Skip to content

Connectors · Identity & security

OneLogin MCP server for AI agents.

actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to OneLogin and the rest of your systems. It gives your agent 200 OneLogin actions (85 reads, 78 writes and 37 that wait for a confirmation) and holds the OneLogin credential itself, so the agent never does. It paces OneLogin's limits and records every call.

100,000 free calls a month. No card, no email, no password: press Start a free sandbox on the next screen and keep the key it shows you.

claude mcp add --transport http actionlake https://connect.actionlake.com/mcp
the first call
do {  action: "onelogin.users.list",  intent: "check which OneLogin account is connected"}# List users · read · 1 upstream call
  • 200actionsin one signed file
  • 85readlook, never change
  • 78writecreate and update
  • 37wait for a yesdestructive, confirmed first

Set up

Connect OneLogin in three steps.

  1. 01

    Add actionlake to Claude.

    Run the command once in Claude Code; its consent page can create a free sandbox: 100,000 calls a month, no card. In the Claude app, add a custom connector with the URL below and paste your key on the consent page. Creating a new sandbox from the Claude app is not yet tested by us.

    https://connect.actionlake.com/mcp
  2. 02

    Connect OneLogin.

    OAuth 2.0, client credentials. Paste the app's client id and secret; actionlake fetches and renews the token, and nobody has to sign in. actionlake stores what you paste write-only, sealed under your tenant's key.

    • client_idClient ID of a OneLogin API credential (Administration > Developers > API Credentials > New Credential)
    • client_secretClient secret of that API credential
    • hostWhere your OneLogin lives: your host
    account { op: "connections.requirements", service: "onelogin" }
    # free: exactly what to paste, and what is found for you
  3. 03

    Make the first call. Check before a write.

    Ask in plain words; Claude picks the action. Before anything changes, check validates the call and prices it, for free.

    do    { action: "onelogin.users.list" }# list users · read · 1 upstream callcheck { action: "onelogin.users.create", input: { … } }# free: inputs, permissions, cost and confirmations, nothing sent

OneLogin at a glance

Sign-in
OAuth 2.0, client credentials. Paste the app's client id and secret; actionlake fetches and renews the token, and nobody has to sign in.
You provide
client_idclient_secret
Setup fields
host
Limits we pace to
5,000 calls an hour, per connection
API covered
OneLogin API v2 with the v1-only operations (developers.onelogin.com, fetched 2026-10-23), at your OneLogin instance's API base URL, which you enter when connecting
Built from
OneLogin's documentation, read 23 October 2026developers.onelogin.comGitHub
Service file
Version 1.0.0, signed (Ed25519)
Cached reads
81 of 85 reads, for up to an hour; a write clears what it affects
Shared entities
4, so ask can line OneLogin up with your other systems
Data
Processed and stored in Sydney, Australia. No US region yet

Capabilities

What an AI agent can do in OneLogin.

200 actions in 37 areas. Every one carries its effect, so a key can allow the reads and hold the rest.

  • 85readlook, never change
  • 78writecreate and update
  • 37destructivewait for a confirmation
  1. Roles

    13

    5 read · 2 write · 6 destructive

    List roles · Create role · Get role · Update role

  2. Mappings

    12

    7 read · 4 write · 1 destructive

    Create mapping · Dry run mapping · List mappings · List mapping action values

  3. App rules

    11

    7 read · 3 write · 1 destructive

    Create app rule · List app rules · List app rule action values · List app rule actions

  4. Privileges

    11

    4 read · 2 write · 5 destructive

    Assign privilege to roles · Assign privilege to users · Create privilege · List privileges

  5. Message templates

    10

    6 read · 3 write · 1 destructive

    Create message template · List message templates · Get message template · Get message template by type

  6. Mfa

    10

    4 read · 5 write · 1 destructive

    Activate a factor (start a verification) · Enroll a factor · Generate MFA token · Get available factors

  7. Users

    10

    5 read · 4 write · 1 destructive

    List users · Create user · Get user · Update user

  8. Users V1

    10

    2 read · 7 write · 1 destructive

    Lock user account (v1) · Assign roles to user (v1) · Get custom attribute names (v1) · Get roles for user (v1)

