_ registry / mcp streamable-http · checked 3h ago

compeller-mcp

https://compeller.ai

Registry code: 41f90a8e6fab55de

api record

Create and track AI music videos and audio-reactive visuals from songs.

from a public catalogue that lists it, not from the operator

endpoint
https://compeller.ai/api/mcp
protocol
streamable-http ·2024-11-05
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
0 · newcomer
_ is it live, free and safe measured by this hub
Is compeller-mcp live?
Yes — it answered the hub's last check (checked 3h ago). It answered 98% of checks over the last 30 days.
Is compeller-mcp free to use?
Partly — some of its tools are open, others need a key or payment.
What tools does compeller-mcp have?
30 tools: upload_media, create_compel, stop_lighting_cue, create_compel_from_music, register_webhook, delete_webhook, update_webhook, rotate_webhook_secret, ….
Is compeller-mcp safe to connect?
The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
reachable
live
uptime, 30 days
97.9%

90 days 98.4%· all time 98.4%

latency
659ms

last good check

priced tools
0

of 30 tools

_ answered our checks, 90 days 621 checks · signed record
  • degraded → live
  • live → degraded· fetch failed
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
_ what it is for
topic
media generation video
used for
  • create an ai music video from a song
  • render an audio-reactive video
  • track video generation jobs
  • control live lighting cues
takes → gives
audio, images → video, data
tools
12 reads12 changes data1 sends messages
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 30 tools
4 open10 auth-required 16 never probed 14 of 30 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • list_lighting_effects reads open 26h ago

    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.

    mcp-tool

    {
  "type": "object",
  "required": [],
  "properties": {}
}
    arguments 5 lines
  • list_styles reads open 17h ago

    List available visual styles for Compeller video generation.

    mcp-tool

    {
  "type": "object",
  "required": [],
  "properties": {}
}
    arguments 5 lines
  • get_capabilities reads open 19h ago

    Get Compeller platform capabilities, supported features, and API version.

    mcp-tool

    {
  "type": "object",
  "required": [],
  "properties": {}
}
    arguments 5 lines
  • get_pricing reads open 19h ago

    Get current Compeller subscription plans and pricing.

    mcp-tool

    {
  "type": "object",
  "required": [],
  "properties": {}
}
    arguments 5 lines
  • list_compels reads auth-required 26h ago

    List all Compeller generation jobs for the authenticated account, newest first.

    mcp-tool

    {
  "type": "object",
  "required": [],
  "properties": {
    "limit": {
      "type": "integer",
      "description": "Max results to return (default 20, max 100)"
    },
    "offset": {
      "type": "integer",
      "description": "Pagination offset"
    }
  }
}
    arguments 14 lines
  • list_renderings reads auth-required 9h ago

    List all video renderings for a specific compel.

    mcp-tool

    {
  "type": "object",
  "required": [
    "compel_id"
  ],
  "properties": {
    "compel_id": {
      "type": "integer",
      "description": "The compel ID to list renderings for"
    }
  }
}
    arguments 12 lines
  • search_media reads auth-required 17h ago

    Search and list uploaded media files for the authenticated account.

    mcp-tool

    {
  "type": "object",
  "required": [],
  "properties": {
    "type": {
      "type": "string",
      "description": "Filter by media type: audio, image, video, or text"
    },
    "limit": {
      "type": "integer",
      "description": "Max results to return (default 20, max 100)"
    },
    "offset": {
      "type": "integer",
      "description": "Pagination offset"
    }
  }
}
    arguments 18 lines
  • list_webhooks auth-required 17h ago

    List all webhook endpoints registered for the authenticated account. Secrets are never returned by this tool.

    mcp-tool

    {
  "type": "object",
  "required": [],
  "properties": {}
}
    arguments 5 lines
  • get_compel reads auth-required 9h ago

    Get the current status, progress, and details of a Compeller generation job.

    mcp-tool

    {
  "type": "object",
  "required": [
    "compel_id"
  ],
  "properties": {
    "compel_id": {
      "type": "integer",
      "description": "The compel ID to check"
    }
  }
}
    arguments 12 lines
  • get_rendering reads auth-required 9h ago

    Get details of a specific video rendering.

    mcp-tool

    {
  "type": "object",
  "required": [
    "rendering_id"
  ],
  "properties": {
    "rendering_id": {
      "type": "integer",
      "description": "The rendering ID to retrieve"
    }
  }
}
    arguments 12 lines
  • get_lighting_cue reads auth-required 21h ago

