Skip to content

Connectors · AI

Claude Admin (Anthropic) MCP server for AI agents.

actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to Claude Admin (Anthropic) and the rest of your systems. It gives your agent 115 Claude Admin (Anthropic) actions (66 reads, 36 writes and 13 that wait for a confirmation) and holds the Claude Admin (Anthropic) credential itself, so the agent never does. It paces Claude Admin (Anthropic)'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: "anthropic_admin.organization.get",  intent: "check which Claude Admin (Anthropic) account is connected"}# Get Current Organization · read · 1 upstream call
  • 115actionsin one signed file
  • 66readlook, never change
  • 36writecreate and update
  • 13wait for a yesdestructive, confirmed first

Set up

Connect Claude Admin (Anthropic) 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 Claude Admin (Anthropic).

    API key. No consent screen: your agent can connect it for you, but the key then passes through your chat. To keep it out of the model's context, paste it in the console instead. actionlake stores what you paste write-only, sealed under your tenant's key.

    • admin_api_keyAnthropic Admin API key (sk-ant-admin…), created by an organisation admin under Settings > Admin keys
    account { op: "connections.requirements", service: "anthropic_admin" }
    # 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: "anthropic_admin.organization.get" }# get current organization · read · 1 upstream callcheck { action: "anthropic_admin.rbac_groups.create", input: { … } }# free: inputs, permissions, cost and confirmations, nothing sent

Claude Admin (Anthropic) at a glance

Sign-in
API key. No consent screen: your agent can connect it for you, but the key then passes through your chat. To keep it out of the model's context, paste it in the console instead.
You provide
admin_api_key
Limits we pace to
at most 16 at a time, per connection
API covered
Claude Admin (Anthropic) API 2023-06-01api.anthropic.com
Built from
Claude Admin (Anthropic)'s documentation, read 1 October 2026GitHub
Service file
Version 1.0.0, signed (Ed25519)
Cached reads
3 of 66 reads, for up to an hour; a write clears what it affects
Shared entities
4, so ask can line Claude Admin (Anthropic) up with your other systems
Data
Processed and stored in Sydney, Australia. No US region yet

Capabilities

What an AI agent can do in Claude Admin (Anthropic).

115 actions in 31 areas. Every one carries its effect, so a key can allow the reads and hold the rest.

  • 66readlook, never change
  • 36writecreate and update
  • 13destructivewait for a confirmation
  1. Analytics

    11

    11 read · 0 write · 0 destructive

    Get Cost Over Time · Get Per-User Cost · Get Artifact Activity · Get Chat Project Usage

  2. External keys

    6

    3 read · 2 write · 1 destructive

    Create External Key · List External Keys · Get External Key · Update External Key

  3. Federation issuers

    5

    2 read · 3 write · 0 destructive

    List Federation Issuers · Create Federation Issuer · Get Federation Issuer · Update Federation Issuer

  4. Federation rules

    5

    2 read · 3 write · 0 destructive

    Create Federation Rule · List Federation Rules · Archive Federation Rule · Get Federation Rule

  5. Org tunnels

    5

    3 read · 1 write · 1 destructive

    Deprecated: List Tunnels · Deprecated: Get Tunnel · Deprecated: Archive Tunnel · Deprecated: Reveal Tunnel Token

  6. Rbac groups

    5

    2 read · 2 write · 1 destructive

    List RBAC Groups · Create RBAC Group · Get RBAC Group · Update RBAC Group

  7. Service accounts

    5

    2 read · 3 write · 0 destructive

    List Service Accounts · Create Service Account · Get Service Account · Update Service Account

  8. Spend limits

    5

    3 read · 1 write · 1 destructive

    List Spend Limits · List Effective Spend Limits · Get Spend Limit · Delete Spend Limit

23 more areas · 68 actions
  • Workspace members 5
  • Workspace service accounts 5
  • Workspaces 5
  • Invites 4
  • Org tunnel certificates 4
  • Plugin marketplaces 4
  • Plugins 4
  • Spend limit increase requests 4
  • Users 4
  • API keys 3
  • Federation rule workspaces 3
  • Plugin installation settings 3
  • Rbac group members 3
  • Reports 3
  • Service account workspaces 3
  • Compliance settings 2
  • Plugin versions 2
  • Rbac roles 2
  • Organization 1
  • Plugin shares 1
  • Rate limits 1
  • Rbac role permissions 1
  • Workspace rate limits 1

Top actions

The Claude Admin (Anthropic) API, shaped for agents.

