跳到正文
cccskills
免费在 GitHub 公开

bdb-grandma3-mcp

Utilizes the grandMA3 MCP server to patch fixtures, execute console commands, and trigger macros via OSC.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(1)

  • SKILL.md4.0 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

grandMA3 MCP — Integration and AI Agent Guide

This skill file instructs AI agents on how to control grandMA3 lighting consoles using the grandma3_mcp.py script. It details OSC routing, command execution, fixture patching, and troubleshooting steps.

1. Overview and Pipeline Value

The grandMA3 MCP Server enables AI models to programmatically configure and drive grandMA3 lighting control software. In the BDB OS workflow, this integration automates fixture patching, triggers lighting states, executes macros, and manages live cue sequencing during stage productions.

Architecture

  • FastMCP server: Implements standard Model Context Protocol.
  • OSC UDP Transport: Sends network packets via Open Sound Control (OSC) to 127.0.0.1 on port 8000.
  • Command Router: Maps JSON-RPC requests to OSC /cmd string paths, executing them natively inside grandMA3's Command Line.

2. System Instructions

Workflow Priorities

  1. Target Port Configuration: Ensure grandMA3's OSC settings are configured to listen on port 8000 and route /cmd addresses.
  2. Console State Syntax: Commands must match grandMA3 command-line syntax (e.g., Fixture 1 At 100, Go Macro 5).
  3. Double Patch Safeguard: Before calling patch_fixture, check if the targeted DMX address or fixture ID is already occupied by existing objects to avoid patching conflicts.

3. Available Tools and API Parameters

ToolParametersDescription
grandma3_pingNoneVerifies that the FastMCP server is active and ready to transmit commands.
execute_commandcommand: stringSends an arbitrary grandMA3 command to the console CLI via OSC (e.g., ClearAll, Go Page 2).
execute_macromacro_number: intExecutes a specific macro number using the Go Macro {num} syntax.
patch_fixturefixture_id: int, name: string, fixture_type: string, address: stringAutomatically runs the console CLI command to assign, name, set fixture type, and patch a fixture.

4. Code Recipes and Prompt Cookbook

Recipe 1: Standard Fixture Patching

Patch four Robe BMFL fixtures starting at DMX address 1.101:

// Tool Call: patch_fixture
{
  "fixture_id": 101,
  "name": "BMFL_StageLeft_01",
  "fixture_type": "Robe BMFL",
  "address": "1.101"
}

// Tool Call: patch_fixture
{
  "fixture_id": 102,
  "name": "BMFL_StageLeft_02",
  "fixture_type": "Robe BMFL",
  "address": "1.121"
}

Recipe 2: Triggering Show Cues

Run a sequence command to clear the programmer, select fixtures, set intensity, and store a cue:

// Tool Call: execute_command
{
  "command": "ClearAll"
}

// Tool Call: execute_command
{
  "command": "Fixture 101 Thru 105 At 80"
}

// Tool Call: execute_command
{
  "command": "Store Cue 1 \"Intro Light\""
}

5. Troubleshooting and Connection Details

Network Configuration

  • OSC Target IP: 127.0.0.1 (localhost)
  • OSC Target Port: 8000 (UDP)
  • OSC Input Address: /cmd

Console Settings Checklist

  1. Open grandMA3 -> Setup -> In & Out -> OSC.
  2. Create a new OSC connection entry.
  3. Configure the following parameters:
    • Mode: In (Listening)
    • Destination IP: 127.0.0.1
    • Port: 8000
    • Protocol: UDP
  4. Verify that the OSC connection status icon is green.

Common Errors and Fixes

  1. OSC message sent, but console is not responding
    • Cause: grandMA3's OSC listener is disabled or binding to a different port.
    • Fix: Verify that the OSC entry in grandMA3 matches port 8000 and has the /cmd prefix active.
  2. Patch Command Syntax Failure
    • Cause: The fixture_type string does not match any profile loaded in grandMA3's fixture library.
    • Fix: Pre-load the required fixture profiles inside grandMA3's Patch window before attempting to script patch mappings.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

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

中文简介正在准备中。当前显示原文说明。

hybridlabor-api/aos62026年10月16日 更新

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

中文简介正在准备中。当前显示原文说明。

hybridlabor-api/aos62026年10月16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.

中文简介正在准备中。当前显示原文说明。

hybridlabor-api/aos62026年10月16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.

中文简介正在准备中。当前显示原文说明。

hybridlabor-api/aos62026年10月16日 更新

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

中文简介正在准备中。当前显示原文说明。

hybridlabor-api/aos62026年10月16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.

中文简介正在准备中。当前显示原文说明。

hybridlabor-api/aos62026年10月16日 更新

查看 hybridlabor-api 的全部技能

报告此技能的问题