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., "@bespoke-mcp Build a pad synth patch and play a Cmaj7 chord"
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 lets an LLM drive a live Bespoke Synth window: build and rewire the module graph, set and modulate controls (including the right-click LFO surface), sequence notes, control playback, and — crucially — hear the result via numeric audio analysis, rendered spectrogram/waveform images, and a symbolic note-event log fed back to the model.
Claude ──stdio──▶ Python MCP server ──TCP NDJSON JSON-RPC──▶ BespokeSynth.exe (fork)
(mcp/src/bespoke_mcp) └─ McpBridge (C++ singleton)
numpy DSP · matplotlib plots drained on the main thread
ASCII piano roll · module catalog in ModularSynth::Poll()C++ bridge (BespokeSynth/Source/Mcp*.{h,cpp}) — an always-on singleton registered via
ModularSynth::AddExtraPoller. Socket threads parse newline-delimited JSON-RPC 2.0 on
127.0.0.1:5309 (pref mcp_port, env BESPOKE_MCP_PORT, CLI -o mcp_port N) and queue requests;
all graph mutation executes on the message thread with the same locks the UI uses. Structured errors
carry did_you_mean / valid_targets payloads so a model self-corrects on the next turn.
Python MCP server (mcp/src/bespoke_mcp) — exposes the bridge as MCP tools, does all audio
analysis in numpy (dBFS/LUFS, spectral centroid/flatness/rolloff, band energies, pitch, onsets,
stereo), renders PNG plots for vision, and formats note/pulse events as an ASCII piano roll.
BespokeSynth/ — git submodule; currently edited in place, to be repointed at a fork.
Upstream file touches are kept minimal and listed in UPSTREAM.md.
Related MCP server: Ableton Live MCP
# C++ (from BespokeSynth/): configure once, then
cmake --build ignore/build --config Release --target BespokeSynth
# Python: uv manages everything from the repo root
uv sync
uv run pytest
uv run ruff check .
# Run the MCP server (spawns/attaches to BespokeSynth via <data>/mcp/instance.json)
uv run bespoke-mcpRegister with Claude Code: claude mcp add bespoke -- uv --directory <this dir> run bespoke-mcp
Path | Contents |
| the synth (submodule) + the C++ bridge in |
| Python MCP server: tools, bridge client, launcher, DSP/rendering |
| fast unit tests (no synth needed) |
| tests that launch the real binary |
| Claude skills teaching patching, modulation, sequencing, analysis |
| deferred roadmap (offline render device, fuzz matrix, skills, …) |
This server cannot be installed
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Create and track AI music videos and audio-reactive visuals from songs.
Generate AI music via the Lacuna Music API from MCP clients like Claude Desktop & Code.
MCP server for Producer/Riffusion AI music generation
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Crack-Pantelimon/bespoke-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server