vps-ops-mcp
MCP server for monitoring and managing long-running processes on a remote VPS via SSH, with tools for status, logs, record summaries, and arbitrary command execution.
README
vps-ops-mcp
An MCP server that puts a long-running process on a remote VPS behind a handful of tools an AI assistant can call. Is it alive, what do the logs say, what has it produced, and an escape hatch for everything else.
Node, stdio transport, one dependency. Works with any MCP client.
Written first, in Node. The Python successor, approval-gate-mcp, adds a human approval gate, hot-reload parameters, and a wider dashboard. Use this one if you want something small; use that one if you want the gate.
Why
Checking on a background process means opening a terminal, finding the host, remembering the log path, and reading ps output. None of that is hard and all of it is friction, which means you check less often than you should.
This turns the same job into a question you ask in whatever assistant you already have open, and it keeps the answer structured enough to act on.
Tools
| Tool | What it does |
|---|---|
process_status |
Running or not, PID, uptime, CPU, memory, disk usage, last log line |
process_logs(lines) |
Tail the last N lines of the log file, up to 500 |
record_summary(n) |
Parse the JSON records the process writes into totals, a breakdown by type, and recent entries |
wallet_balance |
Optional. Read-only ERC-20 and native balance for a watch address |
run_command(cmd) |
Escape hatch. Arbitrary shell over SSH |
Install
git clone https://github.com/WillyV347/vps-ops-mcp
cd vps-ops-mcp
npm install
cp .env.example .env # then edit it
Register it with your MCP client:
{
"mcpServers": {
"vps-ops": {
"command": "node",
"args": ["/absolute/path/to/vps-ops-mcp/index.js"],
"env": {
"VPS_HOST": "your.host.or.ip",
"VPS_USER": "your-ssh-user",
"PROCESS_DIR": "/srv/my-process",
"PROCESS_MATCH": "my_process.py"
}
}
}
}
VPS_HOST, VPS_USER, and PROCESS_DIR have no defaults. The server prints what is missing and exits. A monitoring tool that quietly falls back to a host baked in by its author is a bug, not a convenience.
Everything else is optional:
| Variable | Default | Purpose |
|---|---|---|
PROCESS_MATCH |
none | Pattern used to find the process in ps. Without it, process_status tells you so |
LOG_FILE |
$PROCESS_DIR/app.log |
Log file to tail |
RECORDS_FILE |
$PROCESS_DIR/records.json |
JSON array the process appends to |
SSH_KEY |
system default | Path to a private key |
EVM_RPC_URL |
none | Enables wallet_balance when set with the two below |
WALLET_ADDRESS |
none | Watch address, read-only |
TOKEN_CONTRACT |
none | ERC-20 contract to read |
TOKEN_DECIMALS |
18 |
Decimals for that token |
Authentication is your existing SSH setup. The server shells out to the system ssh binary, so agents, hardware keys, and password managers that expose an agent all work unchanged. It never reads a private key itself.
The records file
record_summary reads a JSON array. Four keys are interpreted if present and everything else is ignored, so you do not have to reshape your data to use it:
[
{
"id": "job-1041",
"record_type": "reindex",
"resolved": true,
"outcome": "win",
"cost": 4.25,
"result": 11.80,
"label": "nightly reindex, shard 3"
}
]
record_typegroups the breakdownresolvedsplits done from openoutcomeandresultdecide win or losscostandresultare summed into totals
Example session
> is the process up?
Process RUNNING
PID: 31882
Uptime: 14h 22m (51720s)
CPU: 0.6%
Memory: 84.3 MB
Disk: 212M
Last log: 2026-08-18 22:03:11 cycle complete, 4 records written
> how's it doing overall?
Record Summary
Total: 128
Resolved: 121 (74 win / 47 loss)
Pending: 7
Success: 61.2%
Net result: 46.90
Gross input: 512.25
By type
reindex: 88 (55W/29L/4P) | net 38.40 | 65%
compact: 40 (19W/18L/3P) | net 8.50 | 51%
Output above is illustrative.
Notes on safety
run_commandruns arbitrary shell on the remote host. Scope the SSH user to what it actually needs rather than running everything as root.wallet_balanceis read-only and never touches a key. Leave it unconfigured and the tool is not registered at all.- No credential is stored in this repo. RPC providers put API keys in the URL path, so keep
EVM_RPC_URLin the environment and out of your config files. StrictHostKeyCheckingis set toaccept-new: unknown hosts are trusted on first connect, changed host keys still fail.
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。