Anthropic Admin MCP integration for AI agents.
Connect AI agents to Anthropic Admin through 6 structured actions, including get organization, list api keys, and list invites. Review authentication, inputs…
- ACTION CONTRACTS
- 6
- 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 Anthropic Admin integration exposes
The Anthropic Admin Agent App exposes 6 provider-backed actions for ai work. Its current contract lets an authorized agent retrieve the anthropic organization associated with the admin api key, list anthropic api keys in the organization, optionally filtered by workspace, and list pending or historical anthropic organization invites. 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 Anthropic Admin account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.
VERIFIED ACTION SAMPLE
Real Anthropic Admin capabilities.
Showing 6 of 6 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.
get_organizationREADRetrieve the Anthropic organization associated with the Admin API key.
list_api_keysREADList Anthropic API keys in the organization, optionally filtered by workspace.
INPUTS: workspace_id / before_id / after_id / limit
list_invitesREADList pending or historical Anthropic organization invites.
INPUTS: before_id / after_id / limit
list_usersREADList users in the Anthropic organization with cursor pagination.
INPUTS: before_id / after_id / limit
list_workspace_membersREADList members of one Anthropic workspace with cursor pagination.
INPUTS: workspace_id / before_id / after_id / limit
list_workspacesREADList Anthropic workspaces in the organization with cursor pagination.
INPUTS: before_id / after_id / limit
INPUT CONTRACTS
Know what the action needs before it runs.
list_api_keys
workspace_idOPTIONAL- Only return API keys belonging to this workspace.
before_idOPTIONAL- Return API keys before this API key identifier.
after_idOPTIONAL- Return API keys after this API key identifier.
limitOPTIONAL- The maximum number of API keys to return.
list_invites
before_idOPTIONAL- Return objects before this object identifier.
after_idOPTIONAL- Return objects after this object identifier.
limitOPTIONAL- The maximum number of objects to return.
list_users
before_idOPTIONAL- Return objects before this object identifier.
after_idOPTIONAL- Return objects after this object identifier.
limitOPTIONAL- The maximum number of objects to return.
list_workspace_members
workspace_idREQUIRED- The Anthropic workspace identifier.
before_idOPTIONAL- Return members before this member identifier.
after_idOPTIONAL- Return members after this member identifier.
limitOPTIONAL- The maximum number of members to return.
PROVIDER-SPECIFIC WORKFLOWS
Jobs this Agent App can support
Inspect Get Organization
Retrieve the Anthropic organization associated with the Admin API key. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.
get_organizationVerify with List Api Keys
List Anthropic API keys in the organization, optionally filtered by workspace. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.
list_api_keysSAFETY BOUNDARY
Operate Anthropic Admin with explicit limits
- Authorize Anthropic Admin with API key and grant only the provider access required by the selected actions.
- The current action names appear read-oriented, but returned Anthropic Admin data may still be sensitive and should be minimized before it enters model context.
- Do not infer permission from catalog visibility. Workspace policy, connection identity, and upstream authorization still govern execution.
- No provider scope string is declared on the sampled actions. Verify the connected account's actual permissions in Anthropic Admin rather than assuming unrestricted access.
- After a call, inspect the structured result and execution record before reporting that the Anthropic Admin task completed successfully.
CONNECTION MODEL
API key
Anthropic Admin API key sent with the x-api-key header. Create or manage Admin keys in the Anthropic Console: https://console.anthropic.com/settings/admin-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
- 6
- WRITE SIGNALS
- 0
- HIGH IMPACT
- 0
- REVIEW SIGNALS
- 0
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 Anthropic Admin.