Clerk MCP integration for AI agents.

Connect AI agents to Clerk through 11 structured actions, including count users, create user, ban user, and lock user. Review authentication, inputs, workflo…

ACTION CONTRACTS
11
AUTHENTICATION
API key
SOURCE STATUS
Provider-backed

CATALOG SOURCE REVIEWED AUGUST 23, 2026 / ACTION NAMES AND SCHEMAS DERIVED FROM WORKING MACHINES PROVIDER SOURCE

CAPABILITY PROFILE

What the Clerk integration exposes

The Clerk Agent App exposes 11 provider-backed actions for security and developer tools work. Its current contract lets an authorized agent count clerk users with optional filters, create a clerk user, and ban a clerk user. These operations are called through Working Machines as typed capabilities rather than through browser navigation or copied UI steps.

A connection uses API key. Before execution, the agent can inspect the selected action, its required fields, declared scopes, and expected output contract. Provider credentials remain inside the Working Machines runtime; the calling agent receives the capability and its structured result, not the underlying secret.

For reliable operation, start with the narrowest action that satisfies the task, resolve stable provider identifiers before changing state, and validate the returned object or status after execution. Availability still depends on the connected Clerk account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.

VERIFIED ACTION SAMPLE

Real Clerk capabilities.

Showing 11 of 11 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.

count_usersREAD

Count Clerk users with optional filters.

INPUTS: email_address / phone_number / username / user_id / external_id

create_userWRITE

Create a Clerk user.

INPUTS: email_address / phone_number / web3_wallet / external_id / first_name

ban_userHIGH IMPACT

Ban a Clerk user.

INPUTS: user_id

lock_userREVIEW

Lock a Clerk user.

INPUTS: user_id

delete_userHIGH IMPACT

Delete a Clerk user.

INPUTS: user_id

get_userREAD

Retrieve a Clerk user by ID.

INPUTS: user_id

list_usersREAD

List Clerk users with optional filtering and pagination.

INPUTS: email_address / phone_number / username / user_id / external_id

unban_userREVIEW

Unban a Clerk user.

INPUTS: user_id

unlock_userREVIEW

Unlock a Clerk user.

INPUTS: user_id

update_userWRITE

Update a Clerk user.

INPUTS: user_id / first_name / last_name / primary_email_address_id / primary_phone_number_id

update_user_metadataWRITE

Deep merge metadata for a Clerk user.

INPUTS: user_id / public_metadata / private_metadata / unsafe_metadata

INPUT CONTRACTS

Know what the action needs before it runs.

count_users

email_addressOPTIONAL
A list of string values used by Clerk filters.
phone_numberOPTIONAL
A list of string values used by Clerk filters.
usernameOPTIONAL
A list of string values used by Clerk filters.
user_idOPTIONAL
A list of string values used by Clerk filters.
external_idOPTIONAL
A list of string values used by Clerk filters.

create_user

email_addressOPTIONAL
Email addresses to add to the new user.
phone_numberOPTIONAL
Phone numbers to add to the new user.
web3_walletOPTIONAL
Web3 wallet addresses to add to the new user.
external_idOPTIONAL
An external ID for the user.
first_nameOPTIONAL
The user's first name.

ban_user

user_idREQUIRED
The Clerk user ID.

lock_user

user_idREQUIRED
The Clerk user ID.

PROVIDER-SPECIFIC WORKFLOWS

Jobs this Agent App can support

Inspect Count Users

Count Clerk users with optional filters. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.

count_users

Control Create User

Create a Clerk user. Resolve the target first, present material changes for confirmation, and make retries idempotent where the provider supports it.

create_user

Verify with Get User

Retrieve a Clerk user by ID. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.

get_user

SAFETY BOUNDARY

Operate Clerk with explicit limits

  • Authorize Clerk with API key and grant only the provider access required by the selected actions.
  • 5 actions are change-capable by name. Confirm the target identity and material parameters before allowing a write.
  • Treat `ban_user` and `delete_user` as high-impact operations and require an explicit approval boundary.
  • No provider scope string is declared on the sampled actions. Verify the connected account's actual permissions in Clerk rather than assuming unrestricted access.
  • After a call, inspect the structured result and execution record before reporting that the Clerk task completed successfully.

CONNECTION MODEL

API key

Clerk secret key used with the Authorization Bearer header. Create or reveal it in the Clerk Dashboard API keys page: https://dashboard.clerk.com/last-active?path=api-keys

Working Machines stores provider credentials behind the execution boundary. An agent can use an authorized connection identity, but catalog discovery alone does not reveal OAuth tokens, API keys, or provider secrets.

READ SIGNALS
3
WRITE SIGNALS
3
HIGH IMPACT
2
REVIEW SIGNALS
3

EVIDENCE AND AVAILABILITY

Provider reference

Action names, input fields, authentication types, and counts on this page are generated from the Working Machines provider catalog. Provider behavior, quotas, object semantics, account eligibility, and regional availability remain governed by Clerk.

Official Clerk website

ONE CONNECTION. REAL WORK.

Give your agent software it can use.

Connect through MCP or explore the Agent App catalog and choose only the capabilities your workflow needs.

EXPLORE AGENT APPS