MCP Server (Beta)

Welcome to the official documentation for the Epidemic Sound Model Context Protocol (MCP) Server (Beta). This guide is designed for developers and partners who want to integrate Epidemic Sound's extensive music, sound effects and voices catalog into their AI-powered applications for automated content creation. It outlines how to connect to our MCP server to discover audio assets (music, sfx and voiceovers) and adapt tracks to specific styles or matching music to a specific video length.

Terms of Service

The Terms of Service for using the Epidemic Sound MCP Server (Beta) are available here.

Overview

What is the Epidemic Sound MCP Server (Beta)?

The Epidemic Sound MCP Server (Beta) is a powerful tool that acts as a bridge between your AI applications and our vast catalog of high-quality music, sound effects, and voiceovers. By leveraging the open MCP standard, our ES MCP server allows AI agents to intelligently and dynamically search for, discover, and retrieve information about our audio assets in real-time. This enables you to build applications that can seamlessly find the perfect soundtrack for any context, whether for a video, a game, a podcast, or any other creative project.

The Epidemic Sound MCP server is designed to be developer-friendly, providing a simple and efficient way to interact with our platform and ensuring compatibility with a wide range of AI development environments and tools.

Getting Started

Remote Server

The Epidemic Sound MCP server is available at https://www.epidemicsound.com/a/mcp-service/mcp.

Authentication & Setup

The Epidemic Sound MCP server supports two authentication methods:

OAuth Authentication - For AI clients like Cursor that support OAuth flows
Bearer Token Authentication - For programmatic access and custom integrations

Option 1: OAuth Authentication

The Epidemic Sound MCP server uses OAuth Dynamic Client Registration to connect MCP clients as per the MCP spec. This method is used by AI clients like Cursor and provides a seamless authentication experience.

Connecting to the Epidemic Sound MCP Server uses an OAuth flow that links directly to your Epidemic Sound account. This ensures a secure and seamless integration. You must be logged into www.epidemicsound.com to authenticate.

Allowlist of client redirect URIs: Epidemic Sound maintains an allowlist of vetted MCP client redirect URIs to protect our users from malicious phishing attacks. If there's an MCP client application that you want to allowlist, email us at mcp@epidemicsound.com.

Option 2: Bearer Token Authentication

For programmatic access and building custom integrations, you can use API key authentication. The API key is tied to your Epidemic Sound account.

Obtaining Your API Key:

Navigate to your Epidemic Sound account: https://www.epidemicsound.com/account/api-keys
Generate or copy your API key from the API Keys page
Store your API key securely - treat it like a password and never commit it to version control

Using Your API Key:

Keys are valid for a period of 30 days, after which they must be regenerated and recopied.

Include your API key in the Authorization header of all HTTP requests to the MCP server:

Authorization: Bearer YOUR_API_KEY

Best Practice: Store your API key in environment variables rather than hardcoding it:

# Set environment variable
export EPIDEMIC_SOUND_API_KEY="your_api_key_here"

// Reference in your code
const apiKey = process.env.EPIDEMIC_SOUND_API_KEY

Connecting with AI Clients

You can connect to the Epidemic Sound MCP Server from various AI-powered tools that support custom MCP integrations.

Cursor

Cursor provides native support for custom MCP servers and supports both OAuth and bearer token authentication methods.

Using OAuth Authentication (Recommended)

Open Settings: In Cursor, navigate to Settings > MCP.
Click the New MCP server button. This will open a configuration file named mcp.json.
Configure the Server: Add the following JSON configuration:

{
  "mcpServers": {
    "epidemic-sound": {
      "url": "https://www.epidemicsound.com/a/mcp-service/mcp"
    }
  }
}

In the MCP settings tab, you will now see your newly configured server. Click the Connect button.
Authorize Access: A browser tab will open, prompting you to login with your Epidemic Sound account.
Start Querying: Once connected, the toggle next to the server name will be active. You can now begin making requests to the Epidemic Sound MCP server directly from Cursor prompts!

Using Bearer Token Authentication (Alternative)

Alternatively, you can use bearer token authentication with your API key:

Open Settings: In Cursor, navigate to Settings > MCP.
Click the New MCP server button. This will open a configuration file named mcp.json.
Configure the Server: Add the following JSON configuration:

{
  "mcpServers": {
    "epidemic-sound": {
      "url": "https://www.epidemicsound.com/a/mcp-service/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

Replace YOUR_API_KEY with your actual API key from https://www.epidemicsound.com/account/api-keys.

In the MCP settings tab, you will now see your newly configured server. Click the Connect button.
Start Querying: Once connected, the toggle next to the server name will be active. You can now begin making requests to the Epidemic Sound MCP server directly from Cursor prompts!

Core Capabilities for AI-driven Workflows

Our MCP tools are designed to help AI agents and automated production flows intelligently discover, adapt, and integrate audio content into creative projects. The following capabilities enable seamless integration of music, sound effects, and voiceovers into your AI-powered applications.

