Clerk
REMOTE · MCP.CLERK.COM
Access Clerk authentication docs, SDK snippets, and quickstart guides
Available components
Last scanned (19 hours ago)
Scores higher than 59% of remote servers
Reachable. Last reached 21 Nov 2026.
Category Developer Tools
Recent critical change
Authorization (9 Oct 2026). See the changelog before you install this server.
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security81
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token. View diagnostics → Pass
- HTTPS enforcement could not be verified: the plaintext port answered with HTTP 421, which proves neither a plaintext path nor enforcement. View diagnostics → Unverified
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
- The authorisation server supports Client ID Metadata Documents, the current MCP client-registration mechanism. View diagnostics → Pass
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability77
- 89% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Partial
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 9481 tokens (~137/item across 69 items; 42 tools + 27 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
- Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage98
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 92% of tool parameters carry a description.Partial
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety75
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "get_deploy_oauth_providers" implies "deploy" and declares readOnlyHint instead, contradicting what its own name says it does. See how to fix → Fail
- An AI judge read all 44 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
- Supports UI / widget rendering.Pass
Unverified: 1 category
A category scored 0 because we could not verify it: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm.
Checks we ran (12)
- TLS certificate
- Authorization
- HSTS header
- DNSSEC
- Transport
- Schema quality
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
- Capabilities
Checks we could not complete (2)
These are gaps on our side, not findings about this hosted endpoint. We only credit what we can confirm, so a category made up entirely of them scores 0.
- HTTPS in Endpoint SecurityHTTPS enforcement could not be verified: the plaintext port answered with HTTP 421, which proves neither a plaintext path nor enforcement.
- Stability in Stability & Change Management (scores 0 for this)Stability not yet verified: not enough scan history yet (needs a 30-day window).
Does not apply to this hosted endpoint (2)
- Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
- Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 21 Nov 26 +41
- A breaking change shipped without a version bump: still 0.0.0 ▼ security
- Tool “disable_billing” was removed ▼ security
- Tool “disable_organizations” was removed ▼ security
- Tool “enable_billing” was removed ▼ security
- Tool “enable_organizations” was removed ▼ security
- Tool “set_oauth_provider_credentials” was removed ▼ security
- Transport: unverified → pass ▲ security
- Injection markers: unverified → pass ▲ security
- Authorization: Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token. security
- The server rewrote its instructions, which are the text every model session reads security
- New tool “configure_mcp_server”, which the server declares destructive security
- New tool “update_user_metadata”, which the server declares destructive security
- Tool “check_domain_dns” rewrote its description, which is the text the model reads security
- Tool “clerk_sdk_snippet” rewrote its description, which is the text the model reads security
- Tool “create_application” rewrote its description, which is the text the model reads security
- Tool “create_production_instance” rewrote its description, which is the text the model reads security
- Tool “create_user” rewrote its description, which is the text the model reads security
- Tool “get_application” rewrote its description, which is the text the model reads security
- Tool “get_domain_status” rewrote its description, which is the text the model reads security
- Tool “get_instance_config” rewrote its description, which is the text the model reads security
- Tool “get_instance_config_schema” rewrote its description, which is the text the model reads security
- Tool “list_applications” rewrote its description, which is the text the model reads security
- Tool “list_clerk_sdk_snippets” rewrote its description, which is the text the model reads security
- Tool “list_domains” rewrote its description, which is the text the model reads security
- Tool “list_users” rewrote its description, which is the text the model reads security
- Tool “patch_instance_config” rewrote its description, which is the text the model reads security
- Tool “put_instance_config” rewrote its description, which is the text the model reads security
- Tool “submit_feedback” rewrote its description, which is the text the model reads security
- Tool “whoami” rewrote its description, which is the text the model reads security
- Destructive annotations: 50% → 0% ▼ functional
- Schema quality: pass → fail ▼ functional
- “submit_feedback” added a required parameter “description”, so existing callers break ▼ functional
- “submit_feedback” added a required parameter “kind”, so existing callers break ▼ functional
- “submit_feedback” added a required parameter “task”, so existing callers break ▼ functional
