本文へ移動
cccskills
無料GitHub で公開

bdb-resolume-mcp

Utilizes the Resolume Arena MCP server to trigger clips, clear layers, adjust speeds, and query composition status via the Resolume REST API.

インストール方法を見る

含まれるファイル(1)

  • SKILL.md4.2 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Resolume Arena MCP — Integration and AI Agent Guide

This skill file instructs AI agents on how to interface with Resolume Arena media servers using the resolume_mcp.py script. It details REST endpoint interactions, layer clearing, composition queries, and troubleshooting steps.

1. Overview and Pipeline Value

The Resolume Arena MCP Server exposes Resolume Arena's local REST API (7.26+) to AI agents. In the BDB OS media playback pipeline, this enables dynamic clip triggering, layer mixing, composition speed overrides, and status feedback for real-time visual performances.

Architecture

  • FastMCP server: Bridges MCP client requests to standard HTTP REST calls.
  • HTTP REST Transport: Talks to Resolume's built-in web server at http://localhost:8080/api/v1.
  • JSON Payload Handler: Processes composition, layer, deck, and clip properties natively.

2. System Instructions

Workflow Priorities

  1. Enable Web Server: Ensure Resolume's Web Server is activated in the preferences menu.
  2. Layer/Clip Indices: Note that Resolume's API endpoints are 1-indexed for layers and clips (e.g., layer=1, clip=1).
  3. Query before Trigger: Query /composition to retrieve current deck layouts and identify which columns/rows contain clips before firing play triggers.

3. Available Tools and API Parameters

ToolParametersDescription
resolume_pingNoneVerifies if Resolume Arena is running by querying the /product endpoint.
trigger_cliplayer: int, clip: intFires a clip located on a target layer and clip index (1-indexed).
clear_layerlayer: intStops playback and clears visual output on a specific layer (1-indexed).
get_compositionNoneRetrieves a full JSON representation of the active composition, decks, layer routing, and parameter states.
set_composition_speedspeed: floatAdjusts composition playback speed multiplier.

4. Code Recipes and Prompt Cookbook

Recipe 1: Sequence Multi-Layer Visual Playback

Trigger clip 3 on layer 1 and clip 5 on layer 2 simultaneously:

// Step 1: Trigger layer 1 clip
// Tool Call: trigger_clip
{
  "layer": 1,
  "clip": 3
}

// Step 2: Trigger layer 2 clip
// Tool Call: trigger_clip
{
  "layer": 2,
  "clip": 5
}

Recipe 2: Transition / Fade-Out Setup

Clear the primary foreground visual layer and scale composition speed to normal:

// Step 1: Clear foreground layer (Layer 3)
// Tool Call: clear_layer
{
  "layer": 3
}

// Step 2: Normalize master composition speed
// Tool Call: set_composition_speed
{
  "speed": 1.0
}

5. Troubleshooting and Connection Details

Network Configuration

  • Resolume API Host: localhost
  • Resolume API Port: 8080 (Default REST Port)
  • API Base URL: http://localhost:8080/api/v1

Resolume Preference Verification

  1. Open Resolume Arena -> Preferences -> Web Server.
  2. Check the box "Enable Web Server".
  3. Verify the port is set to 8080. (If you use a password, note that the current MCP server relies on unauthenticated local network access; disable password auth or modify resolume_mcp.py to add auth headers).

Common Errors and Fixes

  1. Resolume API not reachable: HTTP Error 404
    • Cause: Resolume is running, but the Web Server is disabled.
    • Fix: Enable the Web Server in Resolume's preferences.
  2. Trigger Clip fails / success status returned but no output
    • Cause: The layer or clip indices do not contain active media assets, or the target deck is not selected.
    • Fix: Call get_composition to inspect deck configurations and verify that the target layer/clip slot contains media.
  3. Port Conflict on 8080
    • Cause: Another developer service (e.g. Apache, Tomcat, or Docker) is binding to port 8080.
    • Fix: Change the web server port inside Resolume's Preferences -> Web Server settings, and update RESOLUME_API_BASE inside resolume_mcp.py.

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

Use when manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.

日本語の概要は準備中です。原文の説明を表示しています。

hybridlabor-api/aos62026年10月12日 更新

Use when a hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).

日本語の概要は準備中です。原文の説明を表示しています。

hybridlabor-api/aos62026年10月12日 更新

Reference for how BDB structures autonomous software engineering work — the seven-node dispatcher graph (Architect, TechLead, UI/UX, Engineering, Media/EventTech, Reviewer, Shipping) that /startcycle-graph actually runs. Use when you need the high-level lifecycle framing without inventing your own process.

日本語の概要は準備中です。原文の説明を表示しています。

hybridlabor-api/aos62026年10月12日 更新

Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than necessary. This skill covers tool design from schema to error handling.

日本語の概要は準備中です。原文の説明を表示しています。

hybridlabor-api/aos62026年10月12日 更新

Harness patterns for coding agents — memory, permissions, context engineering, delegation, skills, hooks, bootstrap.

日本語の概要は準備中です。原文の説明を表示しています。

hybridlabor-api/aos62026年10月12日 更新

agenttrail: live map of a multi-agent build in the browser: which plan component is being worked on, by which agent or harness, what is done and what is stuck. Use when a multi-agent pipeline starts (/startcycle, /startcycle-graph, /teamwork-preview) or after a plan-canvas approve, when the user asks to see what the agents are doing ("live map", "build board", "who is running now"), or by yourself whenever a multi-agent run is under way — no user prompt needed.

日本語の概要は準備中です。原文の説明を表示しています。

hybridlabor-api/aos62026年10月12日 更新

hybridlabor-api のスキルをすべて見る

このスキルの問題を報告する