The ids your agent types, what each does, and the one name it shares with other systems. 62 of Claude Admin (Anthropic)'s 62 action names are shared with at least one other connector, so an agent learns them once.

ActionWhat it doesEffectSame name in
anthropic_admin.users.listList UsersList the organization's members.readidentity.user.list474 connectors
anthropic_admin.rbac_groups.listList RBAC GroupsList RBAC Groups in the Claude Enterprise tenant.readidentity.group.list262 connectors
anthropic_admin.service_accounts.listList Service Accounts**Requires an OAuth access token with the `org:admin` scope**, from `ant auth login --scope org:admin` or a workload identity federation rule; Admin API keys…readidentity.service_account.list35 connectors
anthropic_admin.rbac_groups.createCreate RBAC GroupCreate an RBAC Group in the Claude Enterprise tenant.writeidentity.group.create205 connectors
anthropic_admin.users.getGet UserRetrieve a member of the organization by user ID.readidentity.user.get399 connectors
anthropic_admin.users.deleteRemove UserRemove a member from the organization.destructiveidentity.user.delete253 connectors
anthropic_admin.service_accounts.createCreate Service Account**Requires an OAuth access token with the `org:admin` scope**, from `ant auth login --scope org:admin` or a workload identity federation rule; Admin API keys…writeidentity.service_account.create32 connectors
anthropic_admin.workspaces.listList WorkspacesList Workspacesreadwork.workspace.list50 connectors
anthropic_admin.rbac_roles.listList RBAC RolesList RBAC Roles in the organization.readidentity.role.list184 connectors
anthropic_admin.rbac_group_members.listList RBAC Group MembersList members of an RBAC Group.readidentity.group_member.list103 connectors
anthropic_admin.api_keys.listList API KeysList API Keysreadidentity.api_key.list96 connectors
anthropic_admin.invites.createCreate InviteInvite a user to join the organization by email.writeidentity.invitation.create41 connectors

Try it

Prompts to paste into Claude.

Each one names the Claude Admin (Anthropic) actions it will call, so you know what it reads and what it changes before you send it.

  1. Readread

    Who has access in Claude Admin (Anthropic)? List every user and their role.

    callsanthropic_admin.users.list

  2. Writewrite

    Create RBAC Group in Claude Admin (Anthropic). Show me exactly what you will send before you save it.

    callsanthropic_admin.rbac_groups.create

Governance for Claude Admin (Anthropic)

Destructive actions wait for a yes.

13 Claude Admin (Anthropic) actions are destructive. These are all of them:

  • Remove Useranthropic_admin.users.delete
  • Delete RBAC Groupanthropic_admin.rbac_groups.delete
  • Remove RBAC Group Memberanthropic_admin.rbac_group_members.remove
  • Delete Inviteanthropic_admin.invites.delete
  • Delete Spend Limitanthropic_admin.spend_limits.delete
  • Delete Workspace Memberanthropic_admin.workspace_members.remove
  • Delete External Keyanthropic_admin.external_keys.delete
  • Deprecated: Rotate Tunnel Tokenanthropic_admin.org_tunnels.rotate_token
  • Delete Pluginanthropic_admin.plugins.delete
  • Remove Federation Rule Workspaceanthropic_admin.federation_rule_workspaces.remove
  • Remove Workspace From Service Accountanthropic_admin.service_account_workspaces.remove
  • Delete Service Account Workspace Memberanthropic_admin.workspace_service_accounts.remove
  • Remove Plugin Installation Settinganthropic_admin.plugin_installation_settings.remove

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.

doanthropic_admin.users.deleteconfirm_policy: human

Remove User?

intent: the user asked me to remove User

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

Cost

What Claude Admin (Anthropic) costs on actionlake.

