Converts between Strudel mini-notation and MIDI note events, enabling pattern generation and conversion for MIDI-based workflows.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@mcp-strudel convert 'c5 [e5 g5]*2' to MIDI notes"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP server that exposes the Strudel
mini-notation engine (shared with the m4l-strudel device) as tools Claude can
call. Combine it with ableton-mcp so you can say things like "lay down a
bd(3,8) kick and a c5 [e5 g5]*2 bassline" and have Claude convert the
patterns and write them into Ableton clips.
Tool | Input | Output |
|
| JSON note events ( |
|
| mini-notation text |
|
| parse errors or "OK" |
conv = strudel (c5=60, default) or scientific (c4=60).
Related MCP server: Filopastry
pnpm install
pnpm test # engine contract tests (vitest)
pnpm start # launches the stdio MCP server (tsx src/server.ts)Add to the MCP config you pass to the Claude Code CLI (e.g. the mcp-config.json
that the m4l-claude device generates), alongside AbletonMCP:
{
"mcpServers": {
"AbletonMCP": { "command": "uvx", "args": ["ableton-mcp"] },
"strudel": {
"command": "npx",
"args": ["-y", "tsx", "C:/Users/jaime/src/livecam-m4l/tmp/mcp-strudel/src/server.ts"]
}
}
}With both servers available, Claude can call strudel_to_midi to turn a pattern
into notes, then use AbletonMCP's clip/note tools to create the clip - the
m4l-strudel → mcp-strudel → ableton-mcp path, orchestrated in natural language.
src/lib/mini/ is the same parser/scheduler/unparser as the m4l-strudel
device (recursive-descent parser, Bjorklund euclidean rhythms, cycle scheduler,
grid quantizer). Keeping one engine means the device and the server always agree
on how a pattern sounds.
Convert MIDI note events (pitch + start/duration in beats) into Strudel mini-notation text, quantized to a step grid. Simultaneous notes become [a,b] chords; gaps become ~ rests; held notes use @ elongation.
| Name | Required | Description | Default |
|---|---|---|---|
| bars | No | ||
| conv | No | Octave convention: strudel (c5=60) or scientific (c4=60) | strudel |
| grid | No | steps per bar | |
| notes | Yes | note events | |
| octaveOffset | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of disclosing behavior. It explains key conversion details: quantization to a step grid, chords as [a,b], rests as ~, and elongation as @. This is informative but could be more explicit about edge cases like overlapping notes or input validation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the core conversion action, and every sentence adds essential detail. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (conversion with quantization, chords, rests, elongation) and no output schema, the description covers the output format and transformation rules well. It is complete for typical use, though missing info on error handling or parameter effects.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 60% (notes, grid, conv have descriptions; bars and octaveOffset do not). The description does not mention any parameters, but it clarifies the input format (pitch, start, duration in beats) which adds value beyond the schema for the notes array. However, it does not compensate for missing parameter descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool converts MIDI note events into Strudel mini-notation text, including quantization and handling of simultaneous notes, gaps, and held notes. This distinguishes it from sibling tools like strudel_to_midi and strudel_validate.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The usage context is implied by the tool name and description (convert MIDI to Strudel), but there is no explicit guidance on when to use this tool versus its siblings or when not to use it. No alternatives or exclusions are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Convert a Strudel mini-notation pattern into MIDI note events. Supports sequences, [subdivisions], ~ rests, , *repeat, @elongation, [a,b] chords, {poly}%n, and euclid(p,s,rot). Returns note events with pitch and start/duration in beats, plus total length in beats.
| Name | Required | Description | Default |
|---|---|---|---|
| bars | No | bars per cycle | |
| conv | No | Octave convention: strudel (c5=60) or scientific (c4=60) | strudel |
| cycles | No | ||
| pattern | Yes | e.g. "c5 [e5 g5]*2 ~ <a5 b5>" | |
| velocity | No | ||
| octaveOffset | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It lists supported syntax features and the output format, but lacks details on error handling, permissions, or limitations, which is only adequate.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise (three sentences) with the purpose front-loaded. Each sentence adds value: purpose, supported features, and output summary, with no redundant information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity and absence of output schema or annotations, the description provides a reasonable overview of output (note events with pitch, start/duration, and total length), but lacks explicit structure details, making it minimally complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 50% (3 of 6 parameters have descriptions). The description only adds value for the pattern parameter by listing operators, failing to explain bars, cycles, velocity, octaveOffset, or conv beyond basic schema, thus not compensating for low coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's action 'Convert a Strudel mini-notation pattern into MIDI note events' using a specific verb and resource, and this distinguishes it from sibling tools like midi_to_strudel (reverse) and strudel_validate (validation).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for converting Strudel patterns to MIDI, but does not provide explicit guidance on when to use this tool versus alternatives, nor does it mention prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Parse a Strudel mini-notation pattern and report any syntax errors.
| Name | Required | Description | Default |
|---|---|---|---|
| pattern | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. The description implies a read-only validation operation but does not disclose any behavioral traits beyond parsing and error reporting. No mention of side effects, auth requirements, or rate limits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
One concise sentence, front-loaded with purpose, no wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with one parameter and no output schema, the description is nearly complete. It could mention the return format (error report) but is still adequate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0% (no description for 'pattern' in schema). The description adds that the pattern is a 'Strudel mini-notation pattern', which clarifies the parameter's purpose but lacks format examples or constraints.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'parse and report' and the resource 'Strudel mini-notation pattern', distinguishing it clearly from sibling tools which are conversions (midi_to_strudel, strudel_to_midi).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives. Does not mention any prerequisites, exclusions, or typical use cases (e.g., checking syntax before conversion).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.1.1midi_to_strudelstrudel_to_midistrudel_validateEach tool has a distinct and non-overlapping purpose: MIDI-to-Strudel conversion, Strudel-to-MIDI conversion, and Strudel validation. No ambiguity.
All tools follow a consistent verb_noun pattern in snake_case: midi_to_strudel, strudel_to_midi, strudel_validate. Perfectly predictable naming.
Three tools is ideal for a focused conversion/validation server. No bloat or deficiency given the domain.
Covers the essential bidirectional conversion and validation. A minor gap is the lack of a tool for partial conversions or advanced transformations, but the core workflow is complete.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Generate AI music via the Lacuna Music API from MCP clients like Claude Desktop & Code.
Create, co-edit, analyze, publish, and export collaborative step-sequencer sessions through MCP.
Music studio: ABC notation composition and Strudel live coding with ext-apps UI.
Convert projects between Logic, Ableton, FL Studio and REAPER; generate, separate, transcribe
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/alienmind/mcp-strudel'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
