Definitive MCP server for Ableton Live: complete LOM coverage, embedded knowledge base and music recipes.
from $19/mo
Tools
get_capabilities
Get Compeller platform capabilities, supported features, and API version.
ArgumentsA call is made on an account: it counts against an allowance and the publisher sees it, which is why this one asks who you are first.
—
p95 latency
—
call success
—
uptime 90d
0
calls last 7d
What it does
Create and track AI music videos and audio-reactive visuals from songs.
Quickstart
# 1 — install (mcprush login holds a key from your dashboard)
npx mcprush@latest add compeller-mcp
# 2 — ask your agent something
> Create and track AI music videos and audio-reactive visuals from songs.
Compeller is free: there is no plan to choose, no cap to set and nothing that can bill you.
Publishernot claimed
COAll 1 server
compeller.ai1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine — this server runs on the publisher’s own infrastructure behind our gateway, and what you install is the connection to it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. Claude Code registers it in one command.
claude mcp add --transport http compeller-mcp https://compeller.ai/api/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free to install, and it runs from its publisher’s own package: no account, no key, no card.
What it writes
One config entry pointing at the gateway. The server itself runs on the publisher’s own infrastructure, so nothing from this listing executes on your machine.
What you approve
30 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Get Compeller platform capabilities, supported features, and API version.
Takes no parameters.
Example callreturns →
Get current Compeller subscription plans and pricing.
Takes no parameters.
Example callreturns →
List available visual styles for Compeller video generation.
Takes no parameters.
Example callreturns →
Get upload instructions for media files (audio, images, video). Returns the upload URL and required headers. Requires API token authentication.
Takes no parameters.
Example callreturns →
Search Deezer preview tracks by song, artist, or album. Use this when the user provides a song string but no MP3/WAV/FLAC file.
Takes no parameters.
Example callreturns →
Create a compel from a selected Deezer preview track. If the user provides an audio file instead, upload that file and use create_compel.
Takes no parameters.
Example callreturns →
Create a Compeller generation job from primary audio media and optional reference media. Returns compel id, status, and links to track progress and retrieve renderings.
Takes no parameters.
Example callreturns →
Get the current status, progress, and details of a Compeller generation job.
Takes no parameters.
Example callreturns →
Start rendering a READY compel with default configuration so an agent can continue to final MP4 without opening the browser UI.
Takes no parameters.
Example callreturns →
List all Compeller generation jobs for the authenticated account, newest first.
Takes no parameters.
Example callreturns →
Search Compeller generation jobs by title for the authenticated account.
Takes no parameters.
Example callreturns →
List all video renderings for a specific compel.
Takes no parameters.
Example callreturns →
Get details of a specific video rendering.
Takes no parameters.
Example callreturns →
Search and list uploaded media files for the authenticated account.
Takes no parameters.
Example callreturns →
Register an HTTPS endpoint to receive signed push notifications for compel lifecycle events (compel.ready when renderable, compel.completed, compel.failed). Returns webhook_id and the HMAC-SHA256 signing secret exactly once - store the secret immediately, it is never returned again. Deliveries are signed via X-Compeller-Signature: sha256=<hex> over the raw body. Delivery is at-least-once: a failed
Takes no parameters.
Example callreturns →
List all webhook endpoints registered for the authenticated account. Secrets are never returned by this tool.
Takes no parameters.
Example callreturns →
Delete a webhook endpoint by id. Removes the registration and stops future deliveries.
Takes no parameters.
Example callreturns →
Synchronously POST a synthetic webhook.test event to a registered endpoint. Uses the same HMAC-SHA256 signature as real deliveries, runs the standard URL safety check at delivery time, and returns {webhook_id, event_id, event_type, delivered, response_status, response_body_preview, latency_ms, error?}. Ignores the endpoint's events subscription - test delivery is always on-demand. Use this to veri
Takes no parameters.