Every Claude Admin (Anthropic) action is one upstream call, the only thing actionlake bills. Searching, check, cost, account and any call Claude Admin (Anthropic) 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 115 Claude Admin (Anthropic) actions
  • 115actions pageeach page of a long list is one call
  • 3reads 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 Claude Admin (Anthropic) action.

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

Analytics11
  • anthropic_admin.analytics.artifactsGet Artifact Activityread
  • anthropic_admin.analytics.chat_projectsGet Chat Project Usageread
  • anthropic_admin.analytics.connectorsGet Connector Usageread
  • anthropic_admin.analytics.cost_reportGet Cost Over Timeread
  • anthropic_admin.analytics.pluginsGet Plugin Usageread
  • anthropic_admin.analytics.skillsGet Skill Usageread
  • anthropic_admin.analytics.summariesGet Activity Summariesread
  • anthropic_admin.analytics.usage_reportGet Token Usage Over Timeread
  • anthropic_admin.analytics.user_cost_reportGet Per-User Costread
  • anthropic_admin.analytics.user_usage_reportGet Per-User Token Usageread
  • anthropic_admin.analytics.usersList User Activityread
External keys6
  • anthropic_admin.external_keys.createCreate External Keywrite
  • anthropic_admin.external_keys.deleteDelete External Keydestructive
  • anthropic_admin.external_keys.getGet External Keyread
  • anthropic_admin.external_keys.listList External Keysread
  • anthropic_admin.external_keys.updateUpdate External Keywrite
  • anthropic_admin.external_keys.validateValidate External Keyread
Federation issuers5
  • anthropic_admin.federation_issuers.archiveArchive Federation Issuerwrite
  • anthropic_admin.federation_issuers.createCreate Federation Issuerwrite
  • anthropic_admin.federation_issuers.getGet Federation Issuerread
  • anthropic_admin.federation_issuers.listList Federation Issuersread
  • anthropic_admin.federation_issuers.updateUpdate Federation Issuerwrite
Federation rules5
  • anthropic_admin.federation_rules.archiveArchive Federation Rulewrite
  • anthropic_admin.federation_rules.createCreate Federation Rulewrite
  • anthropic_admin.federation_rules.getGet Federation Ruleread
  • anthropic_admin.federation_rules.listList Federation Rulesread
  • anthropic_admin.federation_rules.updateUpdate Federation Rulewrite
Org tunnels5
  • anthropic_admin.org_tunnels.archiveDeprecated: Archive Tunnelwrite
  • anthropic_admin.org_tunnels.getDeprecated: Get Tunnelread
  • anthropic_admin.org_tunnels.listDeprecated: List Tunnelsread
  • anthropic_admin.org_tunnels.reveal_tokenDeprecated: Reveal Tunnel Tokenread
  • anthropic_admin.org_tunnels.rotate_tokenDeprecated: Rotate Tunnel Tokendestructive
Rbac groups5
  • anthropic_admin.rbac_groups.createCreate RBAC Groupwrite
  • anthropic_admin.rbac_groups.deleteDelete RBAC Groupdestructive
  • anthropic_admin.rbac_groups.getGet RBAC Groupread
  • anthropic_admin.rbac_groups.listList RBAC Groupsread
  • anthropic_admin.rbac_groups.updateUpdate RBAC Groupwrite
Service accounts5
  • anthropic_admin.service_accounts.archiveArchive Service Accountwrite
  • anthropic_admin.service_accounts.createCreate Service Accountwrite
  • anthropic_admin.service_accounts.getGet Service Accountread
  • anthropic_admin.service_accounts.listList Service Accountsread
  • anthropic_admin.service_accounts.updateUpdate Service Accountwrite
Spend limits5
  • anthropic_admin.spend_limits.deleteDelete Spend Limitdestructive
  • anthropic_admin.spend_limits.getGet Spend Limitread
  • anthropic_admin.spend_limits.listList Spend Limitsread
  • anthropic_admin.spend_limits.list_effectiveList Effective Spend Limitsread
  • anthropic_admin.spend_limits.setSet Spend Limitwrite
Workspace members5
  • anthropic_admin.workspace_members.addCreate Workspace Memberwrite
  • anthropic_admin.workspace_members.getGet Workspace Memberread
  • anthropic_admin.workspace_members.listList Workspace Membersread
  • anthropic_admin.workspace_members.removeDelete Workspace Memberdestructive
  • anthropic_admin.workspace_members.updateUpdate Workspace Memberwrite
Workspace service accounts5
  • anthropic_admin.workspace_service_accounts.addCreate Service Account Workspace Memberwrite
  • anthropic_admin.workspace_service_accounts.getGet Service Account Workspace Memberread
  • anthropic_admin.workspace_service_accounts.listList Service Account Workspace Membersread
  • anthropic_admin.workspace_service_accounts.removeDelete Service Account Workspace Memberdestructive
