mcp-koii vs filesystem
Side-by-side comparison to help you pick between these two MCP servers.
mcp-koii by benjaminr | filesystem by modelcontextprotocol | |
|---|---|---|
| Stars | ★ 23 | ★ 85,748 |
| 30d uses | — | — |
| Score | 43 | 77 |
| Official | — | ✓ |
| Categories | MediaDeveloper ToolsOther | File SystemDeveloper ToolsProductivity |
| Language | Python | TypeScript |
| Last commit | 3 mo ago | this month |
mcp-koii · Summary
MCP server for controlling Teenage Engineering EP-133 K.O. II sampler via MIDI with pattern creation and playback.
filesystem · Summary
A feature-rich MCP server for filesystem operations with dynamic directory access control.
mcp-koii · Use cases
- Create drum patterns with natural language commands
- Control hardware sampler through AI assistant
- Browse and trigger different sounds on the EP-133 device
filesystem · Use cases
- Enable AI models to read and write project files during development
- Allow Claude or other MCP clients to browse and analyze codebases
- Provide secure sandboxed access to specific directories for content generation
mcp-koii · Install
Prerequisites
- Python 3.8 or later
mido(MIDI handling)mcp(Model Context Protocol SDK)
Installation
# Install the required packages
pip install mido "mcp[cli]"
# Clone the repository
git clone https://github.com/benjaminr/mcp-koii.git
cd mcp-koii
# Install the MCP server
mcp install koii_server.py:server -e .Claude Desktop Configuration
Add this to your Claude Desktop config.json:
{
"mcpServers": {
"koii": {
"command": "python",
"args": ["koii_server.py"]
}
}
}filesystem · Install
Installation
Using NPX
{
"mcpServers": {
"filesystem": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-filesystem",
"/path/to/allowed/directory"
]
}
}
}Using Docker
{
"mcpServers": {
"filesystem": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"--mount", "type=bind,src=/path/to/allowed/dir,dst=/projects/allowed/dir",
"mcp/filesystem",
"/projects"
]
}
}
}VS Code Extension
Click the installation buttons in the README to install directly in VS Code.