io.github.Trushtonfactory/anthropic-admin-mcp

io.github.Trushtonfactory/anthropic-admin-mcp·v0.1.1·AI & LLMs

Quality Score

/100

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

Repository →

§00 Trust verdict · v1 advisory · method

UNVERIFIEDno verdict on file

Verdict not yet evaluated for this tool. The hybrid eval runs adversarial cases first; coverage rolls out as the corpus expands. Until a verdict is recorded, an agent should treat this tool as not-yet-cleared and fall back to its own checks. Method: hybrid eval, four-state verdict, honest limits.

§01 Install

Claude Desktop (uvx)

{
  "mcpServers": {
    "anthropic-admin-mcp": {
      "command": "uvx",
      "args": [
        "anthropic-admin-mcp"
      ],
      "env": {
        "ANTHROPIC_ADMIN_KEY": "<your-anthropic_admin_key>",
        "ALLOWED_WORKSPACES": "<allowed_workspaces>",
        "AUDIT_LOG_PATH": "<audit_log_path>"
      }
    }
  }
}

§02 Environment variables

ANTHROPIC_ADMIN_KEY

requiredsecret

Your Anthropic Admin API key (Console -> Settings -> Admin Keys). Required.

ALLOWED_WORKSPACES

Optional comma-separated workspace IDs to scope write tools to. Recommended for least-privilege setups.

AUDIT_LOG_PATH

Path for JSONL audit log of mutating operations. Defaults to ./audit.jsonl.

§03 MCP Quality Score · methodology

freshness

completeness

installability