About Kinetune
Kinetune lets agents create lyric videos and Spotify Canvas loops from songs, with synchronized lyrics and audio-reactive visuals. Users receive a credit quote before approving a render; the project provides an MCP server, skill, and CLI.
Key features
- 01Create lyric videos from songs
- 02Generate Spotify Canvas loops
- 03Choose 9:16, 16:9, or 1:1 video formats
- 04Quote credit cost before rendering
- 05Use an agent skill or CLI
Use cases
- 01Make a vertical lyric video for a release
- 02Create a Spotify Canvas from cover art
- 03Check credit cost before approving a video
MCP support
Kinetune provides an MCP server at `https://kinetune.com/mcp`, using Streamable HTTP and OAuth sign-in. Agents can use it through an MCP client, or use the `kinetune` CLI instead.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://kinetune.com/mcpclaude mcp add --transport http kinetune https://kinetune.com/mcp{"mcpServers":{"kinetune":{"type":"http","url":"https://kinetune.com/mcp"}}}Open in Cursor{"servers":{"kinetune":{"type":"http","url":"https://kinetune.com/mcp"}}}Open in VS Code{"mcpServers":{"kinetune":{"type":"http","url":"https://kinetune.com/mcp"}}}{"mcpServers":{"kinetune":{"serverUrl":"https://kinetune.com/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project READMEKinetune for AI agents
Kinetune turns a song into release-ready video: lyric videos with word-synced lyrics and audio-reactive visuals in 9:16, 16:9 and 1:1, and Spotify Canvas loops designed from the song's cover.
This repository teaches AI agents to use it. Ask in plain words, for example "make a vertical lyric video for Midnight Drive" or "give my new single a Canvas". The agent finds the song, tells you exactly how many credits it costs, and makes the video only after you say yes.
Claude Code
/plugin marketplace add kinetune/skills
/plugin install kinetune@kinetune
The plugin adds the Kinetune skill and connects the Kinetune MCP server. Run /mcp, choose kinetune, then Authenticate to sign in with your Kinetune account.
Codex, Cursor, opencode and other agents
Install the skill with the skills installer:
npx skills add kinetune/skills
You can also copy skills/kinetune into your agent's skills folder.
The skill works through the MCP server when it is connected, or through the kinetune CLI otherwise:
npm install -g @kinetune/cli
kinetune auth login
MCP only
Point any MCP client at https://kinetune.com/mcp (Streamable HTTP, OAuth sign-in). It's listed in the official MCP Registry as com.kinetune/kinetune, and on Glama, Smithery, mcp.so, Cursor Directory and mcpservers.org. Setup for ChatGPT, Claude, Cursor and VS Code is at kinetune.com/developers.
What's inside
| Path | What it is |
|---|---|
skills/kinetune/SKILL.md | How to make lyric videos and Canvases, and the rule to quote before spending credits |
skills/kinetune/references/cli.md | Every CLI command |
.mcp.json | The Kinetune MCP server, for the Claude Code plugin |
.claude-plugin/ | The Claude Code plugin and marketplace manifests |
.codex-plugin/ | The plugin manifest for ChatGPT and Codex, with its listing details and review test cases |
assets/ | The icon and logo the plugin listings use |
Links
- Developer docs: REST API, MCP server, CLI and n8n
- Full API reference for LLMs
- Pricing
- Support: [email protected]
MIT licensed.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.