Spotify MCP Server
Spotify MCP サーバー
Claude を介して Spotify とやり取りできるシンプルな Model Context Protocol (MCP) サーバーです。このサーバーにより、Claude は Spotify アカウントを使って曲を検索したり、プレイリストを作成したり、おすすめの表示などを行うことができます。
特徴
Spotifyでトラックを検索する
Spotifyプロフィールを表示する
プレイリストを作成する
プレイリストにトラックを追加する
パーソナライズされた音楽のおすすめを受け取る
Related MCP server: Spotify MCP Server
利用可能なツール
ツール名 | 説明 |
| Spotifyの認証情報を設定する |
| 資格情報が有効かどうか、誰がログインしているかを確認します |
| 名前、アーティスト、キーワードでトラックを検索 |
| Spotifyプロフィール情報を取得する |
| アカウントに新しいプレイリストを作成する |
| 既存のプレイリストにトラックを追加する |
| シードトラックに基づいて推奨事項を取得する |
セットアップ手順
1. 前提条件
Node.js v16以上
npm
Spotifyアカウント
登録済みのSpotify開発者アプリケーション
2. Spotify開発者アプリを作成する
Spotifyアカウントでログイン
「アプリを作成」をクリックします
アプリ名と説明を入力してください
リダイレクトURIとして
http://localhost:8888/callbackを追加します。クライアントIDとクライアントシークレットをメモしてください
3. プロジェクトをインストールする
# Clone or download the project first
cd spotify-mcp-server
# Install dependencies
npm install4. Spotifyトークンを入手する
spotify-auth.jsファイルを編集して、クライアント ID とクライアント シークレットを追加します。
// Replace these with your Spotify app credentials
const CLIENT_ID = "your_client_id_here";
const CLIENT_SECRET = "your_client_secret_here";次に、認証スクリプトを実行します。
node spotify-auth.jsこれにより、次のようになります。
ブラウザでURLを開く
Spotifyにログインするように促す
アカウントにアクセスする許可を求める
トークンを
secrets.jsonに保存する
5. MCPサーバーを構築する
npm run build6. Claudeデスクトップを設定する
Claude Desktop 構成ファイルを編集します。
macOSの場合:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows の場合:
%APPDATA%\Claude\claude_desktop_config.json
次の構成を追加します。
{
"mcpServers": {
"spotify": {
"command": "node",
"args": ["/full/path/to/spotify-mcp-server/build/spotify-mcp-server.js"]
}
}
}/full/path/to/spotify-mcp-serverプロジェクト ディレクトリへの実際のパスに置き換えます。
7. Claude Desktopを再起動します
新しい構成をロードするには、Claude Desktop を閉じて再度開きます。
使用法
クロードとの会話を始めるときは、まず Spotify の資格情報を設定する必要があります。
secrets.jsonファイルを参照して資格情報を取得しますset-spotify-credentialsツールを使用して認証するその後、他のSpotifyツールを使用します
プロンプトの例
資格情報の設定
I want to connect to my Spotify account. Here are my credentials from secrets.json:
Tool: set-spotify-credentials
Parameters:
{
"clientId": "your_client_id",
"clientSecret": "your_client_secret",
"accessToken": "your_access_token",
"refreshToken": "your_refresh_token"
}基本コマンド
アカウントを確認してください:
Can you check who I'm logged in as on Spotify?
