flemcee
An MCP server that enables remote control and automation of FL Studio via the flapi Python client. It provides tools for managing transport, mixer tracks, pattern sequencing, and plugin parameters, allowing users to execute Python code directly within the FL Studio environment.
README
flemcee
MCP server for FL Studio powered by the flapi Python client. It exposes
FL Studio control by executing Python inside FL Studio via Flapi.
See /Users/tylertt/flemcee/WORKLOG.md for an implementation summary and
/Users/tylertt/flemcee/ROADMAP.md for the future plan.
Prerequisites
flapiinstalled and working (FL Studio configured with Flapi scripts).- FL Studio running with the Flapi server loaded.
- macOS: keep
flapi port-hostrunning while FL Studio is open.
Install
python -m venv .venv
source .venv/bin/activate
pip install -U pip
pip install -e .
Run
Default MCP transport is streamable HTTP:
python -m flemcee
To use stdio transport:
FLEMCEE_TRANSPORT=stdio python -m flemcee
Configuration
Environment variables:
FLEMCEE_TRANSPORT: MCP transport (streamable-http,stdio, orsse).FLEMCEE_REQ_PORT: MIDI request port name (default:Flapi Request).FLEMCEE_RES_PORT: MIDI response port name (default:Flapi Response).FLEMCEE_CONNECT_ON_START: set totrueto connect to FL Studio at startup.FLEMCEE_LOG_LEVEL: logging level (default:INFO).FLEMCEE_HOST: server host when supported by the MCP transport (default:127.0.0.1).FLEMCEE_PORT: server port when supported by the MCP transport (default:8000).FLEMCEE_MOUNT_PATH: optional base mount path for HTTP transports.FLEMCEE_STREAMABLE_HTTP_PATH: optional streamable HTTP endpoint path.FLEMCEE_SSE_PATH: optional SSE endpoint path.FLEMCEE_GENERATE_TOOLS: set totrueto register per-function tools from stubs (default:true).FLEMCEE_CURATED_TOOLS: set totrueto register curated higher-level tools (default:true).
MCP Tools
fl_connect(force: bool = false)fl_disconnect()fl_status()fl_exec(code: str)fl_eval(expression: str)fl_call(target: str, args: list = [], kwargs: dict = {})fl_catalog(module: str | None = None, include_docs: bool = False)fl_symbol_lookup(symbol: str, include_docs: bool = False)fl_symbol_resolve(target: str, include_docs: bool = False)
Curated tools (auto-generated at startup):
fl_session_summary()fl_transport_play()fl_transport_stop()fl_transport_record_toggle()fl_transport_set_loop_mode(mode: str | int)fl_transport_set_song_pos(position: float | int, mode: int = -1)fl_project_set_tempo(bpm: float)fl_channel_list(global_count: bool = False, use_global_index: bool = False)fl_channel_set(index: int, name: str | None, color: int | None, volume: float | None, pan: float | None, pitch: float | None, target_fx_track: int | None, use_global_index: bool = False)fl_channel_select(index: int, use_global_index: bool = False)fl_pattern_list(include_defaults: bool = False)fl_pattern_select(index: int)fl_pattern_rename(index: int, name: str)fl_sequencer_set_steps(channel_index: int, steps: list[int], value: bool = True, use_global_index: bool = False)fl_sequencer_clear_steps(channel_index: int, length: int = 16, use_global_index: bool = False)fl_mixer_list_tracks(max_tracks: int = 125)fl_mixer_set_track(index: int, volume: float | None, pan: float | None, mute: bool | None, solo: bool | None, arm: bool | None)fl_mixer_route(source_index: int, dest_index: int, enabled: bool = True, level: float | None = None, update_ui: bool = True)fl_plugin_list_params(index: int, slot_index: int = -1, limit: int = 64, use_global_index: bool = False)fl_plugin_set_param(index: int, param_index: int, value: float, slot_index: int = -1, use_global_index: bool = False)fl_plugin_next_preset(index: int, slot_index: int = -1, use_global_index: bool = False)fl_beat_make_hiphop(kick_channel: int, snare_channel: int, hat_channel: int, bars: int = 1, style: str = \"boom_bap\")fl_mix_balance_peaks(track_indices: list[int], target_peak: float = 0.8, mode: int = 2, min_volume: float = 0.0, max_volume: float = 1.0, max_change: float | None = 0.2)
MCP Resources
flstudio://catalogflstudio://module/{module}
Notes
fl_execandfl_evalrun inside FL Studio's Python environment.- Use
fl_callfor convenience (e.g.target="transport.start"). - The API catalog tools read from
fl-studio-api-stubs, providing signatures and documentation when available. - When stub-based tool generation is enabled, each top-level FL Studio function is registered as a tool named
fl_<module>_<function>.
Examples
See /Users/tylertt/flemcee/EXAMPLES.md for complete workflows:
- “Listen to this project and do a mix”
- “Take this loop and sequence it out into a full hip hop beat”
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.
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.
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Neon Database
MCP server for interacting with Neon Management API and databases
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.
E2B
Using MCP to run code via e2b.