LogicProMCP
A local MCP server that bridges Logic Pro MIDI data via an AUv3 plugin, enabling reading, creating, and manipulating MIDI regions and tracks through tools like read_logic_track and create_midi_region.
README
LogicProMCP
LogicProMCP is a local Model Context Protocol server plus a planned Logic Pro MIDI FX bridge for working with Logic Pro MIDI material.
The intended Logic integration is:
- Insert a
LogicProMCP BridgeAUv3 MIDI FX plugin on every MIDI/software-instrument track that should be readable. - Each plugin instance sends captured MIDI events to the local MCP sidecar.
- The MCP server exposes the aggregated result as "all Logic tracks."
- Generated MIDI can be written as
.midfiles first, then later sent back through a virtual MIDI/AUv3 output path.
Logic Pro does not currently expose a public project API that lets one local service directly enumerate every track and MIDI region in an open project. "Read all tracks automatically" therefore means "read all tracks that have the bridge extension inserted," ideally through a saved Logic template.
Tools
bridge_status: show the local Logic bridge receiver.list_logic_tracks: list tracks reported by Logic-side bridge instances.read_logic_track: read captured MIDI from one bridge instance.read_all_logic_tracks: read captured MIDI from all bridge instances.read_midi_file: inspect a Standard MIDI File exported from Logic.create_midi_region: create a new single-region.midfile from a musical prompt.create_drum_region: create a drum pattern region.create_chord_region: create a chord progression region.
Install
cd /Users/shlomy/GIT_Repos/LogicProMCP
python3 -m venv .venv
. .venv/bin/activate
python -m pip install -e .
Run MCP Server
logicpromcp
For Claude Desktop or another MCP client, configure the command as:
{
"mcpServers": {
"logicpro": {
"command": "/Users/shlomy/GIT_Repos/LogicProMCP/.venv/bin/logicpromcp"
}
}
}
CLI Smoke Test
logicpromcp-midi create --prompt "four bar funky bass line in C minor" --out examples/funky_bass.mid
logicpromcp-midi inspect examples/funky_bass.mid
Logic Workflow
- To read live/playback material from Logic: run
logicpromcp, then insert the AUv3 bridge on every track that should be visible to the MCP server. - To read exported material: select regions in Logic, use
File > Export > Selection as MIDI File, then pass that.midpath toread_midi_file. - To write a new track/region: run
create_midi_region, then drag the generated.midfile into Logic or useFile > Import > MIDI File. - To preserve tempo and bar alignment, create generated regions at the same BPM and bar length as the Logic project.
See docs/LOGIC_EXTENSION.md for the extension bridge contract.
Roadmap
- AUv3 MIDI FX listener for live MIDI capture per inserted track.
- Virtual MIDI output for recording generated MIDI directly into Logic.
- AppleScript/Shortcuts helper for importing generated MIDI into the frontmost Logic project.
- Region metadata sidecar files for round-tripping track names, bar ranges, prompts, and model decisions.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.