Skip to main content
Glama
varunneal

Spotify MCP Server

by varunneal

spotify-mcp MCP 服务器

MCP 项目将 Claude 与 Spotify 连接起来。基于spotipy-dev 的 API构建。

特征

  • 开始、暂停和跳过播放

  • 搜索曲目/专辑/艺术家/播放列表

  • 获取有关曲目/专辑/艺术家/播放列表的信息

  • 管理 Spotify 队列

  • 管理、创建和更新播放列表

Related MCP server: Vulpes Spotify MCP Server

演示

确保打开音频

配置

获取 Spotify API 密钥

在developer.spotify.com上创建一个帐户。导航到仪表板。创建一个应用程序,其redirect_uri为http://127.0.0.1:8080/callback 。您可以选择任何所需的端口,但必须使用http和显式的环回地址(IPv4或IPv6)。

更多信息/故障排除请参见此处。您可能需要重启 MCP 环境(例如 Claude Desktop)一到两次才能正常工作。

在本地运行此项目

该项目尚未设置临时环境(例如uvx使用)。请克隆此 repo 以在本地运行该项目。

git clone https://github.com/varunneal/spotify-mcp.git

将此工具添加为 mcp 服务器。

MacOS 上的 Claude 桌面: ~/Library/Application\ Support/Claude/claude_desktop_config.json

Windows 上的 Claude 桌面: %APPDATA%/Claude/claude_desktop_config.json

"spotify": {
    "command": "uv",
    "args": [
      "--directory",
      "/path/to/spotify_mcp",
      "run",
      "spotify-mcp"
    ],
    "env": {
      "SPOTIFY_CLIENT_ID": YOUR_CLIENT_ID,
      "SPOTIFY_CLIENT_SECRET": YOUR_CLIENT_SECRET,
      "SPOTIFY_REDIRECT_URI": "http://127.0.0.1:8080/callback"
    }
  }

故障排除

如果您无法使用此 MCP,请提交问题。以下是一些提示:

  1. 确保uv已更新。我推荐版本>=0.54 。

  2. 确保 claude 具有该项目的执行权限: chmod -R 755 。

  3. 确保您拥有 Spotify premium(运行开发人员 API 所需)。

此 MCP 会将日志发送到 std err(如 MCP 规范中所述)。在 Mac 上,Claude 桌面应用程序会将这些日志发送到~/Library/Logs/Claude 。在其他平台上,您可以在此处找到日志。

您可以使用以下命令通过npm启动 MCP Inspector:

npx @modelcontextprotocol/inspector uv --directory /path/to/spotify_mcp run spotify-mcp

启动后,检查器将显示一个 URL,您可以在浏览器中访问该 URL 以开始调试。

待办事项

遗憾的是,Spotify API 中许多很酷的功能现已弃用。大多数新功能都相对较小,或者是为了项目的健康发展:

  • 測試。

  • 添加用于管理播放列表的 API 支持。

  • 添加分页搜索结果/播放列表/专辑的 API 支持。

公关赞赏!感谢 @jamiew、@davidpadbury、@manncodes、@hyuma7、@aanurraj 和其他人的贡献。

部署

(待办事项)

构建和发布

准备分发包:

  1. 同步依赖项并更新锁文件:

uv sync
  1. 构建软件包分发版:

uv build

这将在dist/目录中创建源和轮子分布。

  1. 发布到 PyPI:

uv publish

注意:您需要通过环境变量或命令标志设置 PyPI 凭据:

  • 令牌: --token或UV_PUBLISH_TOKEN

  • 或用户名/密码: --username / UV_PUBLISH_USERNAME和--password / UV_PUBLISH_PASSWORD

Available Tools

5 tools
SpotifyGetInfoA

Get detailed information about a Spotify item (track, album, artist, or playlist).

ParametersJSON Schema
NameRequiredDescriptionDefault
item_uriYesURI of the item to get information about. If 'playlist' or 'album', returns its tracks. If 'artist', returns albums and top tracks.