  • anthropic_admin.workspace_service_accounts.updateUpdate Service Account Workspace Memberwrite
Workspaces5
  • anthropic_admin.workspaces.archiveArchive Workspacewrite
  • anthropic_admin.workspaces.createCreate Workspacewrite
  • anthropic_admin.workspaces.getGet Workspaceread
  • anthropic_admin.workspaces.listList Workspacesread
  • anthropic_admin.workspaces.updateUpdate Workspacewrite
Invites4
  • anthropic_admin.invites.createCreate Invitewrite
  • anthropic_admin.invites.deleteDelete Invitedestructive
  • anthropic_admin.invites.getGet Inviteread
  • anthropic_admin.invites.listList Invitesread
Org tunnel certificates4
  • anthropic_admin.org_tunnel_certificates.archiveDeprecated: Archive Tunnel Certificatewrite
  • anthropic_admin.org_tunnel_certificates.createDeprecated: Create Tunnel Certificatewrite
  • anthropic_admin.org_tunnel_certificates.getDeprecated: Get Tunnel Certificateread
  • anthropic_admin.org_tunnel_certificates.listDeprecated: List Tunnel Certificatesread
Plugin marketplaces4
  • anthropic_admin.plugin_marketplaces.getGet Plugin Marketplaceread
  • anthropic_admin.plugin_marketplaces.listList Plugin Marketplacesread
  • anthropic_admin.plugin_marketplaces.updateUpdate Plugin Marketplacewrite
  • anthropic_admin.plugin_marketplaces.validate_repositoryValidate Plugin Marketplace Repositoryread
Plugins4
  • anthropic_admin.plugins.deleteDelete Plugindestructive
  • anthropic_admin.plugins.getGet Pluginread
  • anthropic_admin.plugins.listList Pluginsread
  • anthropic_admin.plugins.updateUpdate Pluginwrite
Spend limit increase requests4
  • anthropic_admin.spend_limit_increase_requests.approveApprove Spend Limit Increase Requestwrite
  • anthropic_admin.spend_limit_increase_requests.denyDeny Spend Limit Increase Requestwrite
  • anthropic_admin.spend_limit_increase_requests.getGet Spend Limit Increase Requestread
  • anthropic_admin.spend_limit_increase_requests.listList Spend Limit Increase Requestsread
Users4
  • anthropic_admin.users.deleteRemove Userdestructive
  • anthropic_admin.users.getGet Userread
  • anthropic_admin.users.listList Usersread
  • anthropic_admin.users.updateUpdate Userwrite
API keys3
  • anthropic_admin.api_keys.getGet API Keyread
  • anthropic_admin.api_keys.listList API Keysread
  • anthropic_admin.api_keys.updateUpdate API Keywrite
Federation rule workspaces3
  • anthropic_admin.federation_rule_workspaces.addAdd Federation Rule Workspacewrite
  • anthropic_admin.federation_rule_workspaces.listList Federation Rule Workspacesread
  • anthropic_admin.federation_rule_workspaces.removeRemove Federation Rule Workspacedestructive
Plugin installation settings3
  • anthropic_admin.plugin_installation_settings.listList Plugin Installation Settingsread
  • anthropic_admin.plugin_installation_settings.removeRemove Plugin Installation Settingdestructive
  • anthropic_admin.plugin_installation_settings.setSet Plugin Installation Settingwrite
Rbac group members3
  • anthropic_admin.rbac_group_members.addAdd RBAC Group Memberwrite
  • anthropic_admin.rbac_group_members.listList RBAC Group Membersread
  • anthropic_admin.rbac_group_members.removeRemove RBAC Group Memberdestructive
Reports3
  • anthropic_admin.reports.claude_code_usageGet Claude Code Usage Reportread
  • anthropic_admin.reports.costGet Cost Reportread
  • anthropic_admin.reports.messages_usageGet Messages Usage Reportread
Service account workspaces3
  • anthropic_admin.service_account_workspaces.addAdd Workspace To Service Accountwrite
  • anthropic_admin.service_account_workspaces.listList Workspaces For Service Accountread
  • anthropic_admin.service_account_workspaces.removeRemove Workspace From Service Accountdestructive
Compliance settings2
  • anthropic_admin.compliance_settings.getGet Compliance Settingsread
  • anthropic_admin.compliance_settings.updateUpdate Compliance Settingswrite
Plugin versions2
  • anthropic_admin.plugin_versions.getGet Plugin Versionread
  • anthropic_admin.plugin_versions.listList Plugin Versionsread
Rbac roles2
  • anthropic_admin.rbac_roles.getGet RBAC Roleread
  • anthropic_admin.rbac_roles.listList RBAC Rolesread
Organization1
  • anthropic_admin.organization.getGet Current Organizationread
Plugin shares1
  • anthropic_admin.plugin_shares.listList Plugin Sharesread
Rate limits1
  • anthropic_admin.rate_limits.listList Organization Rate Limitsread
Rbac role permissions1
  • anthropic_admin.rbac_role_permissions.listList RBAC Role Permissionsread
Workspace rate limits1
  • anthropic_admin.workspace_rate_limits.listList Workspace Rate Limitsread

