기존 SSH 연결을 통해 GPU, 모델, 소프트웨어, 데이터셋을 포함한 전체 머신 플릿을 코딩 에이전트가 탐색하고 활용할 수 있도록 지원합니다.
다른 이름 sinolion/fleet, agents-fleet
- 스타
- 0
- Tools
- —
- 다운로드, 30일
- —
- 최신 버전
- 0.6.2
- 마지막 커밋
- 2026년 11월 11일
- 라이선스
- MIT
fleet MCP란?
fleet은(는) MCP server입니다. 기존 SSH 연결을 통해 GPU, 모델, 소프트웨어, 데이터셋을 포함한 전체 머신 플릿을 코딩 에이전트가 탐색하고 활용할 수 있도록 지원합니다.
프로젝트 README에서 생성된 요약
fleet MCP server 정보
fleet은 코딩 에이전트가 GPU, 소프트웨어 환경, 데이터셋을 포함한 사용자의 모든 컴퓨터 자원을 탐색하고 활용할 수 있는 방법을 제공합니다. 에이전트가 실행 중인 단일 머신에 국한되지 않고, SSH를 통해 접근 가능한 모든 호스트를 확인하고 상호작용할 수 있게 해줍니다. 이 도구는 로컬 머신에서 작동하며, 대상 머신에 별도의 소프트웨어를 설치하거나 특수 계정을 생성할 필요 없이 원격 호스트에 연결합니다.
사용자는 이미 사용 중인 SSH 명령어를 입력하는 것만으로 서버, RunPod 또는 vast.ai와 같은 제공업체의 클라우드 대여 자원, 또는 tailnet 상의 머신을 추가할 수 있습니다. 서버는 이러한 머신을 조사하여 VRAM, CPU, 디스크 공간과 같은 하드웨어 상세 정보는 물론, 실행 중인 프로세스와 모델 서버를 파악합니다. MCP 프로토콜을 통해 Claude Desktop, Cursor, VS Code와 같은 다양한 코딩 에이전트 및 데스크톱 애플리케이션과 호환됩니다. 이러한 설정을 통해 에이전트는 특정 용량의 여유 VRAM이나 특정 CUDA 버전을 갖춘 머신을 찾는 등 특정 작업에 가장 적합한 하드웨어를 지능적으로 선택할 수 있습니다.
활용 사례
- 1학습을 위한 최적의 하드웨어 탐색학습 스크립트를 실행하기 위해 특정 양의 여유 VRAM을 가진 머신을 찾아달라고 에이전트에게 요청하세요.
- 2클라우드 대여 비용 모니터링대여한 머신 중 현재 사용되지 않으면서 비용만 발생시키고 있는 인스턴스를 에이전트가 식별하도록 하세요.
프로젝트의 README를 바탕으로 작성되었습니다. 모든 활용 사례는 해당 내용의 인용문과 대조하여 확인합니다.
