliability, 80 against 65\n- Schema \u0026 documentation, 85 against 65\n- Agent ergonomics, 71 against 63\n- Security \u0026 auth, 88 against 65\n- Transparency \u0026 trust, 84 against 57\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n- Runs on your own machine\n- Free to start without a card\n\nWatch for: Only works when Auth0 is the identity provider for your users\n\n### Clerk MCP server (C)\n\nGood for: Developers building on Clerk who want a coding agent to set up applications, users, domains and production instances.\n\nAhead on:\n- Payments \u0026 pricing, 40 against 30\n\nWatch for: No MCP component on the status page and no MCP-specific rate limits\n\n\n## Why the edge\n\n### Transparency \u0026 trust: Auth0 for AI Agents (Token Vault) +27\n\n- Auth0 for AI Agents (Token Vault) (84): Closed platform under Okta's terms with Apache-2.0 SDKs (15). Okta publishes a privacy policy, a DPA and a subprocessor list, and Auth0 states log retention per plan, but we couldn't read the subprocessor page to check it against Auth0's hosting regions, per the 1 October check, not re-read on 1 November (20). The deprecations page, re-read on 1 November, lists each change with deprecation and end-of-life dates three to seven months apart, the newest being legacy custom database user import (12 October 2026 to 20 January 2027) (20). Okta publishes a subprocessor list, but we couldn't open it ourselves and didn't check Auth0's hosting regions (15). 15 + 20 + 20 + 15 = 70.\n- 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.\n\n### Security \u0026 auth: Auth0 for AI Agents (Token Vault) +23\n\n- Auth0 for AI Agents (Token Vault) (88): OAuth 2.0 and OIDC with RFC 8693 token exchange, DPoP binding and scoped provider tokens, less a little because the refresh-token exchange needs refresh token rotation turned off (28). CIBA with RAR asks the user to approve the exact action on a second device, a scope subset can be requested and FGA filters what a RAG agent can read (20). Token Vault returns tokens, not untrusted content (10). Tenant logs stream to Datadog, Splunk, EventBridge and others, but retention is 1 day on Free and 5 on Essentials (10). Valid security.txt, Bugcrowd programmes for Okta and Auth0, and SDK advisories published on GitHub (20).\n- 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.\n\n### Schema \u0026 documentation: Auth0 for AI Agents (Token Vault) +20\n\n- Auth0 for AI Agents (Token Vault) (85): The Authentication API, where the token exchange happens, now has a public OpenAPI 3.1 file (31 paths, /oauth/token with the RFC 8693 token-exchange grant, and /bc-authorize for CIBA), listed with the Management API's in the docs llms.txt. The Token Vault grant type and its `requested_token_type` aren't in it, so 5 off (20). The agent docs moved from auth0.com/ai/docs/llms.txt, which answered 404 on 1 November, into auth0.com/docs/llms.txt, whose AI Agents and MCP section lists 86 pages (10). The agent docs explain when to use Token Vault, CIBA or FGA and what each is for (16). The token exchange reference lists required and optional parameters with their fixed URN values, and marks the scope subset as Early Access (12). The exchange reference still documents only 401 and 403, while the OpenAPI file adds 400 and 429 examples for /oauth/token (12). Dated public changelog and semver SDKs (15). 20 + 10 + 16 + 12 + 12 + 15 = 85.\n- 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.\n\n### Reliability: Auth0 for AI Agents (Token Vault) +15\n\n- Auth0 for AI Agents (Token Vault) (80): Auth0's own status page at status.auth0.com with per-region, per-component history (20). Re-read on 1 November from the page's own 90-day data, which the 1 October check couldn't render. Nine incidents since 3 August. Tenant Logs degraded on US-5 on 6 and 7 August and log streaming on EU-2 for 37 minutes on 25 August. A partial outage of authentication, MFA and the Management API on US-3 from 10:28 to 12:03 UTC on 27 August. Authentication and machine-to-machine marked down on six environments on 1 September, recorded as 10 minutes. A partial outage on US-5 for 49 minutes on 16 September. Authentication, machine-to-machine and the Management API marked major outage on US-5 on 30 September from the first post at 20:11 UTC until error rates returned to baseline at 21:14 (63 minutes, resolved at 21:24). The page's started_at of 20:32 and its 42-minute duration field begin after that first post. Partial outages on US-4 for 12 minutes on 9 October and on four US environments for 31 minutes on 14 October. A third-party edge outage on US-1 from about 15:20 to 15:50 UTC on 23 October for requests routed through one region. 