29 more areas · 113 actions
  • Apps 7
  • Mfa V1 7
  • Self registration profiles 7
  • Brands 6
  • Hooks 6
  • Policies 6
  • Accounts 5
  • API authorizations 5
  • Custom attributes 5
  • Custom messages 5
  • Groups 5
  • Hook env vars 5
  • Risk rules 5
  • API authorization claims 4
  • API authorization clients 4
  • API authorization scopes 4
  • Oath tokens 4
  • Email settings 3
  • Reports 3
  • Risk 3
  • Events 2
  • Invites 2
  • Login 2
  • Saml assertions 2
  • Smart mfa 2
  • Authentication factors 1
  • Connectors 1
  • Event types 1
  • Rate limit 1

Top actions

The OneLogin API, shaped for agents.

The ids your agent types, what each does, and the one name it shares with other systems. 43 of OneLogin's 43 action names are shared with at least one other connector, so an agent learns them once.

ActionWhat it doesEffectSame name in
onelogin.users.listList usersList users.readidentity.user.list474 connectors
onelogin.groups.listList groupsList groups.readidentity.group.list262 connectors
onelogin.roles.listList rolesList roles.readidentity.role.list184 connectors
onelogin.users.createCreate userCreate user.writeidentity.user.create262 connectors
onelogin.apps.listList appsList apps.readidentity.application.list37 connectors
onelogin.groups.createCreate groupCreate group.writeidentity.group.create205 connectors
onelogin.roles.createCreate roleCreate role.writeidentity.role.create105 connectors
onelogin.apps.createCreate appCreate app.writeidentity.application.create27 connectors
onelogin.events.listList eventsList events.readidentity.audit_event.list51 connectors
onelogin.roles.list_usersGet role usersGet role users.readidentity.role_assignment.list41 connectors
onelogin.roles.remove_usersRemove role usersRemove role users.destructiveidentity.role_assignment.remove34 connectors
onelogin.apps.list_usersList app usersList app users.readidentity.application_assignment.list5 connectors

Try it

Prompts to paste into Claude.

Each one names the OneLogin actions it will call, so you know what it reads and what it changes before you send it.

  1. Readread

    Who has access in OneLogin? List every user and their role.

    callsonelogin.users.list

  2. Writewrite

    Create user in OneLogin. Show me exactly what you will send before you save it.

    callsonelogin.users.create

Governance for OneLogin

Destructive actions wait for a yes.

37 OneLogin actions are destructive. The first 10:

  • Delete useronelogin.users.delete
  • Delete grouponelogin.groups.delete
  • Delete roleonelogin.roles.delete
  • Delete apponelogin.apps.delete
  • Remove role usersonelogin.roles.remove_users
  • Assign roles to user (v1)onelogin.users_v1.add_roles
  • Delete security policyonelogin.policies.delete
  • Delete authorization serveronelogin.api_authorizations.delete
  • Add role usersonelogin.roles.add_users
  • Add role adminsonelogin.roles.add_admins

A destructive action runs only with confirm: true. Under the human policy the agent cannot confirm for itself: the run stops until a named person approves, in the console or from a signed link in an email. The cap on a key is refused before the call is sent, never after.

doonelogin.users.deleteconfirm_policy: human

Delete user?

intent: the user asked me to delete user

run suspended · waiting for a named person · key onelogin-agent cannot confirm itself
In the console, or from an emailed signed link.
a key for this connector
account {  op: "keys.create", name: "onelogin-agent",  allowed_actions: ["onelogin.*"], cap_calls: 2000,  confirm_policy: "human_for_writes",  approval_rules: [    { match: "onelogin.users.delete", approver: "[email protected]" },    { match: "onelogin.groups.delete", approver: "[email protected]" },    { match: "onelogin.roles.delete", approver: "[email protected]" }  ]}
Illustrative. Scoped to OneLogin only, capped at 2,000 upstream calls, every write confirmed, and the destructive ones approved by a named person.

Cost

What OneLogin costs on actionlake.

Every OneLogin action is one upstream call, the only thing actionlake bills. Searching, check, cost, account and any call OneLogin refused with 401, 403, 429 or a 5xx are free. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000.

