Band MCP Server

by kanghouchao

168 downloads
Not rated
GitHub

About

Band MCP Server is a Model Context Protocol server that integrates with the Band API, allowing AI assistants and other MCP-compatible tools to interact seamlessly with the Band social platform.

Details

Author
kanghouchao
Downloads
168
Categories
Other

- Integrates with the Band API via the Model Context Protocol.
- Works with any MCP-compatible client, such as Claude Desktop.
- Available as a standalone npm package or Docker container.
- Requires only a Band API Access Token for authentication.
- Enables AI-driven interaction with the Band social platform.

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name Band MCP Server
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Obtain a Band API Access Token from the Band Developer Portal, then configure the server in your MCP client (e.g., Claude Desktop) using either the npm package (band-mcp-server) or the Docker image (kanghouchao/band-mcp-server:latest). Set the token as the BAND_ACCESS_TOKEN environment variable.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "band mcp server": {
            "band-mcp-server": {
                "command": "docker",
                "args": [
                    "build",
                    "-t",
                    "band-mcp-server:latest",
                    "."
                ]
            }
        }
    }
}

McpServers

{
    "band-mcp-server": {
        "command": "docker",
        "args": [
            "build",
            "-t",
            "band-mcp-server:latest",
            "."
        ]
    }
}

Band MCP Server

NPM Version
Docker Pulls

A fully functional Model Context Protocol (MCP) server that integrates with the Band API. This server enables seamless interaction with the Band social platform through AI assistants and other MCP-compatible tools.

Overview

This server can be used in two primary ways:

1. As a standalone executable: Installed via npm and configured directly in a compatible MCP client.
2. As a Docker container: Pulled from Docker Hub and configured in a compatible MCP client to be run on-demand.

Usage & Client Configuration

To use this server, you need a Band API Access Token. You can obtain one from the Band Developer Portal.

Below are configuration examples for different clients and usage methods.

Example 1: Claude Desktop (NPM version)

This method assumes you have installed the server via npm install -g band-mcp-server.

1. In Claude Desktop, open Settings > Developer and click Edit Config.
2. Add the following to the mcpServers object in claude_desktop_config.json:

{
  "mcpServers": {
    "band-api": {
      "command": "band-mcp-server",
      "args": [],
      "env": {
        "BAND_ACCESS_TOKEN": "your_band_api_access_token"
      }
    }
  }
}
Replace your_band_api_access_token with your actual token.

Example 2: Claude Desktop (Docker version)

This method uses the Docker image and does not require npm.

1. In Claude Desktop, open Settings > Developer and click Edit Config.
2. Add the following to the mcpServers object in claude_desktop_config.json:

{
  "mcpServers": {
    "band-api-docker": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "BAND_ACCESS_TOKEN=your_band_api_access_token",
        "kanghouchao/band-mcp-server:latest"
      ]
    }
  }
}
Replace your_band_api_access_token with your actual token.

License

This project is licensed under the MIT License.

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.