TDQS

A3.7/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are present, so the description carries the full burden. It explains return differences by type (tracks for albums/playlists, albums/top tracks for artists), but does not specify nondestructive nature, authentication needs, or rate limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, concise sentence with no wasted words. It efficiently conveys the core function.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, the description partially compensates by specifying behavior per item type, but it does not enumerate all returned fields (e.g., metadata like name, duration). This leaves some ambiguity for a simple tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and already details the URI parameter's behavior. The description adds no additional meaning beyond restating the tool's purpose, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool retrieves detailed information for a Spotify item (track, album, artist, or playlist), differentiating it from siblings like SpotifySearch (which searches by query) and SpotifyPlayback/Queue (which control playback).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the schema requiring a URI, but the description does not explicitly state when to use this tool over siblings or provide exclusions. An agent must infer context from sibling names.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

SpotifyPlaybackB

Manages the current playback with the following actions: - get: Get information about user's current track. - start: Starts playing new item or resumes current playback if called with no uri. - pause: Pauses current playback. - skip: Skips current track.

ParametersJSON Schema
NameRequiredDescriptionDefault
actionYesAction to perform: 'get', 'start', 'pause' or 'skip'.
spotify_uriNoSpotify uri of item to play for 'start' action. If omitted, resumes current playback.
num_skipsNoNumber of tracks to skip for `skip` action.

TDQS

B3.4/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the transparency burden. It discloses basic behaviors like 'resumes current playback' for start and 'skips current track' for skip, but omits details on permissions, rate limits, error states (e.g., no active device), and whether get returns current track info or just status.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise: one introductory sentence followed by a bullet list of actions. Every piece of information is front-loaded and relevant. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (multi-action playback control) and lack of output schema or annotations, the description is incomplete. It fails to mention prerequisites like an active Spotify device, account type requirements, or error handling. Important operational context is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. The tool description does not add significant meaning beyond the schema's parameter descriptions; it repeats the same action list. For example, 'num_skips' and 'spotify_uri' are already explained in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool manages current playback and lists four specific actions (get, start, pause, skip). This is a specific verb+resource with clear action breakdown, distinguishing it from sibling tools like SpotifyGetInfo (which likely retrieves broader info) and SpotifyQueue (queue management).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives, nor does it mention prerequisites (e.g., active device) or when not to use it (e.g., if user lacks Premium). Usage context is entirely implicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

SpotifyPlaylistC

Manage Spotify playlists. - get: Get a list of user's playlists. - get_tracks: Get tracks in a specific playlist. - add_tracks: Add tracks to a specific playlist. - remove_tracks: Remove tracks from a specific playlist. - change_details: Change details of a specific playlist. - create: Create a new playlist.

ParametersJSON Schema
NameRequiredDescriptionDefault
actionYesAction to perform: 'get', 'get_tracks', 'add_tracks', 'remove_tracks', 'change_details', 'create'.
playlist_idNoID of the playlist to manage.
track_idsNoList of track IDs to add/remove.
nameNoName for the playlist (required for create and change_details).
descriptionNoDescription for the playlist.
publicNoWhether the playlist should be public (for create action).

TDQS

C2.6/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. While it lists six actions and their basic purposes, it doesn't disclose critical behavioral traits: authentication requirements, rate limits, whether operations are destructive, what happens on errors, or what the return values look like. For a multi-action tool with potential write operations (add, remove, change, create), this is a significant gap in transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is efficiently structured with a brief overview followed by a bulleted list of actions. Each bullet is concise and to the point. However, the opening 'Manage Spotify playlists' is redundant with the tool name and could be eliminated, and the bullet format while clear isn't the most natural language for AI comprehension.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex multi-action tool with six parameters and no annotations or output schema, the description is incomplete. It doesn't explain return values, error conditions, authentication requirements, or the relationships between actions. The tool handles both read and write operations, but the description provides minimal behavioral context, making it inadequate for safe and effective use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all six parameters thoroughly. The description doesn't add any meaningful parameter semantics beyond what's in the schema - it simply lists action names without explaining parameter dependencies or constraints. The baseline of 3 is appropriate when the schema does all the parameter documentation work.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states 'Manage Spotify playlists' which is a vague purpose that doesn't specify what management entails. It then lists six sub-actions with brief explanations, but the overall purpose remains broad. While it distinguishes from sibling tools by focusing on playlists rather than search, playback, or queue operations, the verb 'manage' is too generic for clear understanding.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided about when to use this tool versus the sibling tools (SpotifyGetInfo, SpotifyPlayback, SpotifyQueue, SpotifySearch). The description lists six actions but doesn't explain when each should be used relative to each other or to other tools. There's no mention of prerequisites, authentication requirements, or contextual factors that would guide selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

SpotifyQueueB

Manage the playback queue - get the queue or add tracks.

