Bandmate MCP Server

Bandmate MCP Server

Provides access to the Bandmate REST API for managing songs with chord notations, lyrics, and metadata, as well as organizing them into lists. Supports searching, creating, updating, and retrieving songs and playlists with optional authentication.

Category
访问服务器

README

Bandmate MCP Server

An MCP (Model Context Protocol) server that provides access to the Bandmate REST API for managing songs and lists with chord notations.

Installation

cd bandmate-mcp
npm install
npm run build

Configuration

Set the following environment variables:

Variable Description Default
BANDMATE_API_URL Base URL for the Bandmate API https://vertigox.ue.r.appspot.com/api
BANDMATE_AUTH_TOKEN Firebase auth token for authenticated endpoints (empty)

Usage with Claude Code

Add to your Claude Code MCP configuration (~/.claude/mcp_settings.json):

{
  "mcpServers": {
    "bandmate": {
      "command": "node",
      "args": ["/path/to/bandmate-mcp/dist/index.js"],
      "env": {
        "BANDMATE_API_URL": "https://vertigox.ue.r.appspot.com/api",
        "BANDMATE_AUTH_TOKEN": "your-firebase-token"
      }
    }
  }
}

Or using npx (after publishing):

{
  "mcpServers": {
    "bandmate": {
      "command": "npx",
      "args": ["bandmate-mcp"],
      "env": {
        "BANDMATE_AUTH_TOKEN": "your-firebase-token"
      }
    }
  }
}

Available Tools

Song Tools

Tool Description
get_songs Get songs (public or filtered by userId/ids)
get_song Get a single song by ID
get_songs_by_user Get all songs created by a specific user
get_songs_in_list Get all songs in a specific list
upsert_song Create or update a song
search_songs Search songs by title or tags

List Tools

Tool Description
get_lists Get lists (public or filtered by userId)
get_list Get a single list by ID
upsert_list Create or update a list (requires auth)

Tool Parameters

get_songs

  • userId (optional): Filter to user's songs + public songs
  • ids (optional): Comma-separated song IDs to fetch

get_song

  • id (required): Song ID

get_songs_by_user

  • userId (required): User ID

get_songs_in_list

  • listId (required): List ID

upsert_song

  • id (optional): Song ID for updates
  • title (required): Song title
  • chordsText (required): Chord notation and lyrics
  • isPublic (optional): Public visibility (default: false)
  • bpm (optional): Beats per minute
  • key (optional): Musical key
  • voice (optional): Vocal range
  • tags (optional): Array of tags
  • spotifyUrl (optional): Spotify link
  • youtubeUrl (optional): YouTube link
  • userId (optional): Creator user ID

get_lists

  • userId (optional): Filter to user's lists + public lists

get_list

  • id (required): List ID

upsert_list

  • id (optional): List ID for updates
  • name (optional): List name
  • isPrivate (optional): Private visibility (default: false)
  • songs (optional): Array of song IDs
  • userId (optional): Owner user ID

search_songs

  • query (required): Search term
  • userId (optional): Include user's private songs

Development

# Run in development mode
npm run dev

# Build for production
npm run build

# Run production build
npm start

Deployment to Google Cloud Run

This MCP server uses SSE (Server-Sent Events) transport, making it deployable as a remote HTTP service.

Prerequisites

  1. Install the Google Cloud CLI
  2. Authenticate: gcloud auth login
  3. Set your project: gcloud config set project YOUR_PROJECT_ID

Deploy

# Build and deploy in one command
gcloud run deploy bandmate-mcp \
  --source . \
  --region us-central1 \
  --allow-unauthenticated \
  --set-env-vars "BANDMATE_API_URL=https://vertigox.ue.r.appspot.com/api"

# Or with authentication token
gcloud run deploy bandmate-mcp \
  --source . \
  --region us-central1 \
  --allow-unauthenticated \
  --set-env-vars "BANDMATE_API_URL=https://vertigox.ue.r.appspot.com/api,BANDMATE_AUTH_TOKEN=your-token"

Using the Remote MCP Server

Once deployed, you'll get a URL like https://bandmate-mcp-xxxxx-uc.a.run.app.

Endpoints

Endpoint Method Description
/ GET Service info
/health GET Health check
/sse GET SSE connection for MCP
/messages POST Client-to-server messages

With Claude Desktop (Remote SSE)

Add to your Claude Desktop config:

{
  "mcpServers": {
    "bandmate": {
      "url": "https://bandmate-mcp-xxxxx-uc.a.run.app/sse"
    }
  }
}

Local Docker Testing

# Build the image
docker build -t bandmate-mcp .

# Run locally
docker run -p 8080:8080 \
  -e BANDMATE_API_URL=https://vertigox.ue.r.appspot.com/api \
  bandmate-mcp

# Test health endpoint
curl http://localhost:8080/health

CI/CD with GitHub Actions

The repository includes automatic deployment to Cloud Run on every push to main.

Setup

  1. Create a GCP Service Account with the following roles:

    • Cloud Run Admin
    • Cloud Build Editor
    • Storage Admin
    • Service Account User
  2. Create a JSON key for the service account:

    gcloud iam service-accounts keys create key.json \
      --iam-account=YOUR_SA@YOUR_PROJECT.iam.gserviceaccount.com
    
  3. Add the secret to GitHub:

    • Go to your repo → Settings → Secrets and variables → Actions
    • Create a new secret named GCP_SA_KEY
    • Paste the contents of key.json
  4. Delete the local key file:

    rm key.json
    

Now every push to main will automatically deploy to Cloud Run.

License

MIT

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选