- “submit_feedback” dropped the required parameter “attempted” ▼ functional
- “submit_feedback” dropped the required parameter “goal” ▼ functional
- “submit_feedback” dropped the required parameter “issue” ▼ functional
- “submit_feedback” dropped the required parameter “outcome” ▼ functional
- Resource “<OrganizationSwitcher> Component” was removed ▼ functional
- Resource “<Protect> Component (Deprecated)” was removed ▼ functional
- Resource “<Show> Component” was removed ▼ functional
- Resource “<UserButton> Component” was removed ▼ functional
- Resource “Astro Quickstart” was removed ▼ functional
- Resource “B2B SaaS Setup Guide” was removed ▼ functional
- Resource “Billing Integration (Stripe)” was removed ▼ functional
- Resource “Clerk Backend SDK” was removed ▼ functional
- Resource “Expo (React Native) Quickstart” was removed ▼ functional
- Resource “Express.js Quickstart” was removed ▼ functional
- Resource “Go Quickstart” was removed ▼ functional
- Resource “Next.js 15 App Router Quickstart” was removed ▼ functional
- Resource “React (Vite) Quickstart” was removed ▼ functional
- Resource “Remix Quickstart” was removed ▼ functional
- Resource “Server-Side Auth (Next.js App Router)” was removed ▼ functional
- Resource “Waitlist Setup” was removed ▼ functional
- Resource “useAuth hook” was removed ▼ functional
- Resource “useClerk hook” was removed ▼ functional
- Resource “useOrganization hook” was removed ▼ functional
- Resource “useOrganizationList hook” was removed ▼ functional
- Resource “useSession hook” was removed ▼ functional
- Resource “useSignIn hook” was removed ▼ functional
- Resource “useSignUp hook” was removed ▼ functional
- Resource “useUser hook” was removed ▼ functional
- Endpoint reachability: behind authorisation → reachable ▲ functional
- Tool coverage: 9% → 100% ▲ functional
- Schema quality: unverified → 89 ▲ functional
- MCP protocol: unverified → pass ▲ functional
- Tool coverage: unverified → 100 ▲ functional
- Tool “check_domain_dns” now declares an output schema ▲ functional
- Tool “create_application” now declares an output schema ▲ functional
- Tool “create_production_instance” now declares an output schema ▲ functional
- Tool “create_user” now declares an output schema ▲ functional
- Tool “get_application” now declares an output schema ▲ functional
- Tool “get_deploy_oauth_providers” now declares an output schema ▲ functional
- Tool “get_domain_status” now declares an output schema ▲ functional
- Tool “get_instance_config” now declares an output schema ▲ functional
- Tool “get_instance_config_schema” now declares an output schema ▲ functional
- Tool “list_applications” now declares an output schema ▲ functional
- Tool “list_domains” now declares an output schema ▲ functional
- Tool “list_users” now declares an output schema ▲ functional
- Tool “patch_instance_config” now declares an output schema ▲ functional
- Tool “put_instance_config” now declares an output schema ▲ functional
- Tool “submit_feedback” now declares an output schema ▲ functional
- Tool “whoami” now declares an output schema ▲ functional
- First check of Capabilities: pass functional
- New resource “Clerk organization” functional
- New resource “Clerk user” functional
- New resource “Clerk users” functional
- New tool “check_mcp_server” functional
- New tool “create_android_application” functional
- New tool “create_browser_session” functional
- New tool “create_ios_application” functional
- New tool “create_redirect_url” functional
- New tool “create_support_ticket” functional
- New tool “enable_native_api” functional
- New tool “get_organization” functional
- New tool “get_support_ticket” functional
- New tool “get_user” functional
- New tool “list_application_feedback” functional
- New tool “list_log_group_events” functional
- New tool “list_logs” functional
- New tool “list_native_applications” functional
- New tool “list_organization_memberships” functional
- New tool “list_organizations” functional
- New tool “list_redirect_urls” functional
- New tool “list_support_tickets” functional
- New tool “list_user_organization_memberships” functional
- New tool “reply_to_support_ticket” functional
- New tool “update_application” functional
- New tool “update_user” functional
- “create_application” added an optional parameter “recipient_public_key” cosmetic
- “create_production_instance” added an optional parameter “recipient_public_key” cosmetic
- “create_user” added an optional parameter “skip_password_requirement” cosmetic
- “list_users” added an optional parameter “banned” cosmetic
- “list_users” added an optional parameter “created_at_after” cosmetic
- “list_users” added an optional parameter “created_at_before” cosmetic
- “list_users” added an optional parameter “deprovisioned” cosmetic
- “list_users” added an optional parameter “email_address_query” cosmetic
- “list_users” added an optional parameter “last_active_at_after” cosmetic
- “list_users” added an optional parameter “last_active_at_before” cosmetic
- “list_users” added an optional parameter “last_active_at_since” cosmetic
- “list_users” added an optional parameter “last_sign_in_at_after” cosmetic
- “list_users” added an optional parameter “last_sign_in_at_before” cosmetic
- “list_users” added an optional parameter “name_query” cosmetic
- “list_users” added an optional parameter “organization_id” cosmetic