Tool: get-current-user
Parameters: {}トラックを検索:
Search for songs by Weekend
Tool: search-tracks
Parameters:
{
"query": "Taylor Swift",
"limit": 5
}プレイリストを作成します:
Create a new playlist called "My Pretty pretty girlfriend"
Tool: create-playlist
Parameters:
{
"name": "My Pretty pretty girlfriend",
"description": "For my girlfriend. Created with Claude and the Spotify MCP server"
}複数ステップのタスク
曲のプレイリストを作成する:
I want to create a workout playlist with energetic songs. First, search for some high-energy songs. Then create a playlist called "Workout Mix" and add those songs to it.お気に入りに基づいて推奨事項を取得する:
I like the song "Blinding Lights" by The Weeknd. Can you search for it, then find similar songs, and create a playlist with those recommendations?トラブルシューティング
エラー: アクセストークンが利用できません: まず
set-spotify-credentialsツールを使用して資格情報を設定する必要があります認証失敗: トークンの有効期限が切れている可能性があります。認証スクリプトを再度実行して、新しいトークンを取得してください。
無効な認証情報: 正しいクライアントIDとクライアントシークレットを使用していることを確認してください
注記
サーバーは資格情報をメモリにのみ保存します
新しい会話を始めるたびに認証情報を設定する必要があります
Claude Desktopが再起動した場合は、資格情報を再度設定する必要があります。
Available Tools
7 toolsadd-tracks-to-playlistD
| Name | Required | Description | Default |
|---|---|---|---|
| playlistId | Yes | The Spotify playlist ID | |
| trackUris | Yes | Array of Spotify track URIs to add |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
check-credentials-statusD
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
create-playlistD
| Name | Required | Description | Default |
|---|---|---|---|
| description | No | Description of the playlist | |
| name | Yes | Name of the playlist |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get-current-userD
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get-recommendationsD
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Number of recommendations to return | |
| seedTracks | Yes | Spotify track IDs to use as seeds (max 5) |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
search-tracksD
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Number of results to return | |
| query | Yes | Search query for tracks |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
set-spotify-credentialsD
| Name | Required | Description | Default |
|---|---|---|---|
| accessToken | Yes | The Spotify Access Token | |
| clientId | Yes | The Spotify Client ID | |
| clientSecret | Yes | The Spotify Client Secret | |
| refreshToken | Yes | The Spotify Refresh Token |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
7 tool updates
v1.0.0- First observed
add-tracks-to-playlist - First observed
check-credentials-status - First observed
create-playlist - First observed
get-current-user - First observed
get-recommendations - First observed
search-tracks - First observed
set-spotify-credentials
TDQS
Scored across 7 tools
Most tools have distinct purposes targeting different Spotify resources like playlists, user info, recommendations, and tracks, but 'add-tracks-to-playlist' and 'create-playlist' could be confused if an agent needs to both create and populate a playlist in one operation. The lack of descriptions increases minor ambiguity.
The naming uses a mix of verb-noun patterns (e.g., 'create-playlist', 'search-tracks') and more descriptive phrases (e.g., 'check-credentials-status', 'set-spotify-credentials'), with all tools using kebab-case. This is readable but lacks a strict, predictable convention across all tools.
With 7 tools, this server is well-scoped for a Spotify integration, covering core functionalities like user management, playlist operations, search, and recommendations without being overwhelming or too sparse.
The toolset covers key Spotify operations like user info, search, recommendations, and playlist management, but lacks update or delete operations for playlists and tracks, and missing tools for managing playback or albums creates notable gaps in a full music streaming workflow.
Maintenance
Related MCP Connectors
Connect Claude to your Platform7n workspaces: chat, links, work and decks. One-click OAuth.
Search and ask the podcasts you follow inside Claude, with the exact quote and timestamp.
Search, read, create and edit your Memol notes from Claude. Team note-taking with AI search.
Connect Claude to Fathom meeting recordings, transcripts, and summaries
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceConnects Claude with Spotify to control playback, search music, get track information, and manage the queue through conversation.1-
- FlicenseAqualityDmaintenanceConnects Claude with Spotify, allowing users to control playback, search for music, get track/artist information, and manage the queue via the Spotify API.51-
- AlicenseNot gradedqualityNot gradedmaintenanceConnects Claude to Spotify for music discovery, playlist creation, and collection analysis through natural language. Enables searching songs, analyzing music diversity, creating playlists, and getting recommendations using Spotify's API.-
- AlicenseNot gradedqualityDmaintenanceEnables Claude to control Spotify features including playback control, playlist management, search, and accessing user's listening history and preferences through the Spotify API.1ISC