fleet MCP 설치 방법
형식 확인: 2026년 11월 10일Cursor에 추가Goose에 추가Claude Code에 fleet MCP 설치
$ claude mcp add fleet -- uvx agents-fleetCursor에 fleet MCP 설치
~/.cursor/mcp.json
{
"mcpServers": {
"fleet": {
"command": "uvx",
"args": [
"agents-fleet"
]
}
}
}VS Code에 fleet MCP 설치
.vscode/mcp.json
{
"servers": {
"fleet": {
"type": "stdio",
"command": "uvx",
"args": [
"agents-fleet"
]
}
}
}VS Code CLI에 fleet MCP 설치
$ code --add-mcp '{"name":"fleet","type":"stdio","command":"uvx","args":["agents-fleet"]}'Claude Desktop에 fleet MCP 설치
claude_desktop_config.json
{
"mcpServers": {
"fleet": {
"command": "uvx",
"args": [
"agents-fleet"
]
}
}
}Codex에 fleet MCP 설치
$ codex mcp add fleet -- uvx agents-fleetCodex config.toml에 fleet MCP 설치
~/.codex/config.toml
[mcp_servers.fleet] command = "uvx" args = ["agents-fleet"]
Gemini CLI에 fleet MCP 설치
$ gemini mcp add -s user fleet uvx -- agents-fleetGemini settings.json에 fleet MCP 설치
~/.gemini/settings.json
{
"mcpServers": {
"fleet": {
"command": "uvx",
"args": [
"agents-fleet"
]
}
}
}자동 검사
2026년 11월 14일에 실행됨전체 보고서 →자동 검사를 통과했습니다. 이는 보안 감사가 아닙니다. 코드를 직접 읽고 서버에 필요한 최소한의 권한만 부여하십시오. 검사 방식
- 소스 저장소 연결 및 접근 가능sinolion/fleet is public and reachablegithub.com/sinolion/fleet ↗통과
- 패키지가 이 저장소를 소스로 명시agents-fleet names sinolion/fleet as sourcepypi.org/project/agents-fleet/ ↗통과
- 빌드 출처(Sigstore 증명)Sigstore attestation for agents-fleetpypi.org/project/agents-fleet/ ↗통과
- 오픈 소스 라이선스 (OSI)MITspdx.org/licenses/MIT.html ↗통과
- 최근 1년 내 커밋 또는 릴리스Last commit or release 2026-11-11github.com/sinolion/fleet ↗통과
- OpenSSF Scorecard검사되지 않음
- 패키지 이름이 인기 패키지와 유사하지 않음No popular package one edit away from agents-fleet통과
- 패키지 및 해당 종속성에 중요한 보안 권고 없음40 resolved dependencies checked; no critical advisoryosv.dev ↗통과
- 모델에 대한 숨겨진 지침 없음0 tool descriptions and the README read; no override phrases, credential paths or hidden characters통과
- 파괴적인 도구에 라벨 표시됨검사되지 않음
- 원격 엔드포인트가 MCP 핸드셰이크에 응답검사되지 않음
README
GitHub에서 보기fleet — let your coding agent use every machine you have
Claude Code, Codex and Gemini see one machine: the one they run on. fleet shows them all of yours — every GPU and what is running on it, the models being served, the software installed, and where your models and data live.
No account, no cloud service, nothing installed on the machines you add, no keys handed out: fleet logs in exactly as you do, with the SSH you already use.
https://github.com/user-attachments/assets/d35e0200-c2a2-44aa-8f60-a3b6e4addfb7
The problem
Ask your agent to train a model and it starts on your laptop — while a 4090 sits idle across the room and a rented A100 bills you by the hour. It cannot use what it cannot see.
- Your agent is stuck on one machine. It has no idea your other boxes exist.
- Finding a free GPU is manual. SSH into five hosts, run
nvidia-smi, compare in your head. - It cannot see what is running, or what is already there — whose job is on that card, which box already serves Llama 3, where the datasets live — so it downloads and installs things twice.
Get started: ask your agent
Paste this into Claude Code, Codex, Gemini CLI, or any agent that can run commands, on the machine you work from:
Install fleet from https://github.com/sinolion/fleet
Agents: the steps are in INSTALL.md.
That is the whole setup. fleet is installed once on this machine, and every supported agent you have here learns it — not only the one you asked. From here on you say what you want in plain words, with no commands to remember.
Then add your machines
Tell the agent how you reach a machine — the SSH command you already use is enough — or
let it look in your ~/.ssh/config and on your tailnet for machines you can already reach:
You: add my GPU server,
ssh ubuntu@10.0.0.7Agent: Added as
gpu-box: 2× RTX 4090, both idle, 46 GB free. It's ready to use.
Each one takes a sentence, whatever the machine is:
| The machine | What you tell the agent |
|---|---|
| a server you can already SSH into | "add ssh ubuntu@10.0.0.7" — fleet logs in as you do, with your key |
| one you reach with a particular key file | "add ssh -i ~/.ssh/my_key ubuntu@1.2.3.4" — or a Host from your ~/.ssh/config |
| a machine on your tailnet | "find my machines" — it lists your ssh config hosts and tailnet machines, and adds the ones you pick |
| a new rental (vast.ai, RunPod, AutoDL) | "add ssh -p 40001 root@1.2.3.4, it costs $1.89/hr" — with the key on your provider account |
| one that only takes a password | "add it" — fleet offers ssh-copy-id, you type the password once into ssh, and your key goes on it |
| one that will not let you in | "why can't you reach the NAS?" — fleet doctor names the one thing to fix |
Nothing is installed on the machines you add: they only need SSH, on Linux, macOS or Windows. fleet probes each one for its GPUs, memory and disks, and keeps that current.