- “list_users” added an optional parameter “phone_number_query” cosmetic
- “list_users” added an optional parameter “provider” cosmetic
- “list_users” added an optional parameter “provider_user_id” cosmetic
- “list_users” added an optional parameter “username_query” cosmetic
- “list_users” added an optional parameter “web3_wallet” cosmetic
- “submit_feedback” added an optional parameter “error” cosmetic
- “submit_feedback” added an optional parameter “impact” cosmetic
- “submit_feedback” added an optional parameter “operation” cosmetic
- “check_domain_dns” reworded the description of “domain” cosmetic
- “create_application” reworded the description of “name” cosmetic
- “create_application” reworded the description of “template” cosmetic
- “create_production_instance” reworded the description of “confirm” cosmetic
- “create_user” reworded the description of “external_id” cosmetic
- “create_user” reworded the description of “first_name” cosmetic
- “create_user” reworded the description of “last_name” cosmetic
- “create_user” reworded the description of “username” cosmetic
- “get_domain_status” reworded the description of “domain” cosmetic
- “get_instance_config” reworded the description of “keys” cosmetic
- “get_instance_config_schema” reworded the description of “keys” cosmetic
- “list_clerk_sdk_snippets” reworded the description of “tag” cosmetic
- “list_users” reworded the description of “external_id” cosmetic
- “list_users” reworded the description of “offset” cosmetic
- “list_users” reworded the description of “order_by” cosmetic
- “list_users” reworded the description of “query” cosmetic
- “list_users” reworded the description of “user_id” cosmetic
- “patch_instance_config” reworded the description of “config” cosmetic
- “patch_instance_config” reworded the description of “destructive” cosmetic
- “put_instance_config” reworded the description of “config” cosmetic
- “put_instance_config” reworded the description of “destructive” cosmetic
- “create_user” dropped the optional parameter “body” cosmetic
- “create_user” dropped the optional parameter “password” cosmetic
- “submit_feedback” dropped the optional parameter “error_text” cosmetic
- “submit_feedback” dropped the optional parameter “tool_name” cosmetic
- Tool “submit_feedback” changed its title: Send feedback to Clerk → Send feedback cosmetic
- 6 Nov 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 10 Oct 26 0
- Endpoint reachability: reachable → behind authorisation ▼ security
- Stability: pass → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Transport: pass → unverified ▼ security
- Authorization: fail → pass ▲ security
- First check of Authorization: pass security
- Capabilities: pass → unverified ▼ functional
- Schema quality: 50 → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- 9 Oct 26 0
- Authorization: partial → fail ▼ critical
- New tool “create_production_instance”, which the server declares destructive security
- New tool “patch_instance_config”, which the server declares destructive security
- New tool “put_instance_config”, which the server declares destructive security
- New tool “set_oauth_provider_credentials”, which the server declares destructive security
- Tool coverage: 100% → 9% ▼ functional
- Tool coverage: 100% → 94% ▼ functional
- Schema quality: 13 → 38 ▼ functional
- Schema quality: good → excellent functional
- Destructive annotations: pass → 50 functional
- New tool “check_domain_dns” functional
- New tool “create_application” functional
- New tool “create_user” functional
- New tool “disable_billing” functional
- New tool “disable_organizations” functional
- New tool “enable_billing” functional
- New tool “enable_organizations” functional
- New tool “get_application” functional
- New tool “get_deploy_oauth_providers” functional
- New tool “get_domain_status” functional
- New tool “get_instance_config” functional
- New tool “get_instance_config_schema” functional
- New tool “list_applications” functional
- New tool “list_domains” functional
- New tool “list_users” functional
- New tool “submit_feedback” functional
- New tool “whoami” functional
- 28 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 25 Sept 26 0
First indexed and scored.
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 21 Nov 2026 · Probed https://mcp.clerk.com/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=mcp.clerk.com | CN=YE1,O=Let's Encrypt,C=US | 28 Oct 2026 | 26 Jan 2027 | ECDSA 256 | ECDSA-SHA384 | 6fd0c9014602ceeeca3a9d3a46ff4360379 |
| SANs: mcp.clerk.com | ||||||
| CN=YE1,O=Let's Encrypt,C=US (CA) | CN=Root YE,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | ECDSA 384 | ECDSA-SHA384 | 5ddd70dd31f801c85c186a7a04b80afe |
| CN=Root YE,O=ISRG,C=US (CA) | CN=ISRG Root X2,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | ECDSA-SHA384 | 872165fc34b6e5fba8add5b3705fb53a |
| CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | SHA256-RSA | 6c8f1dc727c7117f7baf853ac980f9cd |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of mcp.clerk.com. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | Trust anchor | 20326, 38696 | 8, 8 | Verified |
| com. | DS published | 19718 | 13 | Verified |
| clerk.com. | No DS | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication Enforced and verified
The endpoint asked for a token and published valid RFC 9728 metadata describing how to get one.