  • 1upstream call per actionall 200 OneLogin actions
  • 200actions pageeach page of a long list is one call
  • 81reads can be cacheda cache hit costs nothing
  • 100,000calls a month, freepaid plans from US$49 a month for 250,000

See pricing

Action index

Every OneLogin action.

200 actions by area: the id your agent calls, what it does, and its effect.

Roles13
  • onelogin.roles.add_adminsAdd role adminsdestructive
  • onelogin.roles.add_usersAdd role usersdestructive
  • onelogin.roles.createCreate rolewrite
  • onelogin.roles.deleteDelete roledestructive
  • onelogin.roles.getGet roleread
  • onelogin.roles.listList rolesread
  • onelogin.roles.list_adminsGet role adminsread
  • onelogin.roles.list_appsGet role appsread
  • onelogin.roles.list_usersGet role usersread
  • onelogin.roles.remove_adminsRemove role adminsdestructive
  • onelogin.roles.remove_usersRemove role usersdestructive
  • onelogin.roles.set_appsSet role appsdestructive
  • onelogin.roles.updateUpdate rolewrite
Mappings12
  • onelogin.mappings.createCreate mappingwrite
  • onelogin.mappings.deleteDelete mappingdestructive
  • onelogin.mappings.dry_runDry run mappingwrite
  • onelogin.mappings.getGet mappingread
  • onelogin.mappings.listList mappingsread
  • onelogin.mappings.list_action_valuesList mapping action valuesread
  • onelogin.mappings.list_actionsList mapping actionsread
  • onelogin.mappings.list_condition_operatorsList mapping condition operatorsread
  • onelogin.mappings.list_condition_valuesList mapping condition valuesread
  • onelogin.mappings.list_conditionsList mapping conditionsread
  • onelogin.mappings.sortBulk sort mappingswrite
  • onelogin.mappings.updateUpdate mappingwrite
App rules11
  • onelogin.app_rules.createCreate app rulewrite
  • onelogin.app_rules.deleteDelete app ruledestructive
  • onelogin.app_rules.getGet app ruleread
  • onelogin.app_rules.listList app rulesread
  • onelogin.app_rules.list_action_valuesList app rule action valuesread
  • onelogin.app_rules.list_actionsList app rule actionsread
  • onelogin.app_rules.list_condition_operatorsList app rule condition operatorsread
  • onelogin.app_rules.list_condition_valuesList app rule condition valuesread
  • onelogin.app_rules.list_conditionsList app rule conditionsread
  • onelogin.app_rules.sortBulk sort app ruleswrite
  • onelogin.app_rules.updateUpdate app rulewrite
Privileges11
  • onelogin.privileges.add_rolesAssign privilege to rolesdestructive
  • onelogin.privileges.add_usersAssign privilege to usersdestructive
  • onelogin.privileges.createCreate privilegewrite
  • onelogin.privileges.deleteDelete privilegedestructive
  • onelogin.privileges.getGet privilegeread
  • onelogin.privileges.listList privilegesread
  • onelogin.privileges.list_rolesGet roles assigned to privilegeread
  • onelogin.privileges.list_usersGet users assigned to privilegeread
  • onelogin.privileges.remove_roleRemove privilege from roledestructive
  • onelogin.privileges.remove_userRemove privilege from userdestructive
  • onelogin.privileges.updateUpdate privilegewrite
Message templates10
  • onelogin.message_templates.createCreate message templatewrite
  • onelogin.message_templates.deleteDelete message templatedestructive
  • onelogin.message_templates.getGet message templateread
  • onelogin.message_templates.get_by_typeGet message template by typeread
  • onelogin.message_templates.get_by_type_localeGet message template by type and localeread
  • onelogin.message_templates.get_master_by_typeGet master message template by typeread
  • onelogin.message_templates.get_master_by_type_localeGet master message template by type and localeread
  • onelogin.message_templates.listList message templatesread
  • onelogin.message_templates.updateUpdate message templatewrite
  • onelogin.message_templates.update_by_type_localeUpdate message template by type and localewrite
Mfa10
  • onelogin.mfa.activate_factorActivate a factor (start a verification)write
  • onelogin.mfa.enroll_factorEnroll a factorwrite
  • onelogin.mfa.generate_tokenGenerate MFA tokenwrite
  • onelogin.mfa.get_registrationVerify enrollment (poll for Protect and Voice)read
  • onelogin.mfa.get_verificationVerify a factor (poll for Protect and Voice)read
  • onelogin.mfa.list_available_factorsGet available factorsread