Available Tools

Resource	Tool	Description
Music Discovery	`search_music`	Searches the music catalog by keyword or topic, with filters for BPM, mood, duration, instruments, key, and vocals, along with various sorting options.
	`find_similar_track`	Discovers tracks with similar musical characteristics to a given Epidemic Sound trackID.
	`search_external_track`	Finds Epidemic Sound tracks that match the style of external tracks (e.g., from Spotify).
Sound Effects Discovery	`search_sound_effects`	Queries the sound effects catalog by search term, duration, and tags.
	`find_similar_sound_effects`	Finds variations and alternatives for a given sound effect ID.
Voiceovers	`browse_voice_artists`	Explores available AI voices, including their voice characteristics and available languages.
	`list_user_generated_voices`	Lists the voice replicas created using your own voice.
	`generate_voiceover`	Converts a text script into an AI voiceover using a specified voice artist.
	`get_voiceover_status`	Checks the generation status (e.g., DONE, GENERATING) of a voiceover job.
	`get_voiceover_details`	Retrieves complete metadata, audio URLs, and waveform data for a generated voiceover.
	`download_voiceover`	Downloads the high-quality audio file of a completed voiceover.
Asset Downloads	`download_music_track`	Downloads original music tracks in full or as individual stems (bass, drums, etc.).
	`download_sound_effect`	Downloads original sound effect files in MP3 or WAV format.

1. Music Discovery

Find the perfect track for any creative project through intelligent search and similarity matching.

Search Recordings

Search Epidemic Sound's music catalog with powerful filtering and sorting capabilities. AI agents can query by text terms or topics, then refine results using filters like BPM range, duration, mood, featured instruments, musical key, artist, and vocal presence.

Input:

Search query (text term or topic)
Optional filters: BPM range, duration (in milliseconds), mood slugs, artist slugs, featured instrument slugs, musical keys, tag slugs, vocals (boolean)
Optional sorting: relevance, popularity, date, duration, title, or BPM
Pagination parameters

Output:

List of recordings with full metadata: recording ID, title, BPM, cover art URL, audio file (with preview URL and waveform), available stems, tags, and artist credits
Pagination info and total count

Example use case: An AI agent analyzing a fitness video script searches for "energetic workout music" with 120-140 BPM, filters for tracks without vocals, and sorts by popularity.

Find Similar Tracks

Discover music similar to a track you already like. Provide a recording ID from Epidemic Sound's catalog to find tracks with matching musical characteristics.

Input: Recording ID from Epidemic Sound's catalog

Output: List of similar recordings with full metadata (same structure as Search Recordings)

Reference External Music

Search for external music references (like popular tracks on Spotify) to use as similarity search inputs. This helps find Epidemic Sound tracks that match the style of mainstream music.

Input: Search term (e.g., artist name, song title)

Output: List of external reference IDs (currently supports Spotify track IDs) that can be used in Search Recordings

Workflow:

Search for external reference: e.g., "Taylor Swift"
Get Spotify track ID from results
Use that ID in Search Recordings with externalID parameter to find similar tracks in Epidemic Sound's catalog

2. Sound Effects

Enhance your content with the right audio atmosphere through our comprehensive sound effects library.

Search Sound Effects

Query our sound effects catalog to find the perfect audio atmosphere for your content.

Input:

Search term (e.g., "door slam", "ocean waves", "city ambience")
Optional filters: duration range (in milliseconds), tag slugs, specific sound effect IDs
Optional sorting: relevance, popularity, date, duration, or title
Pagination parameters

Output:

List of sound effects with metadata: sound effect ID, title, audio file (with preview URL and waveform), tags
Pagination info and total count

Find Similar Sound Effects

Find variations and alternatives to a sound effect you've already selected.

Input: Sound effect ID from Epidemic Sound's catalog

Output: List of similar sound effects with full metadata

3. Track Adaptation (beta)

Transform any track to fit your exact content requirements with intelligent editing that preserves musical integrity.

Edit Recordings for Custom Lengths (beta)

Adapt any track to match video duration precisely while preserving musical structure, builds, drops, and key moments.

Input:

Recording ID from Epidemic Sound's catalog
Target duration in milliseconds (maximum 300,000ms / 5 minutes)
Download audio format: MP3 or WAV
Optional settings:
- forceDuration: Enforce exact duration match (boolean)
- loopable: Make output seamlessly loop (boolean)
- maxResults: Number of edit variations to generate
- preferenceRegions: Array of time ranges to prefer or avoid with start/end times in milliseconds
- requiredRegionsAtOffsets: Array of specific sections that must appear at exact timestamps in the output
- skipStems: Skip individual stem generation for faster processing (boolean)

Output:

Job ID for tracking the editing process
Status: PENDING, IN_PROGRESS, COMPLETED, or FAILED

Workflow:

Select a track using Search Recordings
Call Edit Recording with the recording ID and target duration
Poll the job status or wait for completion
Download the edited version(s) using the job ID and edit ID

Example: An AI agent needs a 47-second track for a product video. It requests a 47-second edit with the energetic chorus at the 15-second mark (using requiredRegionsAtOffsets). The MCP generates multiple variations to choose from.