Example callreturns →
Update one or more mutable fields on a registered webhook endpoint: url, events, active. At least one of these must be provided. Validation mirrors register_webhook (https-only, <= 2048 chars, URL safety blocklist). Returns the updated endpoint (secret is never returned by this tool - use rotate_webhook_secret for that).
Takes no parameters.
Example callreturns →
Mint a new HMAC-SHA256 signing secret for a registered webhook endpoint. The previous secret is invalidated immediately - integrators must update their receiver before the next compel terminal event fires. Returns the new secret exactly once; store it on receipt.
Takes no parameters.
Example callreturns →
Cancel an in-progress compel. Dequeues it if still queued, otherwise cancels any active external (AI provider) tasks and transitions it to CANCELLED. Idempotent - cancelling an already-CANCELLED compel succeeds. Use to stop a mis-prompted or runaway job before it consumes more render minutes.
Takes no parameters.
Example callreturns →
Get the authenticated account's render-minute balance and plan: minutes remaining (free + paid), monthly allowance, plan code, and whether the quota is exceeded. Call before starting an expensive render so an agent can make cost-aware decisions.
Takes no parameters.
Example callreturns →
List the COM-497 starter lighting effects available to launch as cues (e.g. "gobo-cycle", "x-move", "dimmer-pulse"). Each effect carries an id, the capabilities it needs, and a launch_contract template. Use the returned id as effect_id for launch_lighting_cue.
Takes no parameters.
Example callreturns →
Launch a starter lighting effect onto a stage as a live cue (e.g. "gobo-cycle on the stage's 7R beams at speed 0.5"). Pass effect_id (from list_lighting_effects) and optional variables to override effect defaults. Validation is loud: an unknown effect, a launch_contract whose bindings a stage cannot render, or a missing required field is rejected. Returns the active cue including its launch_id, re
Takes no parameters.
Example callreturns →
List the live (non-stopped) lighting cues REACT is executing, including each cue's launch_id, resolved variables, launch_contract, and feedback. Optionally scope to one stage.
Takes no parameters.
Example callreturns →
Fetch a single live lighting cue by its launch_id, including resolved variables, launch_contract, and REACT feedback.
Takes no parameters.
Example callreturns →
Stop a live cue by its launch_id. Idempotent - the cue is marked stop-requested so REACT drops it on its next refresh.
Takes no parameters.
Example callreturns →
Update variables on a live cue (e.g. change cycle speed or intensity mid-show). Only the variables you pass change; the rest keep their current values. Stopped cues are rejected.
Takes no parameters.
Example callreturns →
REACT/BAE acknowledgement for a launch_id. Idempotently records whether the executor accepted or rejected the cue and which executor observed it.
Takes no parameters.
Example callreturns →
REACT/BAE report-back for cue status, active variables, skipped bindings, capability misses, last_frame_at, and errors.
Takes no parameters.
Example callreturns →
Freeyour plan
$0 forever
- Every tool, no call limit
- No card, no account needed
- Source published under a licence you can read
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because nothing bills
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable. Compeller costs nothing to install and nothing to call, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: $8.42
$16.58 left
—Grade not published
No rule-by-rule report on file for this release
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
This listing is a hosted endpoint: the publisher runs it and we connect to it. The scanner reads packages and source, and neither exists to read here, so there is no grade — not a withheld one, an unmeasured one. What can be checked instead is on Installation: what it asks to reach and what it writes.
Release history
Pinned to 0.5.0 — the install command below asks for that release. A pin is part of an install, so it is kept for this visit and written down when you install.
0.5.0
undated
installedNo release note was published with this version.
—
no reviews yet
Reviews are earned
Only accounts with at least 50 real tool calls against this server in the last 90 days can post. Ratings are weighted by how much the reviewer actually uses it, and publishers can reply once per review.
Reviews are earned
Writing one takes an account with at least 50 real tool calls against Compeller in the last 90 days. That is the whole gate — there is no other way to post, which is why the counts beside each review are worth reading.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes an account with 50 real tool calls against it.