ParametersJSON Schema
NameRequiredDescriptionDefault
actionYesAction to perform: 'add' or 'get'.
track_idNoTrack ID to add to queue (required for add action)

TDQS

B3.4/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist, so the description bears full responsibility. It fails to disclose behavior such as whether adding a track requires an active device, if the queue is appended or overwritten, or what errors occur. Minimal behavioral detail beyond the schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Single, concise sentence that immediately communicates the tool's purpose. No superfluous words, front-loads the resource and actions.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool with two parameters and two actions, the description adequately covers purpose. It lacks details on return values or error cases but is sufficient for basic usage given no output schema and limited complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with parameter descriptions. The description adds marginal value by linking 'add tracks' to the action parameter and implying track_id for add. Baseline score is appropriate as schema handles semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool manages the playback queue with two specific actions: get or add tracks. It distinguishes itself from sibling tools like SpotifyPlayback by focusing on queue management.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives like SpotifyPlayback for control operations. The description simply lists actions without context on prerequisites or typical use cases.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

SpotifySearchB

Search for tracks, albums, artists, or playlists on Spotify.

ParametersJSON Schema
NameRequiredDescriptionDefault
queryYesquery term
qtypeNoType of items to search for (track, album, artist, playlist, or comma-separated combination)track
limitNoMaximum number of items to return

TDQS

B3.4/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries burden. It mentions search types and parameters but omits behavior like response structure, pagination, error handling, auth needs, or rate limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Single clear sentence, front-loaded with action verb. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 3 parameters, no output schema, and no annotations, the description is too brief. Lacks guidance on output format, pagination, or effective usage compared to sibling tools.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema has 100% coverage with descriptions for all 3 parameters. Description adds minimal context beyond schema (e.g., hinting at qtype values already documented). Baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states it searches for tracks, albums, artists, or playlists on Spotify. Distinct from sibling tools like SpotifyGetInfo (specific item info), SpotifyPlayback (playback control), SpotifyQueue (queue management).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Description implies usage for searching Spotify content, but no explicit when-to-use vs alternatives, no when-not or exclusions provided.

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.

  1. 5 tool updatesv1.0.0
    • First observedSpotifyGetInfo
    • First observedSpotifyPlayback
    • First observedSpotifyPlaylist
    • First observedSpotifyQueue
    • First observedSpotifySearch

TDQS

B3.3/5.0

Scored across 5 tools

Disambiguation4/5

Most tools have distinct purposes: GetInfo for metadata, Playback for player control, Playlist for playlist management, Queue for queue operations, and Search for finding content. However, there is some potential overlap between GetInfo and Search, as both can retrieve item details, though GetInfo is more specific to known items while Search is for discovery.

Naming Consistency4/5

Tool names follow a consistent 'Spotify' prefix and descriptive noun-based naming (e.g., SpotifyPlayback, SpotifyPlaylist). The internal actions within tools (like get, start, pause) are also consistent. A minor deviation is that some tools use underscores in action names (e.g., get_tracks), while others do not, but overall the pattern is clear and readable.

Tool Count5/5

With 5 tools, the server is well-scoped for Spotify integration, covering key areas like playback control, playlist management, search, and queue handling. Each tool serves a distinct purpose without being overly broad or too narrow, making it manageable and functional for typical agent tasks.

Completeness4/5

The tool set covers core Spotify functionalities: playback control, playlist CRUD operations, search, and queue management. Minor gaps include lack of user profile management (e.g., get user info) or more advanced features like recommendations, but the essential workflows for playing music and managing content are well-supported.

Maintenance

ActivityInactive
ResponsivenessUnresponsive

Related MCP Connectors

Related MCP Servers