    Fetch a single live lighting cue by its launch_id, including resolved variables, launch_contract, and REACT feedback.

    mcp-tool

    {
  "type": "object",
  "required": [
    "launch_id"
  ],
  "properties": {
    "launch_id": {
      "type": "string",
      "description": "The launch_id returned by launch_lighting_cue or list_lighting_cues"
    }
  }
}
    arguments 12 lines
  • list_lighting_cues reads auth-required 26h ago

    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.

    mcp-tool

    {
  "type": "object",
  "required": [],
  "properties": {
    "stage_id": {
      "type": "integer",
      "description": "Optional stage id to scope the listing to (must belong to the authenticated account)"
    }
  }
}
    arguments 10 lines
  • search_compels reads auth-required 21h ago

    Search Compeller generation jobs by title for the authenticated account.

    mcp-tool

    {
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "description": "Max results to return (default 20)"
    },
    "query": {
      "type": "string",
      "description": "Search query to match against compel titles"
    }
  }
}
    arguments 16 lines
  • search_music auth-required 21h ago

    Search Deezer preview tracks by song, artist, or album. Use this when the user provides a song string but no MP3/WAV/FLAC file.

    mcp-tool

    {
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "description": "Max results to return (default 10, max 20)"
    },
    "query": {
      "type": "string",
      "description": "Song, artist, or album search query"
    }
  }
}
    arguments 16 lines
  • upload_media unknown never probed

    Get upload instructions for media files (audio, images, video). Returns the upload URL and required headers. Requires API token authentication.

    mcp-tool

    {
  "type": "object",
  "required": [],
  "properties": {
    "name": {
      "type": "string",
      "description": "Filename for the upload"
    },
    "type": {
      "type": "string",
      "description": "Media type: audio, image, video, or text"
    },
    "mime_type": {
      "type": "string",
      "description": "MIME type of the file"
    }
  }
}
    arguments 18 lines
  • create_compel changes data unknown never probed

    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.

    mcp-tool

    {
  "type": "object",
  "required": [
    "title",
    "primary_media_id"
  ],
  "properties": {
    "style": {
      "enum": [
        "Cinematic Realistic",
        "Photo Realistic",
        "Cyberpunk",
        "Anime / Manga",
        "Film Noir",
        "Watercolor Painting",
        "Oil Painting",
        "3D Render / Pixar",
        "Retro 80s Synthwave",
        "Vintage Film Grain",
        "Comic Book / Pop Art",
        "Fantasy / Ethereal",
        "Horror / Dark Gothic",
        "Steampunk",
        "Neon Glow",
        "Minimalist / Abstract",
        "Surrealist",
        "Documentary",
        "Vaporwave",
        "Pencil Sketch",
        "Noir Detective",
        "Claymation / Stop Motion",
        "Studio Ghibli",
        "Baroque / Renaissance",
        "Lo-Fi / Grainy VHS",
        "Glitch Art / Digital",
        "Psychedelic"
      ],
      "type": "string",
      "description": "Visual style. Use one of the exact ids returned by list_styles (e.g. \"Cinematic Realistic\", \"Anime / Manga\"). Omit to use the account default."
    },
    "title": {
      "type": "string",
      "description": "Title for the compel"
    },
    "aspect_ratio": {
      "enum": [
        "16:9",
        "9:16",
        "1:1"
      ],
      "type": "string",
      "description": "Explicit aspect ratio override (takes precedence over target_platform)."
    },
    "artist_context": {
      "type": "string",
      "description": "Additional creative context about the artist or song"
    },
    "target_platform": {
      "enum": [
        "tiktok",
        "reels",
        "shorts",
        "instagram",
        "square",
        "youtube",
        "web"
      ],
      "type": "string",
      "description": "Target platform; sets the aspect ratio when aspect_ratio is omitted."
    },
    "primary_media_id": {
      "type": "integer",
      "description": "ID of the uploaded audio media to use as the primary track"
    }
  }
}
    arguments 76 lines
  • stop_lighting_cue changes data unknown never probed

    Stop a live cue by its launch_id. Idempotent - the cue is marked stop-requested so REACT drops it on its next refresh.

    mcp-tool

    {
  "type": "object",
  "required": [
    "launch_id"
  ],
  "properties": {
    "launch_id": {
      "type": "string",
      "description": "The launch_id of the cue to stop"
    }
  }
}
    arguments 12 lines
  • create_compel_from_music changes data unknown never probed