  • onelogin.mfa.list_devicesGet enrolled factorsread
  • onelogin.mfa.remove_deviceRemove a factordestructive
  • onelogin.mfa.verify_factorVerify a factor (OTP for SMS, Email, Authenticator)write
  • onelogin.mfa.verify_registrationVerify enrollment (OTP for SMS, Email, Protect, Authenticator)write
Users10
  • onelogin.users.bulk_logoutBulk logout userswrite
  • onelogin.users.createCreate userwrite
  • onelogin.users.deleteDelete userdestructive
  • onelogin.users.getGet userread
  • onelogin.users.listList usersread
  • onelogin.users.list_appsGet user appsread
  • onelogin.users.list_delegated_privilegesGet user delegated privilegesread
  • onelogin.users.list_privilegesGet user privilegesread
  • onelogin.users.unlockUnlock userwrite
  • onelogin.users.updateUpdate userwrite
Users V110
  • onelogin.users_v1.add_rolesAssign roles to user (v1)destructive
  • onelogin.users_v1.list_custom_attributesGet custom attribute names (v1)read
  • onelogin.users_v1.list_rolesGet roles for user (v1)read
  • onelogin.users_v1.lockLock user account (v1)write
  • onelogin.users_v1.logoutLog user out (v1)write
  • onelogin.users_v1.remove_rolesRemove roles from user (v1)write
  • onelogin.users_v1.set_custom_attributesSet custom attribute values (v1)write
  • onelogin.users_v1.set_password_clear_textSet password in cleartext (v1)write
  • onelogin.users_v1.set_password_using_saltSet password using SHA-256 and salt (v1)write
  • onelogin.users_v1.set_stateSet user state (v1)write
Apps7
  • onelogin.apps.createCreate appwrite
  • onelogin.apps.deleteDelete appdestructive
  • onelogin.apps.delete_parameterDelete app parameterdestructive
  • onelogin.apps.getGet appread
  • onelogin.apps.listList appsread
  • onelogin.apps.list_usersList app usersread
  • onelogin.apps.updateUpdate appwrite
Mfa V17
  • onelogin.mfa_v1.activate_factorActivate a factor (v1)write
  • onelogin.mfa_v1.enroll_factorEnroll a factor (v1)write
  • onelogin.mfa_v1.generate_tokenGenerate MFA token (v1)write
  • onelogin.mfa_v1.list_available_factorsGet available factors (v1)read
  • onelogin.mfa_v1.list_devicesGet enrolled factors (v1)read
  • onelogin.mfa_v1.remove_deviceRemove a factor (v1)destructive
  • onelogin.mfa_v1.verify_factorVerify a factor (v1)write
Self registration profiles7
  • onelogin.self_registration_profiles.add_fieldAdd field to self-registration profilewrite
  • onelogin.self_registration_profiles.createCreate self-registration profilewrite
  • onelogin.self_registration_profiles.deleteDelete self-registration profiledestructive
  • onelogin.self_registration_profiles.getGet self-registration profileread
  • onelogin.self_registration_profiles.listList self-registration profilesread
  • onelogin.self_registration_profiles.remove_fieldRemove field from self-registration profiledestructive
  • onelogin.self_registration_profiles.updateUpdate self-registration profilewrite
Brands6
  • onelogin.brands.createCreate account brandwrite
  • onelogin.brands.deleteDelete account branddestructive
  • onelogin.brands.getGet account brandread
  • onelogin.brands.listList account brandsread
  • onelogin.brands.list_appsGet apps associated with account brandread
  • onelogin.brands.updateUpdate account brandwrite
Hooks6
  • onelogin.hooks.createCreate hookwrite
  • onelogin.hooks.deleteDelete hookdestructive
  • onelogin.hooks.getGet hookread
  • onelogin.hooks.listList hooksread
  • onelogin.hooks.list_logsGet hook logsread
  • onelogin.hooks.updateUpdate hookwrite
Policies6
  • onelogin.policies.createCreate security policywrite
  • onelogin.policies.deleteDelete security policydestructive
  • onelogin.policies.getGet security policyread
  • onelogin.policies.listList security policiesread
  • onelogin.policies.set_defaultSet security policy as defaultwrite
  • onelogin.policies.updateUpdate security policywrite
Accounts5
  • onelogin.accounts.createCreate child accountwrite
  • onelogin.accounts.deleteDelete child accountdestructive
  • onelogin.accounts.getGet child accountread
  • onelogin.accounts.listList child accountsread
  • onelogin.accounts.updateUpdate child accountwrite
API authorizations5
  • onelogin.api_authorizations.createCreate authorization serverwrite
  • onelogin.api_authorizations.deleteDelete authorization serverdestructive
