Splice MCP connector

1. Install the SDK

   Node.js

   npm install @scalekit-sdk/node

   Python

   pip install scalekit

   Full SDK reference: Node.js | Python

2. Set your credentials

   Add your Scalekit credentials to your .env file. Find values in app.scalekit.com > Developers > API Credentials.

   .env

   SCALEKIT_ENVIRONMENT_URL=<your-environment-url>
   SCALEKIT_CLIENT_ID=<your-client-id>
   SCALEKIT_CLIENT_SECRET=<your-client-secret>

3. Authorize and make your first call

   Node.js

   quickstart.ts

   import { ScalekitClient } from '@scalekit-sdk/node'
   import 'dotenv/config'
   
   const scalekit = new ScalekitClient(
     process.env.SCALEKIT_ENV_URL,
     process.env.SCALEKIT_CLIENT_ID,
     process.env.SCALEKIT_CLIENT_SECRET,
   )
   const actions = scalekit.actions
   
   const connector = 'splicemcp'
   const identifier = 'user_123'
   
   // Generate an authorization link for the user
   const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
   console.log('Authorize Splice MCP:', link)
   process.stdout.write('Press Enter after authorizing...')
   await new Promise(r => process.stdin.once('data', r))
   
   // Make your first call
   const result = await actions.executeTool({
     connector,
     identifier,
     toolName: 'splicemcp_create_stack',
     toolInput: { asset_uuid: 'YOUR_ASSET_UUID' },
   })
   console.log(result)

   Python

   quickstart.py

   import os
   from scalekit.client import ScalekitClient
   from dotenv import load_dotenv
   load_dotenv()
   
   scalekit_client = ScalekitClient(
       env_url=os.getenv("SCALEKIT_ENV_URL"),
       client_id=os.getenv("SCALEKIT_CLIENT_ID"),
       client_secret=os.getenv("SCALEKIT_CLIENT_SECRET"),
   )
   actions = scalekit_client.actions
   
   connection_name = "splicemcp"
   identifier = "user_123"
   
   # Generate an authorization link for the user
   link_response = actions.get_authorization_link(
       connection_name=connection_name,
       identifier=identifier,
   )
   print("Authorize Splice MCP:", link_response.link)
   input("Press Enter after authorizing...")
   
   # Make your first call
   result = actions.execute_tool(
       tool_input={"asset_uuid":"YOUR_ASSET_UUID"},
       tool_name="splicemcp_create_stack",
       connection_name=connection_name,
       identifier=identifier,
   )
   print(result)

What you can do

Connect this agent connector to let your agent:

• Update stack — Modify an existing stack by adding, removing, or swapping sounds, or by renaming it or changing its BPM
• Stack share, prompt to — Generate a public shareable URL for an existing stack by its UUID
• Asset download — Purchase a Splice sample and return a presigned download URL for the audio file
• Sound describe a — Search the Splice catalog for samples matching a natural language description, with optional BPM and type filters
• Create stack — Create a multi-track stack from an existing Splice sample, optionally generating a public share URL

Tool list

Use the exact tool names from the Tool list below when you call execute_tool. If you’re not sure which name to use, list the tools available for the current user first.

splicemcp_create_stack # Create a multi-track stack from an existing Splice sample, optionally generating a public share URL. 4 params ▾

Create a multi-track stack from an existing Splice sample, optionally generating a public share URL.

Name Type Required Description

asset_uuid string required The UUID of the sample to use as the seed for the stack

bpm integer optional Target BPM for the stack (e.g. use the seed sample's BPM). Omit to let the backend decide.

generate_public_url boolean optional Set to true ONLY if the user explicitly asks for a shareable, public, or web link. Defaults to false.

name string optional An optional name for the stack

splicemcp_describe_a_sound # Search the Splice catalog for samples matching a natural language description, with optional BPM and type filters. 4 params ▾

Search the Splice catalog for samples matching a natural language description, with optional BPM and type filters.

Name Type Required Description

query string required Natural language description of the sound you are looking for

bpm_max integer optional Maximum BPM filter

bpm_min integer optional Minimum BPM filter

type string optional Sample type: loop or oneshot

splicemcp_download_asset # Purchase a Splice sample and return a presigned download URL for the audio file. 2 params ▾

Purchase a Splice sample and return a presigned download URL for the audio file.

Name Type Required Description

asset_uuid string required UUID of the asset to download

download_path string optional Optional hint indicating where the client should save the downloaded file. The server returns a presigned URL; the client is responsible for fetching and saving the file. Omit when the client does not have local filesystem access (e.g. web-based clients).

splicemcp_prompt_to_stack # Generate a complete multi-track arrangement of compatible samples from a text prompt describing the desired sound. 4 params ▾

Generate a complete multi-track arrangement of compatible samples from a text prompt describing the desired sound.

Name Type Required Description

prompt string required Your prompt describing the sound you want to create (e.g. "lo-fi hip hop beat at 80 bpm with a groovy bassline and jazzy piano", "an upbeat pop song in the style of Bruno Mars in the key of C major")

bpm_max integer optional Maximum BPM for sample selection based on the genre. Must be provided together with bpm_min.

bpm_min integer optional Minimum BPM for sample selection based on the genre. Infer from genre when the user does not specify a BPM. Typical ranges: lo-fi/chill 60–100, soulful beats/R&B 70–120, pop 100–130, disco/funk 110–130, house/techno/dance 115–135, industrial/experimental 110–150, drum and bass/jungle 160–180. For genres not listed, ensure at least a 30 BPM spread between bpm_min and bpm_max.

generate_public_url boolean optional Set to true ONLY if the user explicitly asks for a shareable, public, or web link. Defaults to false.

splicemcp_share_stack # Generate a public shareable URL for an existing stack by its UUID. 1 param ▾

Generate a public shareable URL for an existing stack by its UUID.

Name Type Required Description

stack_uuid string required UUID of the stack to share

splicemcp_update_stack # Modify an existing stack by adding, removing, or swapping sounds, or by renaming it or changing its BPM. 8 params ▾

Modify an existing stack by adding, removing, or swapping sounds, or by renaming it or changing its BPM.

Name Type Required Description

stack_uuid string required The UUID of the stack to modify (returned as Stack UUID by create_stack or prompt_to_stack). Use the UUID value, not a URL.

add_asset_uuids string optional Asset UUIDs to add as new layers at the end of the stack. Mutually exclusive with add_compatible_layers.

add_compatible_layers string optional Layers to add using harmonically compatible samples. Specify the instrument type for each layer. Mutually exclusive with add_asset_uuids.

bpm integer optional New playback BPM for the stack

name string optional New name for the stack (max 64 characters)

remove_layer_uuids string optional Layer UUIDs to remove from the stack (use the Layer UUID values shown in the stack output)

swap_compatible_layers string optional Layers to swap with harmonically compatible replacements. Mutually exclusive with swap_layers.

swap_layers string optional Layers whose sample content should be replaced with a specific asset. Mutually exclusive with swap_compatible_layers.