Songbrain
Song in, video plan out: beat grid, best moments, timed lyrics, story and a beat-synced shot plan.
Should I use this
Quality & Safety
Findings (2)
- LOWTool 'get_pricing' description lacks action verbin get_pricing
- LOWTool 'get_account' description lacks action verbin get_account
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"songbrain": {
"url": "https://api.songbrain.ai/mcp"
}
}
}Remote endpoints
https://api.songbrain.ai/mcpstreamable-httpWhat it can do
Tool inventory
Tools (7)
🟢list_example_songs
List real Songbrain analyses of Songbrain's own songs (no API key needed). Use one to show what the API returns before analysing a user's song.
Input Schema
{
"type": "object",
"properties": {},
"additionalProperties": false
}🟢get_example_analysis(example_id, sections, view)
Full analysis of an example song: Song DNA, beat grid and sections, best moments, lyrics, scores, story and shot plan. No API key needed. Summary view by default (no per-word timings or beat arrays); set view='full' for everything.
Input Schema
{
"type": "object",
"properties": {
"example_id": {
"type": "string",
"description": "id from list_example_songs"
},
"sections": {
"type": "array",
"items": {
"type": "string",
"enum": [
"song_dna",
"timeline",
"best_moments",
"lyrics",
"scores",
"story",
"shot_plan"
]
},
"description": "Only these sections (default: all)"
},
"view": {
"type": "string",
"enum": [
"summary",
"full"
],
"default": "summary"
}
},
"required": [
"example_id"
],
"additionalProperties": false
}🟢get_example_shot_plan(example_id)
The beat-synced shot plan of an example song: every scene with start and end seconds, its act (setup, turn or payoff), the image/video prompt, framing, motion and the lyric sung under it, plus the story, world and palette. No key needed.
Input Schema
{
"type": "object",
"properties": {
"example_id": {
"type": "string"
}
},
"required": [
"example_id"
],
"additionalProperties": false
}🟢get_pricing
Songbrain API prices (free songs per month, price per song) and limits.
Input Schema
{
"type": "object",
"properties": {},
"additionalProperties": false
}🟢analyze_song(audio_url, title, artist, lyrics)
Start the analysis of a song at a public audio URL (MP3, WAV, FLAC, M4A, AAC, OGG or AIFF; 30 s to 10 min). Needs an API key on the MCP connection. Returns a song_id; poll get_song until status is 'done' (typically 60–90 seconds, up to ~2 minutes when busy). Uses one free song or 25 credits.
Input Schema
{
"type": "object",
"properties": {
"audio_url": {
"type": "string",
"description": "Public http(s) URL of the audio file"
},
"title": {
"type": "string"
},
"artist": {
"type": "string"
},
"lyrics": {
"type": "string",
"description": "Optional: the song's lyrics as plain text. Used for the exact words (timings still come from the audio)."
}
},
"required": [
"audio_url"
],
"additionalProperties": false
}🟢get_song(song_id, sections, view)
Status of a song started with analyze_song, then its full analysis once done. Summary view by default; view='full' adds word timings and beat arrays.
Input Schema
{
"type": "object",
"properties": {
"song_id": {
"type": "string"
},
"sections": {
"type": "array",
"items": {
"type": "string",
"enum": [
"song_dna",
"timeline",
"best_moments",
"lyrics",
"scores",
"story",
"shot_plan"
]
}
},
"view": {
"type": "string",
"enum": [
"summary",
"full"
],
"default": "summary"
}
},
"required": [
"song_id"
],
"additionalProperties": false
}🟢get_account
Free songs left this month, credit balance and price per song for the connected key.
Input Schema
{
"type": "object",
"properties": {},
"additionalProperties": false
}Community
Evidence