ai-manage-tools MCP

AI Manager MCP (Model Context Protocol) tool for AI assistants. It lets Cursor, Codex, Claude Desktop, and other MCP-compatible clients check local configuration and upload AI usage reports to AI Manager.

Requirements

• Node.js 18+
• Python 3.11+
• AI Manager upload token

If Python is not available as python3.12, python3.11, or python3, set AI_MANAGE_TOOLS_PYTHON.

Install

You usually do not need to install it globally. Configure your AI tool to run it through npx:

npx -y @bangdao-ai/ai-manage-tools@latest

Environment

AI_MANAGER_BASE_URL=https://token.longshine.com/ai-manage
AI_MANAGER_TOKEN=aim_xxx
# Optional: disable background collection from the MCP server.
AI_MANAGER_AUTO_COLLECT=false

• AI_MANAGER_BASE_URL: AI Manager service URL.
• AI_MANAGER_TOKEN: upload token issued by AI Manager.
• AI_MANAGE_TOOLS_PYTHON: optional Python interpreter path.
• AI_MANAGER_AUTO_COLLECT: optional. Defaults to enabled; set to false to disable background collection.
• Background collection uses local scheduler and collect locks, so only one ai-manage-tools process schedules and runs collection at a time on the same computer.

Cursor

Open Cursor MCP settings and add:

{
  "mcpServers": {
    "ai-manage-tools": {
      "command": "npx",
      "args": ["-y", "@bangdao-ai/ai-manage-tools@latest"],
      "env": {
        "AI_MANAGER_BASE_URL": "https://token.longshine.com/ai-manage",
        "AI_MANAGER_TOKEN": "aim_xxx"
      }
    }
  }
}

After saving, restart MCP or reload Cursor. Ask the assistant:

调用 ai-manage-tools 的 status 工具检查连接配置

Codex

Add this MCP server to your Codex config:

[mcp_servers.ai-manage-tools]
command = "npx"
args = ["-y", "@bangdao-ai/ai-manage-tools@latest"]

[mcp_servers.ai-manage-tools.env]
AI_MANAGER_BASE_URL = "https://token.longshine.com/ai-manage"
AI_MANAGER_TOKEN = "aim_xxx"

Then ask Codex to call the status tool.

Claude Desktop

Add this to claude_desktop_config.json:

{
  "mcpServers": {
    "ai-manage-tools": {
      "command": "npx",
      "args": ["-y", "@bangdao-ai/ai-manage-tools@latest"],
      "env": {
        "AI_MANAGER_BASE_URL": "https://token.longshine.com/ai-manage",
        "AI_MANAGER_TOKEN": "aim_xxx"
      }
    }
  }
}

Restart Claude Desktop after editing the file.

Tools

| Tool | Purpose | | --- | --- | | status | Check base URL and whether AI_MANAGER_TOKEN is present. | | report | Upload a local JSONL usage fixture. | | collect | Collect a bounded local usage batch and upload it. | | doctor | Run a lightweight local diagnostic. | | backfill | Run the local backfill entrypoint. |

CLI fallback

The package also keeps a direct CLI mode:

AI_MANAGER_TOKEN=aim_xxx ai-manage-tools status --base-url https://token.longshine.com/ai-manage
ai-manage-tools report --host codex --fixture ./sample.jsonl --base-url https://token.longshine.com/ai-manage

For MCP clients, prefer the npx configuration above.