  • onelogin.api_authorizations.getGet authorization serverread
  • onelogin.api_authorizations.listList authorization serversread
  • onelogin.api_authorizations.updateUpdate authorization serverwrite
Custom attributes5
  • onelogin.custom_attributes.createCreate custom attributewrite
  • onelogin.custom_attributes.deleteDelete custom attributedestructive
  • onelogin.custom_attributes.getGet custom attributeread
  • onelogin.custom_attributes.listList custom attributesread
  • onelogin.custom_attributes.updateUpdate custom attributewrite
Custom messages5
  • onelogin.custom_messages.deleteDelete custom messagedestructive
  • onelogin.custom_messages.listList custom messagesread
  • onelogin.custom_messages.list_languagesList custom message languagesread
  • onelogin.custom_messages.lookupLookup custom messageread
  • onelogin.custom_messages.updateUpdate custom messagewrite
Groups5
  • onelogin.groups.createCreate groupwrite
  • onelogin.groups.deleteDelete groupdestructive
  • onelogin.groups.getGet groupread
  • onelogin.groups.listList groupsread
  • onelogin.groups.updateUpdate groupwrite
Hook env vars5
  • onelogin.hook_env_vars.createCreate hook environment variablewrite
  • onelogin.hook_env_vars.deleteDelete hook environment variabledestructive
  • onelogin.hook_env_vars.getGet hook environment variableread
  • onelogin.hook_env_vars.listList hook environment variablesread
  • onelogin.hook_env_vars.updateUpdate hook environment variablewrite
Risk rules5
  • onelogin.risk_rules.createCreate risk rulewrite
  • onelogin.risk_rules.deleteDelete risk ruledestructive
  • onelogin.risk_rules.getGet risk ruleread
  • onelogin.risk_rules.listList risk rulesread
  • onelogin.risk_rules.updateUpdate risk rulewrite
API authorization claims4
  • onelogin.api_authorization_claims.createAdd access token claimwrite
  • onelogin.api_authorization_claims.deleteDelete access token claimdestructive
  • onelogin.api_authorization_claims.listList access token claimsread
  • onelogin.api_authorization_claims.updateUpdate access token claimwrite
API authorization clients4
  • onelogin.api_authorization_clients.createAdd client appwrite
  • onelogin.api_authorization_clients.deleteRemove client appdestructive
  • onelogin.api_authorization_clients.listGet client appsread
  • onelogin.api_authorization_clients.updateUpdate client appwrite
API authorization scopes4
  • onelogin.api_authorization_scopes.createAdd scopewrite
  • onelogin.api_authorization_scopes.deleteDelete scopedestructive
  • onelogin.api_authorization_scopes.listList scopesread
  • onelogin.api_authorization_scopes.updateUpdate scopewrite
Oath tokens4
  • onelogin.oath_tokens.deleteDelete OATH tokendestructive
  • onelogin.oath_tokens.getGet OATH tokenread
  • onelogin.oath_tokens.importImport OATH tokenswrite
  • onelogin.oath_tokens.listList OATH tokensread
Email settings3
  • onelogin.email_settings.getGet email settingsread
  • onelogin.email_settings.resetReset email settingsdestructive
  • onelogin.email_settings.updateUpdate email settingswrite
Reports3
  • onelogin.reports.listList reportsread
  • onelogin.reports.runRun reportwrite
  • onelogin.reports.run_backgroundRun report in backgroundwrite
Risk3
  • onelogin.risk.get_scoresGet score insightsread
  • onelogin.risk.track_eventTrack an eventwrite
  • onelogin.risk.verifyGet a risk scoreread
Events2
  • onelogin.events.getGet eventread
  • onelogin.events.listList eventsread
Invites2
  • onelogin.invites.get_linkGenerate invite linkwrite
  • onelogin.invites.send_linkSend invite linkwrite
Login2
  • onelogin.login.create_session_tokenCreate session login tokenwrite
  • onelogin.login.verify_factorVerify factor for loginwrite
Saml assertions2
  • onelogin.saml_assertions.generateGenerate SAML assertionwrite
  • onelogin.saml_assertions.verify_factorVerify factor for SAML assertionwrite
Smart mfa2
  • onelogin.smart_mfa.validate_userValidate a user (Smart MFA step 1)write
  • onelogin.smart_mfa.verify_tokenVerify MFA token (Smart MFA step 2)write
Authentication factors1
  • onelogin.authentication_factors.listList authentication factorsread
Connectors1
  • onelogin.connectors.listList connectorsread
Event types1
  • onelogin.event_types.listList event typesread
Rate limit1
  • onelogin.rate_limit.getGet rate limitread