    Create a compel from a selected Deezer preview track. If the user provides an audio file instead, upload that file and use create_compel.

    mcp-tool

    {
  "type": "object",
  "required": [
    "track_id"
  ],
  "properties": {
    "style": {
      "enum": [
        "Cinematic Realistic",
        "Photo Realistic",
        "Cyberpunk",
        "Anime / Manga",
        "Film Noir",
        "Watercolor Painting",
        "Oil Painting",
        "3D Render / Pixar",
        "Retro 80s Synthwave",
        "Vintage Film Grain",
        "Comic Book / Pop Art",
        "Fantasy / Ethereal",
        "Horror / Dark Gothic",
        "Steampunk",
        "Neon Glow",
        "Minimalist / Abstract",
        "Surrealist",
        "Documentary",
        "Vaporwave",
        "Pencil Sketch",
        "Noir Detective",
        "Claymation / Stop Motion",
        "Studio Ghibli",
        "Baroque / Renaissance",
        "Lo-Fi / Grainy VHS",
        "Glitch Art / Digital",
        "Psychedelic"
      ],
      "type": "string",
      "description": "Visual style. Use one of the exact ids returned by list_styles (e.g. \"Cinematic Realistic\", \"Anime / Manga\"). Omit to use the account default."
    },
    "title": {
      "type": "string",
      "description": "Optional compel title override"
    },
    "track_id": {
      "type": "integer",
      "description": "Deezer track id returned by search_music"
    },
    "aspect_ratio": {
      "enum": [
        "16:9",
        "9:16",
        "1:1"
      ],
      "type": "string",
      "description": "Explicit aspect ratio override (takes precedence over target_platform)."
    },
    "artist_context": {
      "type": "string",
      "description": "Additional creative context"
    },
    "target_platform": {
      "enum": [
        "tiktok",
        "reels",
        "shorts",
        "instagram",
        "square",
        "youtube",
        "web"
      ],
      "type": "string",
      "description": "Target platform; sets the aspect ratio when aspect_ratio is omitted."
    }
  }
}
    arguments 75 lines
  • register_webhook changes data unknown never probed

    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 delivery is retried with backoff (up to 6 attempts) and every retry carries the same X-Compeller-Event-Id, so dedupe on it.

    mcp-tool

    {
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "description": "HTTPS URL to deliver events to (max 2048 chars)"
    },
    "events": {
      "type": "array",
      "items": {
        "enum": [
          "*",
          "compel.ready",
          "compel.completed",
          "compel.failed"
        ],
        "type": "string"
      },
      "description": "Event types to subscribe to. Omit or pass [\"*\"] for all. Known types: compel.ready (renderable - call start_render), compel.completed, compel.failed."
    }
  }
}
    arguments 25 lines
  • delete_webhook changes data unknown never probed

    Delete a webhook endpoint by id. Removes the registration and stops future deliveries.

    mcp-tool

    {
  "type": "object",
  "required": [
    "webhook_id"
  ],
  "properties": {
    "webhook_id": {
      "type": "integer",
      "description": "The webhook id returned by register_webhook or list_webhooks"
    }
  }
}
    arguments 12 lines
  • update_webhook changes data unknown never probed

    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).

    mcp-tool

    {
  "type": "object",
  "required": [
    "webhook_id"
  ],
  "properties": {
    "url": {
      "type": "string",
      "description": "New HTTPS URL (max 2048 chars)"
    },
    "active": {
      "type": "boolean",
      "description": "Toggle delivery on/off without losing the registration"
    },
    "events": {
      "type": "array",
      "items": {
        "enum": [
          "*",
          "compel.ready",
          "compel.completed",
          "compel.failed"
        ],
        "type": "string"
      },
      "description": "Replacement event types. Omit to leave unchanged. [\"*\"] or an empty filtered list resets to wildcard."
    },
    "webhook_id": {
      "type": "integer",
      "description": "The webhook id to update"
    }
  }
}
    arguments 33 lines
  • rotate_webhook_secret changes data unknown never probed

    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.

    mcp-tool

    {
  "type": "object",
  "required": [
    "webhook_id"
  ],
  "properties": {
    "webhook_id": {
      "type": "integer",
      "description": "The webhook id to rotate the secret on"
    }
  }
}
    arguments 12 lines
  • cancel_compel changes data unknown never probed

    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.

