helix-stadium-mcp
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
helix-stadium-mcp
Helix Stadium MCP connects AI assistants to Line 6 Helix Stadium presets. It reads and explains existing presets, edits parameters, blocks and snapshots, and builds new presets from the models in your Helix Stadium installation. It validates every change and backs up the original file before writing.
Point your AI assistant at a .hsp preset and ask what it does, how two snapshots differ, or to
change it — brighten the lead, add a reverb, set up Rhythm / Lead / Clean snapshots. You get
plain-English answers with real values (dB, Hz, ms) instead of raw parameter numbers, and any edits
are written back safely. It's an MCP server, so it runs in any MCP
client (Claude Desktop, Cursor, VS Code, and others).
Example
Ask "what does this preset do?" and point it at a .hsp. You get the whole signal chain back,
per path:
# Dual Rectifier Lead
tempo 120.0 BPM | active snapshot #0
Snapshots: 1. Rhythm (blue), 2. Lead (red)
## Path 1
[amp] Cali Rectifire — on [per-snapshot] · Drive 7.5 | Bass 5.0 | Master 4.0
[cab] 4x12 Cali V30 — on · HighCut 9.0 kHz | Distance 2.0 "
[fx] Minotaur — on [per-snapshot] · Gain 45 % | Level 60 %
[fx] Simple Delay — on [per-snapshot] · Mix 18 % | Time 400 ms | Feedback 25 %Friendly model names, on/off state (and which snapshots switch it), and every parameter in the units you'd read off the hardware.
Because it understands the whole patch, it can also change it for you. Ask for more gain on the lead or a touch more reverb, and it edits the exact block and parameter — then writes the result back through a safety check (validate → byte-exact round-trip → atomic write with a backup). It can also build a preset from scratch, set up snapshots, and assemble a setlist.
Related MCP server: Claud-Ear
Try asking
"What does this preset do?"
"What's different between my Rhythm and Lead snapshots?"
"Add a Plate reverb after the amp and set the mix to 20%."
"Give the Lead snapshot more gain without making it louder."
"Set up Rhythm, Lead, and Clean snapshots on this preset."
"Build me a clean preset with a US Deluxe amp, a 1x12 cab, and a spring reverb."
"Find me a plexi-style amp." / "List every delay model."
"Turn these presets into a setlist for Friday's gig."
What it does
Reads
.hsppresets losslessly (byte-exact round-trip).Explains a preset in plain English — the full signal chain of each path with friendly model names, on/off state, per-snapshot & footswitch tags, and parameters in real units (dB, Hz, ms, %).
Diffs snapshots — exactly what changes between two snapshots (e.g. Rhythm vs Lead), in real units.
Edits — change parameters in real units, toggle or add / remove / reorder blocks, rename, and set up snapshots. Any model in your catalog can be added at its factory defaults.
Creates — start a new preset from scratch and build it up block by block.
Assembles setlists — order a batch of presets into a setlist with a pre-gig checklist.
Browses the model catalog (list / describe / search models).
Validates a preset's structure (and, with the catalog, its model ids and controller sources).
Every change is written back through a safety gate — validate → round-trip → atomic write with a
.bak backup — and HELIX_MCP_READONLY keeps the server read-only whenever you want it.
Install & configure
uvx twelvetake-helix-stadium-mcp@latest serve # or: pipx run twelvetake-helix-stadium-mcp serveAdd it to your MCP client's config. Most use an mcpServers block:
{
"mcpServers": {
"helix-stadium": {
"command": "uvx",
"args": ["twelvetake-helix-stadium-mcp@latest", "serve"]
}
}
}If the catalog isn't auto-detected, set HELIX_STADIUM_RES to the folder containing
P35ModelCatalog.json: your install's res folder on Windows, or
Helix Stadium.app/Contents/Resources on macOS. Check detection with helix-stadium-mcp doctor.
To keep the server read-only — for instance when you point it at presets you don't fully trust — set
HELIX_MCP_READONLY=1, and the write tools are left out at startup.
Tools
Read
Tool | What you'd ask it |
| Load a |
| The full signal chain in plain English, with real units |
| What changes between two snapshots |
| Browse the model catalog |
| Check a preset's structure |
| Find the Helix Stadium catalog this reads from |
Edit & build
Tool | What you'd ask it |
| Set a parameter, by current value or for a specific snapshot |
| Add, remove, or reorder a block |
| Turn a block on/off — globally or per snapshot |
| Name the scenes and pick the active one |
| Rename the preset or a snapshot |
| Start a new blank preset to build up |
| Assemble ordered presets into a setlist + checklist |
Every write tool goes through the safety gate above; set HELIX_MCP_READONLY to leave them out.
Roadmap
Pre-1.0, following semantic versioning — the tool surface can still change between minor versions.
v0.1: Read, explain and compare presets; browse the model catalog; validate presets.
v0.2 (current): Edit parameters; add, remove, reorder and toggle blocks; rename presets and snapshots; configure snapshots; build presets from scratch; assemble setlists. All writes pass through a validation and backup gate, and
HELIX_MCP_READONLYdisables writing entirely.v0.3: Footswitch assignment, block targeting by name, per-block and per-path DSP reporting, and Helix Stadium Native support, including preset conversion between the Stadium and Native and Stadium compatibility checks.
v0.4: Helix Stadium setlist files (
.hss).v0.5: Preset generation from a text description.
v1.0: A stable tool interface.
Requirements
Helix Stadium installed, on Windows or macOS. The server reads the model catalog and per-model definitions from your own install at runtime.
Python 3.10+.
Trademarks
Not affiliated with or endorsed by Line 6 or Yamaha Guitar Group.
All trademarks are the property of their respective owners. "Line 6," "Helix," and "Helix Stadium," along with any amp, cab, or effect model names and other brand or product names that appear (for example through the model catalog or a preset), are used here only to identify compatible gear. This project claims no ownership of any trademark it references.
License
MIT © TwelveTake Studios LLC. See LICENSE.
This server cannot be deployed
Maintenance
Related MCP Connectors
MCP server for Producer/Riffusion AI music generation
An MCP server that integrates with Discord to provide AI-powered features.
MCP server for AI dialogue using various LLM models via AceDataCloud
Driflyte MCP server which lets AI assistants query topic-specific knowledge from web and GitHub.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceAn MCP server that lets AI assistants safely inspect and operate on Kubernetes clusters through natural conversation.MIT
- AlicenseNot gradedqualityDmaintenanceAn MCP server that gives AI agents the ability to listen to and understand music/audio files, enabling semantic analysis, stem separation, lyrics transcription, and signal processing via tool calls.1MIT
- AlicenseNot gradedqualityDmaintenanceA comprehensive MCP server that enables AI assistants to control music playback, manage users and access, configure providers, and administer a Music Assistant setup through natural language commands.MIT
- AlicenseAqualityBmaintenanceAn MCP server that lets users generate, edit, and save Xfer Serum 2 presets from plain-English descriptions directly through MCP clients like Claude Code or Claude Desktop, without any separate API keys or LLM calls.2420MIT