03 / Scorecard / Auth & Identity

Clerk

Name: Clerk Agent Readiness Scorecard
Item: Clerk
Rating: 54
Author: Headless Index pipeline (auto)

Headless Index

54/100

denominator 80

JAIRF

82.4/100

AI-Ready

Verified

MAY 21, 2026

Methodology v1 · JAIRF v1.0.0

Editorial verdict

Clerk is partially headless and partly UI-led. The Headless Index thesis-fit score of 54/100 puts it mid-table on the index, and JAIRF v1.0.0 puts it at 82.4/100 (Level 3, AI-Ready). In practice, vendors at this tier are partly machine-consumable: the core flows are reachable through code but several adjacent surfaces still expect a human at a dashboard, and the rest of this verdict explains where Clerk lands inside that pattern. On the API surface, the question is whether the API is the product or a layer beneath the dashboard. Clerk is built API-first with the Backend API, the Frontend API, and a deep set of official SDKs across Next.js, React, Vue, Expo, Remix, Astro, Node, Python, Go, and Ruby. The Backend API covers users, sessions, organisations, invitations, JWT verification, and webhooks. The product is shaped around Next.js and React app developers but the underlying API works with any stack.^[1] Schema observability is the related test: can an agent introspect the contract from cold, or does it have to read prose documentation to do so? An agent can drive parts of this product, but not all of it: integrators should plan for human-in-the-loop checkpoints where the headless surface stops short. On headless operability: User CRUD, organisation management, session control, MFA enrolment, invitations, allowlist and blocklist, JWT templates, and webhook configuration are all programmatic. The Clerk Dashboard is one of several surfaces. The clerk-cli adds shell access for local development. Limited Terraform provider coverage is the one administrative gap; most everything else is API-native.^[2] On the MCP and agent-integration axis, which is the fastest-moving criterion in the index: Clerk has not published an official MCP server yet, but the company has demonstrated agent-aware features (the AgentKit-style work in their lab) and the JWT verification primitive is widely used inside MCP-enabled agent stacks for authenticating end users to tools. The protocol layer itself is not first-party.^[3] Event posture closes the loop: an agent that cannot react to state changes is reduced to polling. On webhooks and events, the docs crawler did not locate a webhooks reference page or events catalog. Editorial review should confirm whether the vendor publishes events at all, and if so whether signing and replay are documented. Net assessment: integrators can build agent flows against Clerk, but the rough edge to plan around is schema observability^[4]. Expect to wrap missing pieces in bespoke glue or accept human-in-the-loop checkpoints. Workable but requires scaffolding.

Verdict by Headless Index pipeline (auto)

// AI-drafted from the evidence layer. Editorial review pending.

Scores

Scorecard detail

Headless Index · 5 sub-criteria

API-first design intent10/20

scored

Clerk is built API-first with the Backend API, the Frontend API, and a deep set of official SDKs across Next.js, React, Vue, Expo, Remix, Astro, Node, Python, Go, and Ruby. The Backend API covers users, sessions, organisations, invitations, JWT verification, and webhooks. The product is shaped around Next.js and React app developers but the underlying API works with any stack.

signals (6)

+AI review appliedReviewer: Editorial review on 2026-05-20
+OpenAPI specPublished, 0 operations
−GraphQL endpointNot discovered (5 probes; project-scoped endpoints require a real project ID)
+SDKs maintained8 (dotnet, go, java, javascript, kotlin, php, python, ruby); top by stars: clerk/clerk-sdk-python (182 stars)
+SDK recency8 of 8 SDK repos pushed within 30 days (most recent SDK commit: 2026-05-19)
−npm weekly downloadsNo published npm package detected for the JS/TS SDKs

cite (5)

openapi.probes_tried@2026-05-19
graphql.probes_tried@2026-05-19
github.sdks@2026-05-19
freshness.most_recent_sdk_commit@2026-05-19
github.sdks@2026-05-19

Headless operation8/20

scored

User CRUD, organisation management, session control, MFA enrolment, invitations, allowlist and blocklist, JWT templates, and webhook configuration are all programmatic. The Clerk Dashboard is one of several surfaces. The clerk-cli adds shell access for local development. Limited Terraform provider coverage is the one administrative gap; most everything else is API-native.

signals (9)

