BailingHub Governance

Overview

BailingHub Governance is a Model Context Protocol server that lets you submit and inspect governed AI business actions through a self-hosted BailingHub control plane. It plugs directly into AI assistants as callable tools, giving your models access to governed workflows with built-in audit trails and human approval gates.

The server runs locally via npx -y bailinghub-mcp-server and communicates with your BailingHub instance over stdio. You'll need to configure three environment variables: BAILINGHUB_BASE_URL, BAILINGHUB_CLIENT_TOKEN, and BAILINGHUB_ROUTE. The latest release is v0.2.0, published under the MIT license, with source code available at bailinghub/bailinghub-mcp-server on GitHub.

BailingHub Governance appears in the AI & Agents category on mcp.site and works with Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed, and other MCP clients. If you maintain this server, claim your listing to verify ownership and keep the information up to date.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "bailinghub_governance": {
      "command": "npx",
      "args": [
        "-y",
        "bailinghub-mcp-server"
      ],
      "env": {
        "BAILINGHUB_BASE_URL": "<bailinghub-base-url>",
        "BAILINGHUB_CLIENT_TOKEN": "<bailinghub-client-token>",
        "BAILINGHUB_ROUTE": "<bailinghub-route>"
      }
    }
  }
}

Requires BAILINGHUB_BASE_URL, BAILINGHUB_CLIENT_TOKEN, BAILINGHUB_ROUTE