    mcp-tool

    {
  "type": "object",
  "required": [
    "compel_id"
  ],
  "properties": {
    "compel_id": {
      "type": "integer",
      "description": "The compel ID to cancel"
    }
  }
}
    arguments 12 lines
  • get_account_credits unknown never probed

    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.

    mcp-tool

    {
  "type": "object",
  "required": [],
  "properties": {}
}
    arguments 5 lines
  • launch_lighting_cue unknown never probed

    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, resolved variables, and launch_contract for REACT. REACT executes the cue per-frame; the live strobe slider stays authoritative and is never raised by a launch.

    mcp-tool

    {
  "type": "object",
  "required": [],
  "properties": {
    "stage_id": {
      "type": "integer",
      "description": "The stage to launch onto (must belong to the authenticated account)"
    },
    "effect_id": {
      "type": "string",
      "description": "COM-497 starter effect id from list_lighting_effects, e.g. \"gobo-cycle\""
    },
    "variables": {
      "type": "object",
      "description": "Optional variable overrides (name -> value), e.g. {\"speed\": 0.5}. Defaults come from the effect."
    },
    "launch_contract": {
      "type": "object",
      "description": "Advanced: an explicit launch_contract to launch instead of resolving one from effect_id."
    }
  }
}
    arguments 22 lines
  • ack_lighting_cue changes data unknown never probed

    REACT/BAE acknowledgement for a launch_id. Idempotently records whether the executor accepted or rejected the cue and which executor observed it.

    mcp-tool

    {
  "type": "object",
  "required": [
    "launch_id",
    "accepted"
  ],
  "properties": {
    "accepted": {
      "type": "boolean",
      "description": "true when REACT/BAE accepted the cue for execution"
    },
    "launch_id": {
      "type": "string",
      "description": "The launch_id to acknowledge"
    },
    "executor_id": {
      "type": "string",
      "description": "Stable REACT/BAE executor instance id"
    },
    "observed_at": {
      "type": "string",
      "description": "Executor observation timestamp"
    },
    "rejected_reason": {
      "type": "string",
      "description": "Required by convention when accepted=false"
    }
  }
}
    arguments 29 lines
  • report_lighting_cue changes data unknown never probed

    REACT/BAE report-back for cue status, active variables, skipped bindings, capability misses, last_frame_at, and errors.

    mcp-tool

    {
  "type": "object",
  "required": [
    "launch_id"
  ],
  "properties": {
    "error": {
      "type": "string"
    },
    "status": {
      "type": "string",
      "description": "ACTIVE, STOP_REQUESTED, or STOPPED"
    },
    "launch_id": {
      "type": "string",
      "description": "The launch_id to report"
    },
    "executor_id": {
      "type": "string"
    },
    "last_frame_at": {
      "type": "string"
    },
    "active_variables": {
      "type": "object",
      "description": "Variables actually being sampled by REACT/BAE"
    },
    "skipped_bindings": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "capability_misses": {
      "type": "array",
      "items": {
        "type": "object"
      }
    }
  }
}
    arguments 41 lines
  • start_render changes data unknown never probed

    Start rendering a READY compel with default configuration so an agent can continue to final MP4 without opening the browser UI.

    mcp-tool

    {
  "type": "object",
  "required": [
    "compel_id"
  ],
  "properties": {
    "compel_id": {
      "type": "integer",
      "description": "The READY compel ID to render"
    }
  }
}
    arguments 12 lines
  • test_webhook_delivery sends messages unknown never probed

    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 verify your integration before relying on compel.completed / compel.failed events.

    mcp-tool

    {
  "type": "object",
  "required": [
    "webhook_id"
  ],
  "properties": {
    "webhook_id": {
      "type": "integer",
      "description": "The webhook id to test. Must belong to the authenticated account."
    }
  }
}
    arguments 12 lines
  • set_lighting_cue_variables changes data unknown never probed

    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.

    mcp-tool

    {
  "type": "object",
  "required": [
    "launch_id",
    "variables"
  ],
  "properties": {
    "launch_id": {
      "type": "string",
      "description": "The launch_id of the cue to update"
    },
    "variables": {
      "type": "object",
      "description": "Variables to set (name -> value), e.g. {\"speed\": 0.75}"
    }
  }
}
    arguments 17 lines
_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id 41f90a8e6fab55de.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/41f90a8e6fab55de/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/41f90a8e6fab55de/badge.svg)](https://brick.blue/agent/41f90a8e6fab55de?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we know
card completeness
100%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.