Then let the agent pick
You describe the work; the agent finds where it fits. It checks what each machine has and what is free on it right now, so it will not send a job to a busy card:
You: train
train.pyon whatever has a free 24 GB cardAgent:
rtx4090has 23.1 GB free and an idle GPU;a100-spotis free too but costs $1.89/hr. Starting onrtx4090, logging totrain.log.
| You say | How the agent finds it |
|---|---|
| "what's free right now?" | every machine checked, the free ones listed |
| "find me a box with a 24 GB card" | matched by what machines have — NVIDIA or AMD, VRAM, cores, RAM — not by name |
| "run the tests on the Linux box" | the machine that runs Linux, results brought back |
| "what's costing me money?" | idle paid rentals flagged, with their hourly price |
| "who is using the GPUs?" | every job on every card — user, VRAM, how long, the command |
| "is Llama 3 already served somewhere?" | every model server's models, and the URL or ssh tunnel to reach it |
| "which box has torch 2.5 and CUDA 12?" | each machine's CUDA or ROCm, Python environments and package versions |
| "download the dataset where datasets go" | the folder that machine says holds datasets, and the room left there |
Keys and passwords never go into the conversation, and anything irreversible waits for your yes.
Only install fleet where you use it. The machines you add need nothing but SSH. Install
fleet on another machine only if you also run agents there; it works the same everywhere,
with nothing to join or sync. There, fleet ls --discover lists the machines in your ssh
config and on your tailnet; the ones you added by hand are in one file you can share with
your dotfiles.
An app that cannot run commands?
Desktop apps and editors get fleet in one click; it runs as an MCP server:
| App | Install |
|---|---|
| Claude Desktop | open fleet.mcpb from the latest release |
| Cursor | |
| VS Code |
Plus plugins for Claude Code, Codex, Copilot CLI and Gemini CLI, and OpenCode, Amp, Windsurf, Cline, Zed, Qwen Code, Goose, Kiro, Hermes — 35+ agents in all: every agent →
Built to be safe
- Nothing to install on your machines. fleet probes with one script over one SSH connection — Linux, macOS or Windows. A NAS or a fresh rental works as it is. The few files it does leave there are listed in What fleet changes.
- No keys handed out, no access managed. fleet connects exactly as you do — your ssh
config, your keys and agent, Tailscale SSH, your rental provider's key — and writes no
keys anywhere. Who may reach what stays where you already decide it. When a machine
refuses,
fleet doctortells you the fix; fleet never makes it. - No passwords. fleet never asks for one or stores one, and the agent never sees a credential. Secrets in a GPU job's command line are blanked before anyone sees them.
- The agent asks, not guesses. It is told to ask which machine you mean, to leave irreversible commands to you, and not to start work on a GPU someone else is using.
- Nothing phones home. Apart from installing and updating itself, fleet talks to your machines and nothing else: no account, no telemetry, no update check. Found a flaw? SECURITY.md says how to report it privately.
Prefer the command line?
