Server Ops MCP

io.github.GT-dinuoPublished by GitHub account GT-dinuov1.0.3Updated Oct 24, 2026

Server ops MCP: logs, monitoring, code edit, Nginx & certs. Local + SSH, confirmations & redaction.

VerifiedSTDIODesktop onlyCloud & InfrastructureDeveloper ToolsSecurity & Monitoring

Overview

AI-generated overview

A local MCP server that lets an AI assistant inspect and operate a project or remote server: logs, resources, files, Nginx and certificates, over local or SSH.

What you can do
Inspect system resources: CPU, memory, disk, load, processes, service status and system logs, with memory and disk analysis tools. Work with project logs: list, read and search project and channel logs. Read and edit code: read, list, search, write, patch and delete files, sandboxed to the project root. Manage Nginx and certificates: test and read config, reload Nginx, install and renew certificates. Run whitelisted commands and audit configs for leaked secrets, with a confirmation step for pending actions.
When to use it
Useful when you want an assistant to troubleshoot production issues, do routine server inspections, search logs, make small code edits, or handle Nginx and certificate tasks on a local project or a remote host reached over SSH.
Requirements
Node.js 18 or later; runs locally via npx or a built entry point. OPS_PROJECT_ROOT is required. Remote mode adds OPS_SSH_HOST, OPS_SSH_PORT, OPS_SSH_USER and either OPS_SSH_KEY or OPS_SSH_PASSWORD, plus OPS_SSH_PASSPHRASE for a protected key. OPS_CONFIG_PATH optionally points to a config file for log channels, command whitelist and read limits.
Before you install
Write, delete, command execution, Nginx reload and certificate actions are gated by a two-step confirmation, but still change the target system. SSH credentials and private key passphrases are passed as environment variables; keep key files at permission 600 and never commit .mcp.json or config.json with passwords. Remote access should use a read-only or tightly scoped account. Redaction of secrets in logs and configs is automatic but should not be relied on alone.

Installation

In SourceWeft

  1. Open Server Ops MCP in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Server Ops MCP

English | 简体中文

[npm version] [License: MIT] [Node.js] [MCP] [GitHub stars]

A general-purpose server-ops MCP Server. Let AI tools like Claude Code / Cursor / Codex manage multiple projects or servers through .mcp.json — log troubleshooting, system resource inspection, code read/write, and Nginx / certificate management.

Supports local and remote (SSH) modes, with built-in two-step confirmation, command whitelisting, path-traversal protection, and automatic secret redaction.

Features

  • 🔍 Log troubleshooting: list / read / search project logs, multi-channel logs & system logs
  • 📊 Resource monitoring: CPU / memory / disk / load / processes / service status at a glance
  • 📁 Code operations: read, write, patch, delete, and search files — all sandboxed to the project root
  • 🌐 Nginx & certificates: config test & read, safe reload, certificate install & renewal
  • 🔒 Secure by design: two-step confirmation for writes, command whitelist, path-traversal protection, auto redaction

Installation

Requires Node.js 18+. No clone or build needed — npx fetches and runs the published npm package on first use (see the config below).

To build from source instead (e.g. for development):

bash
git clone https://github.com/GT-dinuo/server-ops-mcp.gitcd server-ops-mcpnpm installnpm run build

Build output goes to dist/; the entry point is dist/index.js.

Configuration

In each project where you want to use this tool, create (or append to) .mcp.json and declare an MCP Server per environment. Local mode only needs OPS_PROJECT_ROOT; remote mode adds the SSH variables.

json
{  "mcpServers": {    "myproject-server": {      "command": "npx",      "args": ["-y", "server-ops-mcp"],      "env": {        "OPS_PROJECT_ROOT": "/www/wwwroot/your-project",        "OPS_SSH_HOST": "<server-ip-or-domain>",        "OPS_SSH_PORT": "22",        "OPS_SSH_USER": "ubuntu",        "OPS_SSH_KEY": "~/.ssh/id_rsa"      }    }  }}

If you built from source, point the command at the local build instead: "command": "node", "args": ["/absolute/path/to/server-ops-mcp/dist/index.js"].

