@roomi-fields
基本信息
OSC ↔ MIDI/SysEx bridge for 849 hardware synths and music software (Ableton, Bitwig, Reaper, Sonic Pi). A MIDI MCP and OSC MCP for Claude.
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"osc-bridge": {
"command": "npx",
"args": [
"-y",
"@roomi-fields/osc-bridge",
"mcp"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。
点击上方按钮,在临时沙箱中运行此服务器并实时获取工具列表。
It is an MCP server that provides a declarative bridge between music hardware (synthesizers over MIDI/SysEx) and software (DAWs and live-coding environments over OSC). It supports 849 devices across 187 vendors and includes a built-in MIDI MCP and OSC MCP to drive everything from an LLM like Claude.
Run it as an MCP server with npx -y @roomi-fields/osc-bridge mcp, then configure your MCP client (e.g., Claude Desktop) to point to that command. Each supported device is described by one JSON file, so you can control synths and DAWs via named OSC addresses after startup.
The bridge supports 849 devices across 187 vendors, including Moog, Arturia, Roland, Yamaha, Ableton, Bitwig, and many more. Devices are categorised by verification status (hardware‑verified, software‑verified, vendor‑doc derived, etc.). A full searchable catalogue is at <https://roomi-fields.github.io/osc-bridge/>.
Open a pull request adding a JSON file under `devices/<vendor>/<slug>.json`. The 30‑minute tutorial in `docs/TUTORIAL_FIRST_DEVICE.md` walks you through building a driver. Devices must cite a source (vendor documentation, third‑party CSV, etc.); contributions that promote a device from “doc‑derived” to “hardware‑verified” are especially welcome.
Each device gets a single declarative JSON file as its driver — no Rust code, no build step. The bridge handles both hardware (MIDI/SysEx) and software (OSC) with the same named OSC surface, supports bidirectional feedback, and includes a built‑in MCP server for LLM control. It also provides honest provenance markers so you know whether a mapping was tested on real hardware.
It is distributed as a single static binary for Windows, Linux, and macOS. No runtime dependencies, no garbage collector, no separate bridge process needed. For MCP usage, only Node.js is needed to run the `npx` command that launches the pre‑built binary.
The MCP server uses standard stdio transport (the command runs as a subprocess of the MCP client). For OSC, it listens on the ports defined in device JSON files (defaults shown in the documentation). No authentication layer is described — the bridge is intended for local or trusted network use.
Manage CI/CD pipelines, debug failed builds, and optimize test suites directly from your AI agents - no terminal required. The CircleCI MCP Server is a remote server hosted by CircleCI that connects AI tools and agents
Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.
SSH MCP server for AI agents: remote commands, file transfer, log search and server audits through OpenSSH.
ArtiBot Cloud MCP (Zhijiangyun 智匠云) — cloud MCP server for robot manipulation data & GPU workloads. 15 tools: robot fleet management, data collection & video recording, post-processing pipelines, and benchmark evaluation
Open-source MCP server for Google Play developer workflows. Runs locally with your own credentials.
评论