Questions

The OneLogin MCP server, answered.

Is there a OneLogin MCP server for Claude?

Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 200 OneLogin actions across roles, mappings, app rules and privileges, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by OneLogin.

What do I need to connect OneLogin?

Client ID of a OneLogin API credential (Administration > Developers > API Credentials > New Credential) and Client secret of that API credential. Plus your host. The free call account { op: "connections.requirements", service: "onelogin" } lists exactly what to paste.

Can an AI agent delete or change things in OneLogin?

Only if its key allows it, and only with an explicit confirmation. 37 OneLogin actions are destructive, including delete user, delete group and delete role. Each runs only with confirm: true. Under the human confirm policy, or an approval rule on the key, the run waits until a named person approves it.

Will an AI agent use up my OneLogin API limit?

actionlake paces every call to the limits in the OneLogin service file: 5,000 calls an hour per connection. Repeated reads are answered from cache (81 OneLogin actions can be), which never reaches OneLogin.

What does a OneLogin action cost?

One upstream call, the only unit actionlake bills. A list that pages bills one call per page (200 OneLogin actions page). Cache hits, searches, dry runs and calls OneLogin refused with 401, 403, 429 or a 5xx are free. The Free plan includes 100,000 calls a month with no card. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000.

Which OneLogin API does it cover?

The OneLogin API v2 with the v1-only operations (developers.onelogin.com, fetched 2026-10-23) at your OneLogin instance's API base URL, which you enter when connecting. It is built from OneLogin's documentation as read on 23 October 2026. 200 actions in 37 areas, each one in the signed service file (version 1.0.0).

Does actionlake keep my OneLogin data, and where?

actionlake processes and stores data in Sydney, Australia; there is no US region yet. Reads may be cached for up to an hour, and a write clears the reads it affects. Each run's request and response is kept, sealed, for your plan's trace window: 1 day on Free, 3 days on Starter, 7 days on Pro, 14 days on Team, 30 days on Business and 30 days on Enterprise. Your OneLogin credential is sealed under your tenant's key, never logged and never returned. Your traffic is not used to train models.

Which AI clients can use it?

Claude Code, tested by us end to end, and the Claude app as a custom connector, tested by us with an existing key. Other MCP clients that support remote servers over Streamable HTTP (MCP revisions 2025-06-18 and 2025-11-25) and OAuth dynamic client registration, or a bearer header, should connect the same way; we have not tested them. Or plain REST, under the same action names.

Give your agent OneLogin today.

Start free - 100,000 calls/month, no card. No signup. Hard caps on every key. Cached answers are free.