Anthropic Admin Mcp

io.github.TrushtonfactoryPublished by GitHub account Trushtonfactoryv0.1.1Updated Oct 24, 2026

Native MCP server for the Anthropic Admin API: org, workspaces, members, API keys, usage, costs.

VerifiedSTDIODesktop onlyCloud & InfrastructureSecurity & MonitoringData & Analytics

Overview

AI-generated overview

Local MCP server for the Anthropic Admin API that lets an assistant inspect and manage an organization's workspaces, members, API keys, usage and costs.

What you can do
Read organization info, members, invites, workspaces, workspace members and API keys, with filters by status or workspace. Retrieve usage and cost reports grouped by workspace, API key or model, plus Claude Code usage. Invite members, cancel invites, change or remove member roles, and remove non-admin members. Create, rename, recolor or archive workspaces and grant, change or revoke workspace access. Rename or deactivate API keys. All write tools require an explicit confirmation flag and are recorded to a JSONL audit log.
When to use it
Useful for organization admins who want to query Anthropic spend and token usage, audit API keys and members, or make routine org changes such as invites and workspace access from an MCP client instead of the Console.
Requirements
Runs locally as a Python package (pip install) over stdio. Requires an Anthropic Admin API key in ANTHROPIC_ADMIN_KEY, which needs an Organization plan (Team, Pro+ or Enterprise) and the admin role. Optional ALLOWED_WORKSPACES scopes write tools; AUDIT_LOG_PATH sets the audit log location. A read-only mode flag exists.
Before you install
The Admin key grants broad organization access: reads expose everything the Admin API returns with that key, and write tools can invite, remove or re-role members, archive workspaces and deactivate API keys. Writes require confirm=True and are audit-logged, but there are no usage limits yet. Keep the key out of shared configs and prefer read-only mode or workspace scoping for least privilege.

Installation

In SourceWeft

  1. Open Anthropic Admin Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

anthropic-admin-mcp

The MCP server Anthropic hasn't shipped yet — full coverage of the Anthropic Admin API and the Usage & Cost API, properly typed, properly tooled, and properly safety-scoped.

Manage your Anthropic organization from any MCP-compatible client (Claude Desktop, Cursor, Windsurf, ChatGPT, etc.) using natural language:

  • "What did my organization spend last week, grouped by workspace?"
  • "Which API key burned through the most Opus tokens yesterday?"
  • "Show me Pre-Mortem's usage day-by-day for the last 14 days."
  • "Invite [email protected] as a developer to the Sandbox workspace."
  • "Deactivate the API key named 'old-laptop'."

10 read tools, 10 write tools, audit logging, optional workspace scoping, read-only mode, role-escalation guard.

Why this exists

Anthropic ships an excellent Admin API with ~22 endpoints across organization management, workspaces, members, API keys, usage reporting, and cost reporting. Existing MCP wrappers from third parties cover a tiny slice of it through commercial integration platforms. This server is native, free, open-source, and complete — installable in two minutes against your own Admin key.

Install

bash
pip install git+https://github.com/Trushtonfactory/anthropic-admin-mcp.git

Or for local development:

bash
git clone https://github.com/Trushtonfactory/anthropic-admin-mcp.gitcd anthropic-admin-mcppython3 -m venv .venvsource .venv/bin/activatepip install -e .

Configure

  1. Get an Admin API key at console.anthropic.com → Settings → Admin Keys. Requires an Organization plan (Team / Pro+ / Enterprise) and the admin role. Individual accounts cannot create Admin keys.

  2. Copy .env.example to .env and fill in your key:

    bash
    cp .env.example .env# edit .env: ANTHROPIC_ADMIN_KEY=sk-ant-admin-...

  3. Wire it into your MCP client. For Claude Desktop, add to ~/Library/Application Support/Claude/claude_desktop_config.json:

    json
    {  "mcpServers": {    "anthropic-admin": {      "command": "anthropic-admin-mcp",      "env": {        "ANTHROPIC_ADMIN_KEY": "sk-ant-admin-..."      }    }  }}

    See examples/claude_desktop_config.json for more options (read-only mode, workspace scoping).

Tools

Read (10)

ToolPurpose
get_org_infoSmoke-test the key; return org id + name
list_membersList org members and roles
list_invitesList pending and historical invites
list_workspacesList active (and optionally archived) workspaces
get_workspaceResolve a workspace ID to its full record
list_workspace_membersList members of a specific workspace
list_api_keysList keys with filters by status / workspace
get_usage_reportToken usage, grouped by workspace/api_key/model/etc.
get_cost_reportDollar costs, grouped by workspace / description
get_claude_code_usageClaude Code-specific usage data

Write (10) — all require confirm=True

ToolAction
invite_memberSend an invite (cannot grant admin)
delete_inviteCancel a pending invite
update_member_roleChange a member's org role (cannot touch admin)
remove_memberRemove a non-admin member
create_workspaceCreate a new workspace
update_workspaceRename or recolor a workspace
archive_workspaceArchive a workspace
add_workspace_memberGrant workspace access
update_workspace_member_roleChange a workspace role
remove_workspace_memberRevoke workspace access
update_api_keyRename or deactivate an API key

Running

bash
# Full mode (read + write), stdio transportanthropic-admin-mcp
# Read-only — recommended for first-time setupanthropic-admin-mcp --read-only
# Streamable HTTP (for remote MCP clients)anthropic-admin-mcp --http --port 8000
# Restrict writes to specific workspaces (set in .env or shell)ALLOWED_WORKSPACES=wrkspc_abc,wrkspc_xyz anthropic-admin-mcp

Safety

See SECURITY.md for the full threat model and design notes. The short version:

  • Reads are open. Anything the Admin API exposes with your key, this server exposes.
  • Writes are guarded. Every mutation requires confirm=True, gets audit-logged to JSONL, and respects optional workspace scoping.
  • Role escalation is blocked client-side even though the API itself blocks it server-side — clearer error messages for Claude.
  • No credential exfiltration paths. The Admin API never returns key values, and this server never logs the Admin key itself.

Status

v0.1.0 — read + write tool surface complete. Pagination, error messages, and audit logging tested manually. No usage limits implemented yet. Pydantic response models are minimal (tools return raw dicts).

Issues and PRs welcome.

License

MIT — see LICENSE.

Source: README.md at commit dd826cb

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.1LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts