MCP.Market

u-he Preset Randomizer MCP server

by Fannon·io.github.Fannon/u-he-preset-randomizer·v1.2.0·32 stars

Generate, randomize, explain, and manage u-he synthesizer presets via the Model Context Protocol.

A92/100grade A
What users say
No reviews yet
Be the first
Safety scan
A92/100

full report

Adoption
Growing

32 stars232 downloads/wk

Reviews

Write one

Nobody has reviewed u-he Preset Randomizer yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

u-he Preset Randomizer tools (14, 1 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • explain_preset

    Get detailed information about a specific preset including all metadata, parameters, and values. Use this to understand what makes a preset unique. Requires a synth to be selected first.

  • filter_presets

    Filter presets by specific criteria including category (hierarchical), author, favorites file, or glob pattern. Can combine multiple filters. Requires a synth to be selected first.

  • generate_random_presets

    Generate fully random presets based on parameter statistics from the loaded preset library. Optionally filter the statistical basis by author, category, pattern, or favorites to generate more focused/coherent sounds (e.g., random bass presets). Generated presets are automatically added to the library for immediate use with search_presets and explain_preset. Defaults to … presets if amount is omitt

  • get_authors

    Get a list of all unique preset authors/creators in the currently loaded presets. Useful for filtering by favorite sound designers. Requires a synth to be selected first.

  • get_categories

    Get a list of all unique preset categories available in the currently loaded presets. Useful for discovering what types of sounds are available. Requires a synth to be selected first.

  • get_current_synth

    Get information about the currently selected synth, including its name and the number of loaded presets.

  • get_favorites_files

    Get a list of all .uhe-fav favorites files found for the current synth. These can be used for filtering presets. Requires a synth to be selected first.

  • get_synth_context

    Get detailed technical documentation about how the currently selected u-he synth works, including its preset format, parameters, modules, and architecture. This is extremely useful for understanding synth-specific settings before analyzing or creating presets. Requires a synth to be selected first.

  • list_presets

    List all loaded presets for the current synth with their names, categories, and authors. Use this for browsing available presets. Requires a synth to be selected first.

  • list_synths

    List all available u-he synths detected on this system. Call this to see which synths are installed and can be selected.

  • merge_presets

    Merge multiple presets to create hybrid sounds using weighted random ratios. Select presets via preset_names (supports wildcards: "*" for random from all, "?" for random from list), or filter by author/category/pattern. Generated merges are automatically added to the library. Defaults to … merged presets with 0% additional randomness.

  • randomize_presetswrite action

    Create variations of existing presets by randomly modifying their parameters (0-100% randomness). Select source presets by preset_names, pattern, author, or category. IMPORTANT: 'amount' is per source preset (1 preset + amount=4 → 4 files; 10 presets + amount=2 → 20 files). Generated variations are automatically added to the library. Defaults to … variations per preset and 50% randomness.

  • search_presets

    Search presets by name, category, or author using fuzzy matching. Returns matching presets with relevance scoring. Requires a synth to be selected first.

  • select_synth

    Select a synth and load its preset library. MUST be called before other preset tools. Optional pattern filters which presets are loaded (for faster loading with large libraries). Trade-off: filtered loading is faster but limits subsequent operations to only those presets until reloaded. Omit pattern for full library access (recommended unless library is very large).

Public scan report

scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it

no findings
  • Code scan41 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 12 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 92/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How u-he Preset Randomizer compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
92/100
higher than 90% of 4,460 AI and agents servers
Tools
14
the typical AI and agents server has 6
Tools that change things
7%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
32
more than 91% of 2,711 AI and agents servers
Downloads a week
232
more than 76% of 1,538 AI and agents servers with a package

What its tools let an agent do: 11 read · 1 create · 2 change

Install u-he Preset Randomizer in Claude Code, Cursor or VS Code

Runs npx -y u-he-preset-randomizer on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add u-he-preset-randomizer -- npx -y u-he-preset-randomizer
Add to Cursor

What the publisher says

From the u-he Preset Randomizer repository's README, as published. We do not edit it. Read it on GitHub

u-he-preset-randomizer

Generate u-he synth presets through randomization and merging of your existing presets (genetics like).

This tool can generate random presets in three different modes:

  • Generate fully random presets based on real values and value distributions in your preset library
  • Randomize existing presets, with a customizable amount of randomness
  • Merge multiple presets together, with randomness introduced by different ratios between them.

The randomization / merging approach is very generic as it analyzes your actual preset library and bases the random values on the resulting statistical distributions.

There are optional flags / modes that that affect the randomization:

  • Narrow down the analyzed presets that are the basis for random generation.
  • E.g. by only using a sub-folder, a certain tag category, author or a favorite file export.
  • This will influence / limit the range of values in the generated presets.
  • Use stable mode for more reliable, but slightly less random results
  • Use binary mode, see --binary CLI arguments documentation.

It should work for all u-he synths on all platforms. Some synths may work better, due to their simpler architecture (e.g. u-he Diva, Repro). More modular synths like Bazille or Zebra also work, but you'll get more "varied" results or broken presets.

How to use

This is a CLI application that you need to run in your terminal / command line.

First you need to install the Node.js runtime. Then you can open your Terminal / Console / Command Prompt and start it by entering a command, optionally with some arguments. They start with npx u-he-preset-randomizer@latest, which will download and run the latest version of this tool:

npx u-he-preset-randomizer@latest

This will start the tool in interactive mode. It will guide you though the necessary choices. Alternatively, you can pass some arguments if you already know the choices (non interactive).

The generated patches will be put into your selected synth preset directory, under a /RANDOM folder in your user presets.

If you want to download the tool for offline use and manual updates:

# install it as a global CLI tool
npm i -g u-he-preset-randomizer

# Now you can run it without npx:
u-he-preset-randomizer

MCP Server Interface

In addition to the CLI, this tool provides a Model Context Protocol (MCP) server that allows AI assistants like Claude to interact with your u-he presets through natural conversation.

Features:

  • 🔍 Search and browse your preset libraries conversationally
  • 📝 Get detailed explanations of what makes presets unique
  • 🎲 Generate random presets with natural language instructions
  • 🔄 Create variations and merge presets through AI-assisted workflows
  • 💾 Stateful sessions - select a synth once, then explore freely

Quick Setup for Claude Desktop:

Add this to your Claude Desktop config (~/Library/Application Support/Claude/claudedesktopconfig.json on macOS):

{
  "mcpServers": {
    "u-he-preset-randomizer": {
      "command": "u-he-mcp-server"
    }
  }
}

Then you can ask Claude things like:

  • "What synths do I have installed?"
  • "Show me bass presets from Diva"
  • "Create 5 variations of the '303 Bass' preset with 30% randomness"
  • "Merge my favorite pad presets to create hybrid sounds"

📚 Read the full MCP Server documentation →

CLI Usage Examples

Generate Fully Randomized Presets

This command will run the randomizer to generate 3 fully randomized Diva presets. Random values will be based on real values (and their distribution) of your actual presets.

npx u-he-preset-randomizer@latest --synth Diva --amount 3

Randomize a particular Preset

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

u-he Preset Randomizer: common questions

Is u-he Preset Randomizer MCP server safe?
Yes, by our scan: it is graded A (92/100). Read the u-he Preset Randomizer safety report
How do I install u-he Preset Randomizer?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does u-he Preset Randomizer need an API key?
No secret keys are declared. It reads 2 settings from the environment.
Is u-he Preset Randomizer maintained?
The last commit was 49 days ago (2026-09-16). The latest release is v1.2.0.
What can I use instead of u-he Preset Randomizer?
Servers from other publishers that do the same job: PaperBanana MCP server, Agent-Native Slides MCP server and Image MCP server.
How does u-he Preset Randomizer compare with other AI and agents MCP servers?
safety score 92/100 (higher than 90% of 4,460 AI and agents servers); tools 14 (the typical AI and agents server has 6); tools that change things 7% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to u-he Preset Randomizer

Same job from other publishers: the closest match first, then the best rated.

  • PaperBanana
    Generate academic diagrams and statistical plots from text using multi-agent AI.
    A
  • Agent-Native Slides
    Agent-Native Google Slides - generate and edit React presentations
    A
  • Image
    AI image generation and editing with prompt optimization and quality presets
    B