Download Edited Tracks

Once editing is complete, download the high-quality audio files.

Input:

Job ID from the editing process
Edit ID (which variation to download)

Output: Direct download URL for the high-quality audio file (MP3 or WAV as specified during editing)

Note: Individual stems (drums, bass, instruments) are also available unless skipStems was enabled during editing.

4. Voiceover Creation

Generate professional AI voiceovers with natural-sounding voice artists from our library.

Browse Voice Artists

Explore available voices to find the perfect narrator for your content.

Input: Optional pagination parameters (offset and limit)

Output:

List of voices with metadata: voice ID, title, example audio URL, artwork, language code, supported languages array
Voice characteristics: gender, location, biography, vocal characteristics

List User-Generated Voices

Access custom voices you've created for your projects.

Input: Optional pagination parameters

Output: List of your custom voices with voice ID, title, and language code

Generate Voiceovers

Convert text scripts into professional narration.

Input:

Voice ID (from Browse Voice Artists or List User-Generated Voices)
Text script to narrate
Optional: Language code (IETF BCP 47 format, e.g., "en-US", "es-ES")
Optional: Speed adjustment (-1.0 to +1.0, where 0.0 is default speed)

Output:

Voiceover ID
Generation status: DONE, GENERATING, or FAILED
Failure reason (if status is FAILED)

Check Voiceover Status

Track generation progress for your voiceovers.

Input: Voiceover ID

Output: Current status (DONE, GENERATING, or FAILED) and failure reason if applicable

Get Voiceover Details

Retrieve complete information about a generated voiceover.

Input: Voiceover ID

Output:

Voiceover metadata: ID, original text, speed, language code
Audio details: playback URL, duration in milliseconds
Waveform visualization URL

Download Voiceover

Download high-quality voiceover files for production use.

Input: Voiceover ID

Output: Direct download URL for the high-quality audio file

Example workflow: An AI agent creating localized video ads generates voiceovers in English, Spanish, and French simultaneously, polls their generation status, and downloads the completed files for each language version.

5. Asset Downloads

All discovered and generated assets can be downloaded in production-ready formats.

Download Music Tracks

Input:

Recording ID
File format: MP3 or WAV
Stem type: FULL (complete mix), BASS, DRUMS, or INSTRUMENTS
Optional: Bundle option for downloading multiple stems together

Output: Direct download URL

Download Sound Effects

Input:

Sound effect ID
File format: MP3 or WAV
Optional: Bundle option

Output: Direct download URL

FAQ

Coming soon.

Reach out to us

Do you have questions or feedback on the Epidemic Sound MCP Server (Beta)? Email us at mcp@epidemicsound.com or join our Discord server.

Terms of Service​

Overview​

What is the Epidemic Sound MCP Server (Beta)?​

Getting Started​

Remote Server​

Authentication & Setup​

Option 1: OAuth Authentication​

Option 2: Bearer Token Authentication​

Connecting with AI Clients​

Cursor​

Using OAuth Authentication (Recommended)​

Using Bearer Token Authentication (Alternative)​

Core Capabilities for AI-driven Workflows​

Available Tools​

1. Music Discovery​

Search Recordings​

Find Similar Tracks​

Reference External Music​

2. Sound Effects​

Search Sound Effects​

Find Similar Sound Effects​

3. Track Adaptation (beta)​

Edit Recordings for Custom Lengths (beta)​

Download Edited Tracks​

4. Voiceover Creation​

Browse Voice Artists​

List User-Generated Voices​

Generate Voiceovers​

Check Voiceover Status​

Get Voiceover Details​

Download Voiceover​

5. Asset Downloads​

Download Music Tracks​

Download Sound Effects​

FAQ​

Reach out to us​

Terms of Service

Overview

What is the Epidemic Sound MCP Server (Beta)?

Getting Started

Remote Server

Authentication & Setup

Option 1: OAuth Authentication

Option 2: Bearer Token Authentication

Connecting with AI Clients

Cursor

Using OAuth Authentication (Recommended)

Using Bearer Token Authentication (Alternative)

Core Capabilities for AI-driven Workflows

Available Tools

1. Music Discovery

Search Recordings

Find Similar Tracks

Reference External Music

2. Sound Effects

Search Sound Effects

Find Similar Sound Effects

3. Track Adaptation (beta)

Edit Recordings for Custom Lengths (beta)

Download Edited Tracks

4. Voiceover Creation

Browse Voice Artists

List User-Generated Voices

Generate Voiceovers

Check Voiceover Status

Get Voiceover Details

Download Voiceover

5. Asset Downloads

Download Music Tracks

Download Sound Effects

FAQ

Reach out to us