Everything the agent does is a plain fleet command. To install fleet yourself, run this
on the machine you work from (this is also what your agent runs when you ask it):
curl -LsSf https://raw.githubusercontent.com/sinolion/fleet/main/install.sh | sh
Windows: powershell -ExecutionPolicy ByPass -c "irm https://raw.githubusercontent.com/sinolion/fleet/main/install.ps1 | iex"
Then drive it yourself:
fleet ls # every machine, with what is free right now
fleet ls --tag cuda --tag vram-24g # by capability: NVIDIA, a card of 24 GB or more
fleet ls --tag rocm # every AMD machine
fleet top # live view, like htop for the whole fleet
fleet show gpu-box # one machine in detail: jobs, software, models, folders
fleet ps # every job on every GPU, and which GPUs are idle
fleet models # every model being served, and how to reach it
fleet edit gpu-box --path models=/data/models # where that machine keeps its models
fleet ssh gpu-box -- nvidia-smi # run something there
fleet add "ssh ubuntu@10.0.0.7" # add a machine
fleet ls --discover # machines in your ssh config and on your tailnet
fleet doctor nas # why a machine will not let you in, and the fix
Where a machine keeps its models, datasets and media is written on the machine itself,
in machine.yaml (fleet edit NAME --path models=/data/models). Whoever looks at that
machine reads the same answer, and the folder sizes and free space come with every probe.
Rentals from vast.ai, RunPod or AutoDL show their price (fleet edit a100 --cost 1.89),
the fleet's burn rate, and an alert when a rental sits idle. On Tailscale, ZeroTier
or WireGuard? fleet just needs an address it can route to.
How fleet compares
fleet is about the machines you already have. It complements tools that launch new ones.
ssh + nvidia-smi |
nvitop / gpustat | all-smi / gpuwho | SkyPilot / dstack | fleet | |
|---|---|---|---|---|---|
| All your machines in one view | ✗ | ✗ one machine | ✓ | ✓ the ones it manages | ✓ |
| Built for coding agents (skill / MCP) | ✗ | ✗ | ✗ | partly | ✓ |
| Nothing installed on target machines | ✓ | ✗ | gpuwho ✓, all-smi ✗ | ✗ | ✓ |
| Jobs, served models, software, data folders | ✗ | jobs, one machine | jobs | ✗ | ✓ |
| NVIDIA, AMD and Apple GPUs | NVIDIA | NVIDIA | all-smi ✓ | ✓ | ✓ |
| Launches new cloud VMs | ✗ | ✗ | ✗ | ✓ | ✗ |
| History, alerts sent to you | ✗ | ✗ | all-smi ✓ | partly | ✗ alerts when asked |
When to use something else. To rent GPUs on demand at the lowest price, use SkyPilot or dstack: they launch and stop machines, and fleet does not. For weeks of metrics and paging on a large cluster, use DCGM with Prometheus and Grafana. For a live dashboard of many accelerator kinds (Gaudi, NPUs), use all-smi. fleet is for the machines you already have, and for letting your agent use them.
Why not just Tailscale, Ansible, or an ~/.ssh/config? Use them with fleet, not
instead of it. Tailscale connects your machines, and fleet runs over it happily, but it
does not tell your agent which machine has a free GPU. Ansible changes machines to match
a playbook you write, and has no idea what is busy right now. An ~/.ssh/config names
your hosts, and fleet reads it. fleet is the part in between: what you have, what is
free on it, what is running and installed there, in a form your agent can use without
you.
FAQ
Setting up
No. Install it where you use it: the machine you work from, and any other machine where you also run agents. The machines you only use — GPU servers, rentals, a NAS — need SSH and nothing else.
No. fleet uses whatever SSH reaches your machines: a LAN, a VPN, a jump host, a rental's
public port. If you have Tailscale, fleet ls --discover finds your tailnet machines
for you, and Tailscale SSH decides who may log in where — fleet just connects. See
Reaching your machines.
They do not need to: each one looks at the machines its own SSH reaches, and what a
machine says about itself — its cost, tags, where its models live — is kept on that
machine, so both read the same. The machines you added by hand are in one file,
machines.yaml (fleet paths shows where); copy it, or keep it in your dotfiles.
Yes — that is the normal case. fleet is installed once per machine: one command, one
list of machines. Each agent only gets a small skill or MCP entry pointing at
it, so Claude Code, Codex, Gemini CLI and a desktop app all see the same machines, and can
use them at the same time. Install a new agent later? Ask an agent that has fleet to run
fleet setup.
Agents that can run commands (Claude Code, Codex, Gemini CLI, Copilot CLI, OpenCode, …)
get a skill — text that tells them the fleet commands; it costs nothing until a task
needs a machine. Apps that cannot (Claude Desktop, Cursor, VS Code, …) get an MCP server
that runs the same commands for them. See Agents. After
installing, start a new session so the agent loads it.