+AI review appliedReviewer: Editorial review on 2026-05-20
−API operations exposedOpenAPI present but operations could not be counted
·Docs pages crawled0 pages (crawler: none)
·Auth schemes documentedAuth documentation page not reached by crawler
·Setup / quickstart docsNot reached by crawler
·Billing docsNot reached by crawler
·Teams / org docsNot reached by crawler
·CLI docsNot reached by crawler
·Schema / data model docsNot reached by crawler

cite (1)

ai_review_browser.topics_found@2026-05-20

MCP & agent posture20/20

scored

Clerk has not published an official MCP server yet, but the company has demonstrated agent-aware features (the AgentKit-style work in their lab) and the JWT verification primitive is widely used inside MCP-enabled agent stacks for authenticating end users to tools. The protocol layer itself is not first-party.

signals (4)

+AI review appliedReviewer: Editorial review on 2026-05-20
+Official MCP serverhttps://github.com/clerk/mcp-express-example (5 stars, last commit 1 days ago)
·Community MCP servers2 community MCP repos; top by stars: https://github.com/clerk/mcp-tools (42 stars)
+Agent-friendly SDKs1 TS/JS SDKs available; top: clerk-oauth-test-client

cite (1)

ai_review_browser.mcp@2026-05-20

Schema observability5/20

scored

REST documentation is detailed; a public OpenAPI URL is not the central artifact, but the SDKs are auto-generated from internal definitions and the @clerk/clerk-sdk-node package is the canonical client. Cold schema discovery requires docs context.

signals (3)

+AI review appliedReviewer: Editorial review on 2026-05-20
+OpenAPIPublished at https://raw.githubusercontent.com/clerk/openapi-specs/main/bapi/2024-10-01.yml (OpenAPI undefined, 0 operations)
−GraphQL introspectionNo GraphQL endpoint discovered (5 probes; some vendors use project-scoped endpoints that require a real project handle)

cite (2)

openapi.probes_tried@2026-05-19
graphql.probes_tried@2026-05-19

Webhooks & eventsUnknown

Unknown

Clerk webhooks deliver session, user, organisation, and invitation events with HMAC signing via the svix delivery system. Event catalog is comprehensive for the identity lifecycle and replay through the Clerk Dashboard is one click away. This is reference-class webhook behaviour for the auth category.

signals (2)

+AI review appliedReviewer: Editorial review on 2026-05-20
·Webhook docs pageNot reached by crawler within budget (0 pages crawled). Cannot confirm whether vendor offers webhooks.

cite (1)

docs.pages_crawled@2026-05-19

JAIRF · 6 dimensions

FCFoundational Compliance

100/100

Structural validity, standards conformance, and parsability of the OpenAPI specification.

DXJDeveloper Experience & Tooling Compatibility

68.3/100

Documentation clarity, example coverage, response completeness, and ingestion health.

ARAXAI-Readiness & Agent Experience

60.8/100

Semantic clarity, intent expression, datatype specificity, and error standardization.

AUAgent Usability

90/100

Operational composability, complexity comfort, navigation affordances, and safety patterns.

SECSecurity

80/100

Authentication strength, transport security, secret hygiene, and OWASP risk posture.

AIDAI Discoverability

100/100

Descriptive richness, intent phrasing, workflow context, and registry signals.

Band rationale:C band: scores 40-75 range

04 / Embed

Show Clerk's score on your site.

Drop a live badge into your README, footer, or marketing page. It updates automatically when we re-score, and every embed is a dofollow link back here.

Get embed code

Calibration

How THI compares to external scorers

Source	Score	Measures	Last checked
Fern Agent Score	not found	Documentation completeness and SDK shape (~22 checks)	—
CLIRank Agent Friendliness	70 · Good	CLI readiness, docs quality, and overall agent affordances	—
Cloudflare Is It Agent Ready?	blocked	Cloudflare's manual agent-readiness heuristic per vendor URL	—
Jentic Scorecard	n a	JAIRF-based scorecard requiring a public OpenAPI specification	—

THI 54 vs external median 70, delta -16

THI display 54 vs external median 70 (delta -16). Within calibration band.

Peers in Auth & Identity

SuperTokensC

Headless Index 54/100

AuthsignalC

Headless Index 54/100

StytchC

Headless Index 52/100

See full Auth & Identity ranking →