Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
作者提供的说明(英文原文)
Native MCP server for the Anthropic Admin API: org, workspaces, members, API keys, usage, costs.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
ANTHROPIC_ADMIN_KEY, ALLOWED_WORKSPACES, AUDIT_LOG_PATH标为机密的值是你账户的钥匙。千万不要分享给别人,也不要粘贴到聊天里。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"anthropic-admin": {
"command": "uvx",
"args": [
"anthropic-admin-mcp"
],
"env": {
"ANTHROPIC_ADMIN_KEY": "your-value",
"ALLOWED_WORKSPACES": "your-value",
"AUDIT_LOG_PATH": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add anthropic-admin --env ANTHROPIC_ADMIN_KEY=your-value --env ALLOWED_WORKSPACES=your-value --env AUDIT_LOG_PATH=your-value -- uvx anthropic-admin-mcp运行前请先填写空着的值。
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"anthropic-admin": {
"command": "uvx",
"args": [
"anthropic-admin-mcp"
],
"env": {
"ANTHROPIC_ADMIN_KEY": "your-value",
"ALLOWED_WORKSPACES": "your-value",
"AUDIT_LOG_PATH": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"anthropic-admin": {
"type": "stdio",
"command": "uvx",
"args": [
"anthropic-admin-mcp"
],
"env": {
"ANTHROPIC_ADMIN_KEY": "your-value",
"ALLOWED_WORKSPACES": "your-value",
"AUDIT_LOG_PATH": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
你的选择通过 Cookie 保存在这台设备上,无需账户。
ALLOWED_WORKSPACES envAUDIT_LOG_PATH env这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月7日
注册名称已通过 GitHub 账户 Trushtonfactory 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
你需要填写:ANTHROPIC_ADMIN_KEY
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于–,最新版本(0.1.1)于6个月前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Python (uv)。
同一分类中有:Spec Driven Development, Remote Desktop Commander, Signoff
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Five gates that make an agent's 'done' provable: run them, read the verdict, audit the record.
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
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:
10 read tools, 10 write tools, audit logging, optional workspace scoping, read-only mode, role-escalation guard.
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.
pip install git+https://github.com/Trushtonfactory/anthropic-admin-mcp.git
Or for local development:
git clone https://github.com/Trushtonfactory/anthropic-admin-mcp.git
cd anthropic-admin-mcp python3 -m venv .venv source .venv/bin/activate pip install -e .
.env.example to .env and fill in your key: cp .env.example .env
~/Library/Application Support/Claude/claude_desktop_config.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).
| Tool | Purpose |
|---|---|
get_org_info | Smoke-test the key; return org id + name |
list_members | List org members and roles |
list_invites | List pending and historical invites |
list_workspaces | List active (and optionally archived) workspaces |
get_workspace | Resolve a workspace ID to its full record |
list_workspace_members | List members of a specific workspace |
list_api_keys | List keys with filters by status / workspace |
get_usage_report | Token usage, grouped by workspace/api_key/model/etc. |
get_cost_report | Dollar costs, grouped by workspace / description |
get_claude_code_usage | Claude Code-specific usage data |
confirm=True| Tool | Action |
|---|---|
invite_member | Send an invite (cannot grant admin) |
delete_invite | Cancel a pending invite |
update_member_role | Change a member's org role (cannot touch admin) |
remove_member | Remove a non-admin member |
create_workspace | Create a new workspace |
update_workspace | Rename or recolor a workspace |
archive_workspace | Archive a workspace |
add_workspace_member | Grant workspace access |
update_workspace_member_role | Change a workspace role |
remove_workspace_member | Revoke workspace access |
update_api_key | Rename or deactivate an API key |
# Full mode (read + write), stdio transport
anthropic-admin-mcp
anthropic-admin-mcp --read-only
anthropic-admin-mcp --http --port 8000
ALLOWED_WORKSPACES=wrkspc_abc,wrkspc_xyz anthropic-admin-mcp
See SECURITY.md for the full threat model and design notes. The short version:
confirm=True, gets audit-logged to JSONL, and respects optional workspace scoping.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.
MIT — see LICENSE.