Environment Variables

VariableRequiredDescription
OPS_PROJECT_ROOTYesProject root path; all file operations are sandboxed here
OPS_SSH_HOSTNoRemote server IP / domain; leave empty to run locally
OPS_SSH_PORTNoSSH port, default 22
OPS_SSH_USERNoSSH username
OPS_SSH_KEYNoPath to SSH private key (choose either key or password)
OPS_SSH_PASSWORDNoSSH password (choose either key or password)
OPS_SSH_PASSPHRASENoPrivate key passphrase
OPS_CONFIG_PATHNoPath to an extra config file — see "Custom Configuration"

Usage

Once configured, just give ops instructions in natural language in your AI tool. The AI picks and calls the right tool automatically.

Read-only operations (run directly)

Check the server's CPU, memory, and disk usageSearch for error-level logs from the last hourList the project's log filesRead the Nginx config and check for problemsFind every place in the code that calls sendSms

Write operations (require confirmation)

For writes, deletes, command execution, Nginx reload, certificate install, and similar, the tool first returns a confirmationId. The AI shows you exactly what will run, and it only executes after you confirm:

You: Reload nginxAI: (calls nginx_reload, returns the pending action + confirmationId)    About to run: nginx -s reload. Confirm?You: ConfirmAI: (calls confirm_execute to run it)

file_write, file_patch, file_delete, command_exec, and similar all follow the same confirmation flow.

Typical scenarios

  • Production troubleshooting: "Why is the server memory full?" → memory_analysis + log_search working together
  • Routine inspection: "Is the disk almost full? Which directory uses the most?" → disk_analysis
  • Security audit: "Audit the project config for leaked secrets" → config_audit (output is auto-redacted)

Tool List

System Ops

ToolDescription
system_infoCPU / memory / disk / load / processes
memory_analysisMemory usage analysis
disk_analysisDisk usage analysis
service_statusService status
log_search_systemSearch system logs
nginx_config_testTest Nginx config
nginx_config_readRead Nginx config
nginx_reloadReload Nginx (requires confirmation)
certbot_installInstall certificate (requires confirmation)
certbot_renewRenew certificate (requires confirmation)

Project Code

ToolDescription
log_listList project logs
log_readRead a log
log_searchSearch logs
file_readRead a file
file_listList a directory
file_searchSearch code
file_writeWrite a file (requires confirmation)
file_patchPatch a file (requires confirmation)
file_deleteDelete a file (requires confirmation)
command_execRun whitelisted commands
project_overviewProject overview
config_auditAudit config (auto-redacted)
confirm_executeConfirm and run a pending action

Security

  1. Read-only tools run directly.
  2. Writes, command execution, Nginx reload, certificate install require two-step confirmation (confirm_execute).
  3. Command execution uses a whitelist — dangerous operations like rm -rf, sudo, and piping into a shell are rejected.
  4. File operations are sandboxed to OPS_PROJECT_ROOT; path traversal is blocked.
  5. Passwords, tokens, and other secrets in .env files and logs are automatically redacted.

Custom Configuration

Download config.example.json as config.json, then point OPS_CONFIG_PATH at it to customize log channels, the command whitelist, read limits, and more.

bash
curl -o config.json https://raw.githubusercontent.com/GT-dinuo/server-ops-mcp/main/config.example.json# (if you cloned the repo: cp config.example.json config.json)# After editing config.json, set in the .mcp.json env:# "OPS_CONFIG_PATH": "/absolute/path/to/config.json"

Main fields of config.example.json:

  • logChannels: channel name → log directory path (relative to project root)
  • maxReadLines / maxReadBytes: per-read line / byte limits
  • commandWhitelist.direct: commands that run directly
  • commandWhitelist.confirm: commands that require confirmation

Development

bash
npm run dev    # watch mode, recompiles on changenpm run build  # build to dist/npm run clean  # remove dist/npm start      # run the built Server

Notes

  • Remote operations rely on SSH — use a read-only account or a tightly-scoped command whitelist for the AI.
  • Private key files should have permission 600 (chmod 600 ~/.ssh/id_rsa).
  • Never commit .mcp.json or config.json containing passwords to a repository.

License

MIT © 2026 server-ops-mcp

Source: README.md at commit 16c2f8b

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.0.3LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts