GitHub
GitHub’s official server lets AI read and manage code, issues and pull requests in your account. Use GitHub’s hosted version or run it locally with Docker.
Computer or cloud
kiriya
Overview
Description from the maker (original English)
Developer tools for files, git, ports, processes and more, the same on Windows, Linux and macOS
PopNx MCP’s three pillars
These three are never merged into one score: opinions, measurements and popularity are different things.
- User voiceiNo reviews yetReviews open together with accounts in a later step
- Our basic checksi1 of 1 passedChecked from public information; code not scanned yet
- UsageiVery new↓ 73/wk · ★ –
What you can do with it
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
- Connection: Runs on your computer
- Transport: stdio
- Category: Developer tools
Install
Pick the AI app you use, then copy the settings.
Before you install
- Basic checks: 1 of 1 passed
- Runs on your computer with your user’s permissions (files, network, apps).
- The registry lists no key to fill in.
You need
- npmNode.js installed (for the npx command)
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"kiriya": {
"command": "npx",
"args": [
"-y",
"kiriya",
"mcp"
]
}
}
}Run this in your terminal
claude mcp add kiriya -- npx -y kiriya mcpOr copy the settings yourself
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"kiriya": {
"command": "npx",
"args": [
"-y",
"kiriya",
"mcp"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Or copy the settings yourself
Paste into .vscode/mcp.json in your project
{
"servers": {
"kiriya": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"kiriya",
"mcp"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
What it can do
Runs on your computer; the tool list appears in your AI app after you install it.
Basic checksi
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 8, 2026
- ✓ Pass
Maker matches the repo
The registry name was verified with the GitHub account SatPaingOo, which owns the repo
- … Not checked yet
Still maintained
We have not read this repo from GitHub yet
- … Not checked yet
Has a licence
We have not read this repo from GitHub yet
- – Not applicable
Endpoint responds
This one runs on your computer; there is no internet endpoint
- – Not applicable
Sign-in with OAuth
Runs on your computer and uses local settings instead
- … Not checked yet
No hidden instructions in tool descriptions
Runs on your computer; we can only read tool lists from internet endpoints
Compared with others in Developer toolsi
- More stars than 0% of the other 4933 servers in this category
- Published to the registry more recently than 58% of the other 4933 servers in this category
- Basic checks equal to or better than 100% of the other 4933 servers in this category
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
Common questions
Is kiriya safe?
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
What keys or codes does it need?
The registry does not list a required key, though some servers ask you to sign in on first use.
Does it run on my computer or in the cloud?
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
Is it still maintained?
The GitHub repo last changed –, and the latest version (0.3.0) reached the registry 29 days ago.
Which apps can use it?
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.
What can I use instead?
In the same category: GitHub, Desktop Commander, Cloudflare MCP
Alternatives
Servers in the same category from other makers, sorted by stars.
Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Desktop Commander
MCP server for terminal commands, file operations, and process management
Runs on your computer
README from the maker
Open the README
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
kiriya
One command-line toolbox for everyday developer work that behaves the same on Windows, Linux and macOS.
kiriya (ကိရိယာ, Burmese for "tool") saves remembering del and rm, netstat -ano and lsof -i, clip and pbcopy, or writing a one-off script for each. It is one Node.js program with no runtime dependencies. Every command answers --json, and convert json --get reads a value back out of that answer without a second tool. Changes to many files show a plan first, deletions go to the trash, and nothing that cannot be undone happens until you type a confirmation. AI agents can use the same commands over MCP, under the same rules.
Install
kiriya needs Node.js 22.13 or later.
npm install --global kiriyaThen check what this machine gives it:
kiriya doctorEvery release is published from CI with provenance, so npm audit signatures can show which workflow built the copy you installed. Every module below is tested on Windows, Linux and macOS with Node.js 22, 24 and the current release.
Getting started takes it from there, and CONTRIBUTING.md covers building from source.
Quick start
kiriya doctor # what this machine offers kiriyakiriya port who 3000 # which process holds port 3000 kiriya files find --name "*.log" --older 30d # the same search in every shell kiriya files delete dist --dry-run # the plan, before anything changes kiriya git status ~/code --json # every repository under a folder, as JSON
Finding your way
Help goes three steps deep, and each step names the next, so nothing has to be guessed.
kiriya --help # the modules, and the options every command acceptskiriya help files # one module: its commands, and what each one takes kiriya help files delete # one command: its arguments, options and examples
kiriya files delete --help says the same as that third line. The middle step lists each command's option names underneath it, so a module's whole surface fits on one screen:
Commandsdelete Send files and folders to the trash, or remove them for good with --permanent --permanent --dry-run --yes --confirm --all find Find files and folders by name, extension, type, size, age or emptiness --name --ext --type --larger --smaller --newer --older --empty --all --limit
Every module also has a guide below with a full reference: every command, argument and option, what each does, and whether it can be undone.
Modules
| Module | What it does |
|---|---|
archive | ZIP and tar.gz archives, made and opened the same way on every OS with no zip, tar or 7-Zip installed. |
clip | Copy text to the clipboard and paste it back, with Unicode intact on every OS. |
completion | Tab completion for kiriya's modules, commands, options and values in bash, zsh, fish and PowerShell. |
config | kiriya's own settings, such as the plugins to load, in one file per user. |
convert | Convert text between base64, hex, URL encoding, JSON, JWT, times and cases, entirely on this machine. |
docker | docker compose for the project in the current folder, and a previewed clean-up of the engine. |
doctor | Check what this machine gives kiriya: runtime, configuration, trash, clipboard, git, docker and plugins. |
env | Environment variables, PATH and .env files, read the same way on every OS. |
files | Files and folders: create, find, read, search, compare, copy, move, rename and delete, the same on every OS. |
gen | Random identifiers, passwords and tokens from the operating system's secure random source. |
git | Git across every repository under a folder: status, fetch, pull and switch. |
net | Local addresses, TCP reachability and DNS lookups, the same on every OS. |
open | Open a file or folder in its default application, or a web address in the browser. |
port | See which process listens on a TCP port, end it, or find a free port, the same on every OS. |
proc | List, find and end processes, and show them as a tree, the same on every OS. |
secrets | Find secrets committed into a folder's files: tokens, private keys and passwords in plain sight. |
self-update | Ask the registry whether a newer kiriya exists, and install it with --apply. |
sys | This machine and the developer tools on it, described the same way on every OS. |
wait | Wait until a port listens, a web address answers or a file appears, the same way on every OS. |
AI agents
kiriya mcp serves these commands to AI agents over the Model Context Protocol. It offers only commands that change nothing until you allow more, and asks you before any work that cannot be undone. MCP server shows how to add it to a client.
Documentation
| For | Read |
|---|---|
| Using kiriya | Getting started · Usage · Modules |
| Guides | MCP server · Tab completion · Plugins |
| Contributing | CONTRIBUTING.md · Architecture · Design |
| Everything | Documentation index |
Project
Changelog · Security policy · Code of conduct · MIT licence