Safety
No and no. fleet has no key of its own and never handles a password: it runs ssh as
you would. For a machine that only takes a password, it offers ssh-copy-id in your
terminal, where you type the password into ssh itself, once. The agent runs fleet ssh NAME and never sees a key or a password; it may see a machine's address, as fleet show prints it.
Almost nothing: the notes file fleet edit writes there (machine.yaml: tags, cost,
a note, folders, declared servers), a
small cache of software versions and folder sizes in ~/.cache/fleet, and nothing at
all in authorized_keys. No program, no service.
What fleet changes has the full list.
It is told not to. Removing a machine is left to you, and is not available to apps over MCP at all. When a request is ambiguous — which machine, which user — the agent asks instead of guessing.
Machines
Some systems — containers, GPU rentals — show / as a small overlay while the space is on
another volume. Tell fleet which paths to watch: "on gpu-box, watch /workspace", or
fleet edit gpu-box --disk-path /workspace. See
Disks.
Re-point it, keeping its name, tags, cost and history: "gpu-box is now at
ssh -p 40123 root@5.6.7.8", or fleet edit gpu-box --ssh "ssh -p 40123 root@5.6.7.8".
fleet does not solve connectivity; it uses the routes you have. The machine you run fleet on must reach each machine over SSH; the machines never need to reach each other. For machines behind different NATs, put them on a mesh network such as Tailscale or ZeroTier and add them by their mesh address. See Reaching your machines.
Yes, both ways. A Windows machine works as a target with OpenSSH Server and nothing else, and fleet runs on Windows too. See Windows.
No service. fleet runs only when you or an agent use it. The ssh connection it opened to
each machine stays open for two minutes after the command (on Linux and macOS), so the
next one does not dial again, and then closes by itself. On a machine it looks at, a
du of the folders you named may run in the background now and then, so their sizes
are known without making a probe wait.
fleet stopped managing access: no center, no invites, no keys of its own. Upgrade, and add your machines again. Upgrading from 0.5 lists what 0.5 left on your machines and how to remove it.
fleet uninstall (--purge to delete its files too): it removes fleet from your agents
and prints the last step, uv tool uninstall agents-fleet. See
Removing fleet.
Learn more
- Getting started — your first fleet, in ten minutes
- Guides — adding machines, reaching them, what is on each one, Windows
- Every agent — install commands and config for 35+ agents
- Command reference — every command and option
- How fleet works — what happens, step by step, under the hood
- Design — one core per machine, a skill per agent, MCP for the rest
- All documentation, also as a website: agents-fleet.dev
Status: v0.6. The test suite runs on Linux, macOS and Windows, and every command is run end to end on a real machine of each OS in CI — from a script, as an agent runs it, and at a real terminal, as you do.
Issues and pull requests are welcome — see CONTRIBUTING.md. If fleet saved you a GPU-hour, a ⭐ helps other people find it.
fleet MCP 질문
fleet MCP를 Claude Code에 추가하려면 어떻게 하나요?
터미널에서 claude mcp add fleet -- uvx agents-fleet를 실행합니다. 모든 프로젝트에서 사용할 수 있게 하려면 --scope user를 추가합니다.
fleet MCP를 Cursor에 추가하려면 어떻게 하나요?
~/.cursor/mcp.json를 열고 mcpServers 아래에 서버를 추가합니다. 위 설치 섹션에 표시된 Cursor 구성을 사용합니다.
원격 머신에 별도로 설치해야 하는 것이 있나요?
아니요, 추가하는 머신에 아무것도 설치할 필요가 없습니다. SSH 연결만 가능하면 되며 Linux, macOS, Windows에서 모두 작동합니다.
클라우드 GPU 대여 관리에 도움이 되나요?
네, vast.ai, RunPod, AutoDL와 같은 제공업체의 대여 현황을 추적할 수 있으며, 시간당 비용 확인 및 유휴 인스턴스 식별이 가능합니다.