| Result | Enforced and verified |
|---|---|
| Enforced | On tool calls |
| HTTP status | 200 |
WWW-Authenticate challenge Bearer resource_metadata="https://mcp.clerk.com/.well-known/oauth-protected-resource/mcp", scope="user:org:read applications:read applications:manage users:read users:manage application_logs:read organizations:read application_domains:read application_domains:manage support_tickets:manage"
Bearer resource_metadata="https://mcp.clerk.com/.well-known/oauth-protected-resource/mcp", scope="user:org:read applications:read applications:manage users:read users:manage application_logs:read organizations:read application_domains:read application_domains:manage support_tickets:manage" Protected resource metadata
| Document | https://mcp.clerk.com/.well-known/oauth-protected-resource/mcp |
|---|---|
| Retrieved | Yes |
| Resource | https://mcp.clerk.com/mcp |
| Authorisation server | https://clerk.clerk.com |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://mcp.clerk.com/mcp | Verified | 200 | |
| http (plaintext) | http://mcp.clerk.com/mcp | Inconclusive | 421 |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
update_user_metadata Update user metadata ~252
Deep-merge public, private or unsafe metadata into an instance's user. Existing nested objects merge recursively and null-valued keys are removed at merged levels. New or replacement nested objects are copied as-is, including nulls, matching BAPI. Repeating such a patch can change its result. Arrays replace existing arrays. Omitted fields and top-level null leave metadata unchanged. Returns only a confirmation, never metadata values. With dry_run, returns the target and supplied metadata categories without writing or showing values.
| Name | Type | Req | Description |
|---|---|---|---|
| application_id | string | yes | Clerk application ID (app_…). |
| dry_run | boolean | – | Preview the target and metadata categories without writing or returning values. |
| instance | string | yes | Instance to target: "development", "production", or a full instance ID (ins_…). |
| private_metadata | – | – | Private metadata merge patch, available only through backend APIs. Never returned by this tool. |
| public_metadata | – | – | Public metadata merge patch, visible to the frontend. Limit 8 KB per field. |
| unsafe_metadata | – | – | Unsafe metadata merge patch, also writable by the user through frontend APIs. |
| user_id | string | yes | Clerk user ID (user_…) in the selected instance. |
| Name | Type | Req | Description |
|---|---|---|---|
| dry_run | boolean | – | – |
| metadata_fields | array | – | – |
| updated | boolean | – | – |
| user_id | string | yes | – |
No examples provided.
whoami Who am I ~48
Show who this connection acts as (like `clerk whoami`): the Clerk user ID, the workspace ID, the MCP client's OAuth client ID, and the OAuth scopes the connection was granted.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| oauth_client_id | string | yes | – |
| scopes | array | yes | – |
| user_id | string|null | yes | – |
| workspace_id | string | yes | – |
No examples provided.
How do I install the Clerk MCP server?
Clerk is a hosted endpoint at https://mcp.clerk.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · mcp.clerk.com
claude mcp add --transport http clerk-mcp-server 'https://mcp.clerk.com/mcp'
What is the Clerk MCP server?
Clerk is an MCP server listed in the public MCP registry as io.github.clerk/mcp-server. Access Clerk authentication docs, SDK snippets, and quickstart guides. This page covers its hosted endpoint (https://mcp.clerk.com/mcp).
Is the Clerk MCP server safe to use?
Clerk scores 73 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Clerk MCP server expose?
Clerk exposes 42 tools: clerk_sdk_snippet, list_clerk_sdk_snippets, whoami, create_browser_session, submit_feedback, and 37 more. Their descriptions and schemas cost roughly 8,943 tokens of context every time the server is loaded.
Does the Clerk MCP server require authentication?
Yes. Clerk asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.
Is the Clerk MCP server still maintained?
Clerk is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What did VerifyMCP test on the Clerk MCP server?
VerifyMCP ran 12 checks on Clerk, covering TLS certificate, Authorization, HSTS header, DNSSEC and 8 more. 2 items could not be completed, a gap on our side rather than a finding about Clerk: HTTPS and Stability. One category scores 0 for that reason, because we only credit what we can confirm. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.