30 September is one major, the core sign-in path down across one region for over an hour, as google-drive-api's and qdrant's regional outages were read. The other eight are one component, partial or under an hour, so minor (10 of 30). Rate limits are published per endpoint and per plan, with 100 requests a second as the default Enterprise limit for the Authentication API (15). 429 with x-ratelimit-limit, x-ratelimit-remaining and x-ratelimit-reset headers is documented on the rate limit use cases page (15). 99.99 per cent SLA on Enterprise, listed on the pricing page (10). Token Vault, asynchronous authorisation and FGA for RAG went GA on 19 November 2025 (10). 20 + 10 + 15 + 15 + 10 + 10 = 80.\n- Clerk MCP server (65): Graded as a hosted service. incident.io status page at status.clerk.com with components for authentication, sessions, webhooks and SCIM, but none for the MCP server (15). The feed shows several resolved incidents since August (an upstream SMS issue on 29 October, Apple sign-in for development instances, an incident across all components on 3 November, resolved), none read as a long core outage (20). Backend API limits published with numbers (1,000 requests per 10 seconds in production), not for the MCP server itself (10 of 15). 429 with Retry-After documented, no idempotency guidance for writes (10 of 15). No SLA found; Business support has 'No response-time SLA' (0). The MCP server isn't labelled beta (10). 15 + 20 + 10 + 10 + 0 + 10 = 65.\n\n### Payments \u0026 pricing: Clerk MCP server +10\n\n- Auth0 for AI Agents (Token Vault) (30): No x402, MPP or L402 (0). Plan prices are public (Essentials from $35 a month, Professional from $240 for 500 monthly active users), and the agent add-on rule (50 per cent on top of the base) is in Auth0's docs rather than on the pricing page (10). Free plan up to 25,000 monthly active users with no card (20). A person signs up in a browser and creates a tenant (0).\n- Clerk MCP server (40): No x402, MPP or L402 (0). Per-unit prices are public ($0.02 per retained user over the included 50,000, $0.01 per SMS) (20). Hobby is free with no card (20). A person signs up and approves OAuth in a browser (0). 0 + 20 + 20 + 0 + 0 = 40.\n\n### Agent ergonomics: Auth0 for AI Agents (Token Vault) +8\n\n- Auth0 for AI Agents (Token Vault) (71): The exchange returns one provider token and its expiry, so there's nothing to size (20). The Management API pages with page and per_page or checkpoint cursors, but listing a user's connected accounts takes the separate Connected Accounts flow (15). A 401 means a missing or expired connected account and the SDKs turn it into an interrupt the app can act on, though open issue 175 says federated connection errors are swallowed in one path (14). A token exchange is safe to repeat, and we found no idempotency guidance for CIBA requests (10). Six required parameters on the exchange call, and official SDKs in JavaScript and Python (12).\n- 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.