The clutor command and local server: plan whether a model fits your machine, inspect GGUF files, simulate expert streaming, run a sandboxed coding agent, and serve an OpenAI- and Ollama-compatible API
{ "mcpServers": { "clutor-cli": { "command": "npx", "args": [ "-y", "@clutor/[email protected]" ] } }}Power your agent
Perintah milik penerbit sendiri. Bukan endpoint PlugMCP.
Host a copy with our keys and logs.
npx -y @clutor/[email protected]Claude Code tidak punya tautan instal untuk perintah lokal. Salin perintah di bawah dan jalankan di terminal.
claude mcp add clutor-cli -- npx -y @clutor/cli@0.3.1Jalankan di terminal.
{ "mcpServers": { "clutor-cli": { "command": "npx", "args": [ "-y", "@clutor/[email protected]" ] } }}claude_desktop_config.json
URL remote atau perintah di mesin Anda? Perbedaan kedua cara instal
Jalankan di PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
BukaRingkasan umum
The clutor command and local server: plan whether a model fits your machine, inspect GGUF files, simulate expert streaming, run a sandboxed coding agent, and serve an OpenAI- and Ollama-compatible API on localhost in front of llama.cpp.
Tool
Belum ada daftar tool. Server remote mendapatkannya setelah pemeriksaan kesehatan pertama.
FAQ
Salin konfigurasi stdio untuk Cursor, Claude Desktop, Claude Code, atau VS Code di halaman ini. Konfigurasi ini memakai instalasi dari penerbit, bukan proxy PlugMCP.
Tidak ada variabel lingkungan wajib yang tercantum di catatan ini.
@clutor/cli berjalan secara lokal melalui stdio.
Terakhir diperiksa 2026-11-10. The clutor command and local server: plan whether a model fits your machine, inspect GGUF files, simulate expert streaming, run a sandboxed coding agent, and serve an OpenAI- and Ollama-compatible API on localhost in front of llama.cpp.
Dari penerbit
README belum di-crawl. Buka repositori
The clutor command and local server: plan whether a model fits your machine, inspect GGUF files, simulate expert streaming, run a sandboxed coding agent, and serve an OpenAI- and Ollama-compatible API on localhost in front of llama.cpp.