Questions

The Claude Admin (Anthropic) MCP server, answered.

Is there a Claude Admin (Anthropic) MCP server for Claude?

Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 115 Claude Admin (Anthropic) actions across analytics, external keys, federation issuers and federation rules, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by Claude Admin (Anthropic).

What do I need to connect Claude Admin (Anthropic)?

Anthropic Admin API key (sk-ant-admin…), created by an organisation admin under Settings > Admin keys. The free call account { op: "connections.requirements", service: "anthropic_admin" } lists exactly what to paste.

Can an AI agent delete or change things in Claude Admin (Anthropic)?

Only if its key allows it, and only with an explicit confirmation. 13 Claude Admin (Anthropic) actions are destructive, including remove User, delete RBAC Group and remove RBAC Group Member. 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 Claude Admin (Anthropic) API limit?

actionlake paces every call to the limits in the Claude Admin (Anthropic) service file: at most 16 at a time per connection. Repeated reads are answered from cache (3 Claude Admin (Anthropic) actions can be), which never reaches Claude Admin (Anthropic).

What does a Claude Admin (Anthropic) action cost?

One upstream call, the only unit actionlake bills. A list that pages bills one call per page (115 Claude Admin (Anthropic) actions page). Cache hits, searches, dry runs and calls Claude Admin (Anthropic) 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 Claude Admin (Anthropic) API does it cover?

The Claude Admin (Anthropic) API 2023-06-01 at api.anthropic.com. It is built from Claude Admin (Anthropic)'s documentation as read on 1 October 2026. 115 actions in 31 areas, each one in the signed service file (version 1.0.0).

Does actionlake keep my Claude Admin (Anthropic) 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 Claude Admin (Anthropic) 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 Claude Admin (Anthropic) today.

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