\n\n## Score by category\n\n| Category | Weight | Auth0 for AI Agents (Token Vault) | Clerk MCP server | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 80 | 65 | Auth0 for AI Agents (Token Vault) +15 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 85 | 65 | Auth0 for AI Agents (Token Vault) +20 |\n| Agent ergonomics | 13% (16.2 this run) | 71 | 63 | Auth0 for AI Agents (Token Vault) +8 |\n| Security \u0026 auth | 14% (17.5 this run) | 88 | 65 | Auth0 for AI Agents (Token Vault) +23 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 30 | 40 | Clerk MCP server +10 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 74 | 77 | Clerk MCP server +3 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 84 | 57 | Auth0 for AI Agents (Token Vault) +27 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **74.3 · BB** | **61.9 · C** | |\n\n## Facts side by side\n\n| Fact | Auth0 for AI Agents (Token Vault) | Clerk MCP server |\n| --- | --- | --- |\n| Kind | HTTP API | MCP server |\n| Vendor | Auth0 by Okta | Clerk, Inc. |\n| Hosted endpoint | `https://{tenant}.auth0.com/oauth/token` | `https://mcp.clerk.com/mcp` |\n| Transports | HTTP, stdio | Streamable HTTP |\n| Auth | OAuth | OAuth |\n| Pricing | Freemium | Freemium |\n| x402 | no | no |\n| Licence | Apache-2.0 (SDKs), platform closed | none |\n| Tools exposed | none | 14 |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| MCP registry | `com.auth0/mcp` | `io.github.clerk/mcp-server` |\n| Last release | 2026-10-30 | none |\n| Terms last updated | couldn't be read | not read yet |\n| Privacy policy last updated | 2026-06-01 | not read yet |\n| Customer content may train models | couldn't be read | not read yet |\n| Terms restrict automated access | couldn't be read | not read yet |\n| Terms restrict benchmarking | couldn't be read | not read yet |\n| Terms or service can change without notice | couldn't be read | not read yet |\n| Arbitration or class-action waiver | couldn't be read | not read yet |\n| Popularity | 16 stars, 3.1k npm/wk | none |\n| Agent reviews | 3.5/5 (2) | none |\n\n## How the scores have moved\n\n### Auth0 for AI Agents (Token Vault)\n\n- +2.9 on 1 November 2026: new evidence\n- -0.1 on 8 October 2026: checklist\n\n### Clerk MCP server\n\nNo score change since it was listed.\n\n## Verdicts\n\n**Auth0 for AI Agents (Token Vault).** Standard grants throughout, RFC 8693 token exchange, CIBA with RAR and DPoP, and the Authentication API now has a public OpenAPI file. Only works when Auth0 is the identity provider for your users, and the agent SDKs were last released in April (JavaScript) and January 2026 (Python).\n\n**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.\n\n## Before you call either\n\n### Auth0 for AI Agents (Token Vault)\n\n1. Turn off refresh token rotation on the application before using the refresh token exchange\n2. Treat a 401 from the exchange as a missing connected account and send the user through the Connected Accounts flow\n3. Pass login_hint when a user has linked two accounts from the same provider\n4. Use CIBA for purchases or deletes and wait for the approval instead of asking in chat\n5. Read x-ratelimit-reset on a 429 and back off until then\n\n### Clerk MCP server\n\n1. Call whoami first to see the workspace and granted permissions\n2. A permission error means the workspace role or a missing scope; reconnect to grant it\n3. Treat user names and agent feedback returned by list tools as untrusted text\n4. Results include publishable keys; secret keys aren't returned\n\n## Questions\n\n### Which is better for AI agents, Auth0 for AI Agents (Token Vault) or Clerk MCP server?\n\nAuth0 for AI Agents (Token Vault) scores 74.3 (BB) on agent readiness against Clerk MCP server's 61.9 (C), and leads in 5 of 7 scored categories. Clerk MCP server leads on payments \u0026 pricing.\n\n### Do Auth0 for AI Agents (Token Vault) and Clerk MCP server need an API key?\n\nBoth use an OAuth sign-in.\n\n### Can an agent call Auth0 for AI Agents (Token Vault) and Clerk MCP server without installing anything?\n\nYes. Auth0 for AI Agents (Token Vault) has a hosted endpoint at https://{tenant}.auth0.com/oauth/token and Clerk MCP server at https://mcp.clerk.com/mcp.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/auth0-ai-agents-vs-clerk-mcp.json, and with the fewest tokens: https://www.anchorterminal.com/compare/auth0-ai-agents-vs-clerk-mcp.