Skip to main content
Glama
igorgarbuz

Spotify MCP Node Server

by igorgarbuz

playMusic

Play Spotify tracks, albums, artists, or playlists by providing a URI, ID, or specifying the content type to initiate music playback on your device.

Instructions

Start playing a Spotify track, album, artist, or playlist

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
uriNoThe Spotify URI to play (overrides type and id)
typeNoThe type of item to play
idNoThe Spotify ID of the item to play
deviceIdNoThe Spotify device ID to play on

Implementation Reference

  • The handler function that destructures input args, validates them, constructs Spotify URI if needed, and uses handleSpotifyRequest to interact with Spotify player API for playback.
    handler: async (args, extra: SpotifyHandlerExtra) => {
      const { uri, type, id, deviceId } = args;
    
      if (!uri && (!type || !id)) {
        return {
          content: [
            {
              type: 'text',
              text: 'Error: Must provide either a URI or both a type and ID',
              isError: true,
            },
          ],
        };
      }
    
      let spotifyUri = uri;
      if (!spotifyUri && type && id) {
        spotifyUri = `spotify:${type}:${id}`;
      }
    
      await handleSpotifyRequest(async (spotifyApi) => {
        const device = deviceId || '';
    
        if (!spotifyUri) {
          await spotifyApi.player.startResumePlayback(device);
          return;
        }
    
        if (type === 'track') {
          await spotifyApi.player.startResumePlayback(device, undefined, [
            spotifyUri,
          ]);
        } else {
          await spotifyApi.player.startResumePlayback(device, spotifyUri);
        }
      });
    
      return {
        content: [
          {
            type: 'text',
            text: `Started playing ${type || 'music'} ${id ? `(ID: ${id})` : ''}`,
          },
        ],
      };
    },
  • Zod schema for playMusic tool inputs: optional uri, type (track/album/artist/playlist), id, and deviceId.
    schema: {
      uri: z
        .string()
        .optional()
        .describe('The Spotify URI to play (overrides type and id)'),
      type: z
        .enum(['track', 'album', 'artist', 'playlist'])
        .optional()
        .describe('The type of item to play'),
      id: z.string().optional().describe('The Spotify ID of the item to play'),
      deviceId: z
        .string()
        .optional()
        .describe('The Spotify device ID to play on'),
    },
  • src/index.ts:12-14 (registration)
    Registers all tools (including playMusic from playTools) to the MCP server by calling server.tool() for each.
    [...playTools, ...readTools, ...writeTools].forEach((tool) => {
      server.tool(tool.name, tool.description, tool.schema, tool.handler);
    });
  • src/player.ts:130-130 (registration)
    Exports playTools array containing the playMusic tool for use in main server registration.
    export const playTools = [playMusic, playbackAction];
  • Helper utility wrapped around Spotify API calls in the playMusic handler; manages authentication, token refresh, and error retry.
    export async function handleSpotifyRequest<T>(
      action: (spotifyApi: SpotifyApi) => Promise<T>,
    ): Promise<T> {
      let config = loadSpotifyConfig();
      let spotifyApi: SpotifyApi;
      try {
        // If token is expired, refresh first
        if (
          config.accessTokenExpiresAt &&
          config.accessTokenExpiresAt - Date.now() < 60 * 1000
        ) {
          config = await refreshAccessToken(config);
        }
        spotifyApi = createSpotifyApi();
        return await action(spotifyApi);
      } catch (error: any) {
        // If 401, try refresh once
        if (error?.status === 401 || /401|unauthorized/i.test(error?.message)) {
          config = await refreshAccessToken(config);
          cachedSpotifyApi = null;
          spotifyApi = createSpotifyApi();
          return await action(spotifyApi);
        }
        // Skip JSON parsing errors as these are actually successful operations
        const errorMessage = error instanceof Error ? error.message : String(error);
        if (
          errorMessage.includes('Unexpected token') ||
          errorMessage.includes('Unexpected non-whitespace character') ||
          errorMessage.includes('Exponent part is missing a number in JSON')
        ) {
          return undefined as T;
        }
        // Rethrow other errors
        throw error;
      }
    }

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

B3.3/5.0
Behavior2/5

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

No annotations exist, so the description must disclose side effects, requirements (like active device), and behavior such as replacing current queue. It only states the action, leaving the agent to guess about deviceId handling, error conditions, or return values.

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?

A single, to-the-point sentence. It's efficient but lacks additional context that could aid selection; still, it doesn't waste 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?

With no output schema and no annotations, the description fails to convey essential behavioral details such as whether playback starts immediately, what happens without a deviceId, or the response format. Incomplete for a 4-param tool with optional interactions.

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?

All four parameters are fully described in the schema, so the description adds no additional parameter semantics. It doesn't explain how id, uri, and type interrelate or which takes precedence.

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 uses a specific verb ('Start playing') and resource ('Spotify track, album, artist, or playlist'), clearly distinguishing from sibling playback controls like pause and skip. It accurately reflects the tool's function.

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?

No explicit when-to-use or alternative guidance is provided. While the function is intuitive, it doesn't mention exclusions (e.g., when to use resume vs play) or prerequisites.

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