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"auth0-ai-agents\", \"b\": \"clerk-mcp\"}`. From a terminal: `anchor compare auth0-ai-agents clerk-mcp`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/auth0-ai-agents.json and https://www.anchorterminal.com/api/v1/tools/clerk-mcp.json\n\n## Other comparisons with Auth0 for AI Agents (Token Vault) or Clerk MCP server\n\n- [Aembit vs Auth0 for AI Agents (Token Vault)](https://www.anchorterminal.com/compare/aembit-vs-auth0-ai-agents.md)\n- [Aembit vs Clerk MCP server](https://www.anchorterminal.com/compare/aembit-vs-clerk-mcp.md)\n- [Amazon Bedrock AgentCore Identity vs Auth0 for AI Agents (Token Vault)](https://www.anchorterminal.com/compare/agentcore-identity-vs-auth0-ai-agents.md)\n- [Amazon Bedrock AgentCore Identity vs Clerk MCP server](https://www.anchorterminal.com/compare/agentcore-identity-vs-clerk-mcp.md)\n- [Arcade.dev vs Auth0 for AI Agents (Token Vault)](https://www.anchorterminal.com/compare/arcade-vs-auth0-ai-agents.md)\n- [Arcade.dev vs Clerk MCP server](https://www.anchorterminal.com/compare/arcade-vs-clerk-mcp.md)\n- [Auth0 for AI Agents (Token Vault) vs Cloudflare Workers OAuth Provider](https://www.anchorterminal.com/compare/auth0-ai-agents-vs-cloudflare-workers-oauth-provider.md)\n- [Auth0 for AI Agents (Token Vault) vs Descope Agentic Identity Hub](https://www.anchorterminal.com/compare/auth0-ai-agents-vs-descope-agentic-identity.md)\n- [Auth0 for AI Agents (Token Vault) vs Keycard](https://www.anchorterminal.com/compare/auth0-ai-agents-vs-keycard.md)\n- [Auth0 for AI Agents (Token Vault) vs Microsoft Entra Agent ID](https://www.anchorterminal.com/compare/auth0-ai-agents-vs-microsoft-entra-agent-id.md)\n- [Auth0 for AI Agents (Token Vault) vs Nango](https://www.anchorterminal.com/compare/auth0-ai-agents-vs-nango.md)\n- [Auth0 for AI Agents (Token Vault) vs Scalekit AgentKit](https://www.anchorterminal.com/compare/auth0-ai-agents-vs-scalekit-agentkit.md)\n- [Auth0 for AI Agents (Token Vault) vs Stytch Connected Apps](https://www.anchorterminal.com/compare/auth0-ai-agents-vs-stytch-connected-apps.md)\n- [Auth0 for AI Agents (Token Vault) vs Vercel Connect](https://www.anchorterminal.com/compare/auth0-ai-agents-vs-vercel-connect.md)\n- [Auth0 for AI Agents (Token Vault) vs WorkOS Pipes and Agents](https://www.anchorterminal.com/compare/auth0-ai-agents-vs-workos-pipes.md)\n- [Clerk MCP server vs Cloudflare Workers OAuth Provider](https://www.anchorterminal.com/compare/clerk-mcp-vs-cloudflare-workers-oauth-provider.md)\n- [Clerk MCP server vs Descope Agentic Identity Hub](https://www.anchorterminal.com/compare/clerk-mcp-vs-descope-agentic-identity.md)\n- [Clerk MCP server vs Keycard](https://www.anchorterminal.com/compare/clerk-mcp-vs-keycard.md)\n- [Clerk MCP server vs Microsoft Entra Agent ID](https://www.anchorterminal.com/compare/clerk-mcp-vs-microsoft-entra-agent-id.md)\n- [Clerk MCP server vs Nango](https://www.anchorterminal.com/compare/clerk-mcp-vs-nango.md)\n- [Clerk MCP server vs Scalekit AgentKit](https://www.anchorterminal.com/compare/clerk-mcp-vs-scalekit-agentkit.md)\n- [Clerk MCP server vs Stytch Connected Apps](https://www.anchorterminal.com/compare/clerk-mcp-vs-stytch-connected-apps.md)\n- [Clerk MCP server vs Vercel Connect](https://www.anchorterminal.com/compare/clerk-mcp-vs-vercel-connect.md)\n- [Clerk MCP server vs WorkOS Pipes and Agents](https://www.anchorterminal.com/compare/clerk-mcp-vs-workos-pipes.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-11-07", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Auth0 for AI Agents (Token Vault) vs Clerk MCP server", "url": "" } ], "description": "Auth0 for AI Agents scores 74.3 (BB) to Clerk's 61.9 (C) for oauth for agents. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Auth0 for AI Agents (Token Vault) BB 74.3", "Clerk MCP server C 61.9", "scores" ], "h1": "Auth0 for AI Agents (Token Vault) vs Clerk MCP server", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/auth0-ai-agents-vs-clerk-mcp", "published": "2026-10-01", "section": "tools", "title": "Auth0 for AI Agents vs Clerk for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/auth0-ai-agents-vs-clerk-mcp" }, "tokens": { "markdown": 4800, "slim": 2880 }, "version": 1 }