ZeroMind (OrigoZero game engine)
What it does
Build, run and publish 3D games in the Zero engine from Claude Code, Cursor or Codex, over MCP.
- Connects Runs in the cloud
- Account or key Sign in to the service when you connect (OAuth)
- Category Games, sports, food & learning
Install
Pick the AI app you use, then copy the settings.
Passed 4/4 checks · What you ask goes through the maker’s server (origozero.ai) · ✓ Commands checked Nov 13, 2026
First: which AI do you use?
Pick your app and the steps appear below.
Works with Claude · about 2 min
No key, nothing to install · Set it up once on claude.ai or the desktop app, then use it in chat · free accounts can add 1 · on Team/Enterprise an Owner adds it
Open Claude’s Connectors page
CustomizeConnectors
Click “Add” → “Custom” → “Web” and fill in these 2 fields
Copy each value into the field with the same name in Claude, then click Continue
Name · NameZeroMind (OrigoZero game engine)Remote MCP server URL · Addresshttps://origozero.ai/mcpClick Continue past the sign-in settings Claude detected · under Authentication choose what the maker says (Sign in now, Sign in when needed or No sign in), then click Add
Turn it on in a chat
+ConnectorsZeroMind (OrigoZero game engine)
Try it
Use ZeroMind (OrigoZero game engine) and tell me what you can do for me, then show me one thing✓ If Claude says it is using ZeroMind (OrigoZero game engine) or shows a ZeroMind (OrigoZero game engine) tool in the answer, you are connected
Menu names checked against Anthropic’s help page on Nov 11, 2026 · your screen may differ slightly by app version
Works with ChatGPT, depending on your plan
Full MCP: ChatGPT Business, Enterprise or Edu on the web · Pro: connects with read/fetch permissions, so tools that change data may not work · Plus: not confirmed in OpenAI’s docs; if you see an add-custom-MCP option on the Plugins page you can try these steps · web only
Open ChatGPT’s add-MCP page on the web
Plugins+Add custom MCP server
Fill in the name and address
Enter a name, paste the address under Connection, tick the risk warning and click Create as a plugin
Name · NameZeroMind (OrigoZero game engine)Connection · Addresshttps://origozero.ai/mcpPick ZeroMind (OrigoZero game engine) in a chat
Start a new chat and pick ZeroMind (OrigoZero game engine) from your plugins before typing
Try it
Use ZeroMind (OrigoZero game engine) and tell me what you can do for me, then show me one thing✓ If ChatGPT says it is using ZeroMind (OrigoZero game engine) or shows a ZeroMind (OrigoZero game engine) tool in the answer, you are connected
Menu names checked against OpenAI’s help page on Nov 11, 2026 · your screen may differ slightly by app version
Works with Claude Code · about 2 min
No key, nothing to install
Open Terminal
Mac: press Command+Space and type Terminal · Windows: open PowerShell
Paste this command and press Enter
claude mcp add --transport http --scope user zeromind https://origozero.ai/mcpType /mcp in Claude Code
You should see ZeroMind (OrigoZero game engine) listed as connected
Try it
Use ZeroMind (OrigoZero game engine) and tell me what you can do for me, then show me one thing✓ If Claude Code says it is using ZeroMind (OrigoZero game engine) or shows a ZeroMind (OrigoZero game engine) tool in the answer, you are connected
Menu names checked against Anthropic’s help page on Nov 11, 2026 · your screen may differ slightly by app version
Works with Cursor · about 2 min
No key, nothing to install
Open the AI chat in Cursor in Agent mode
Try it
Use ZeroMind (OrigoZero game engine) and tell me what you can do for me, then show me one thing✓ If Cursor says it is using ZeroMind (OrigoZero game engine) or shows a ZeroMind (OrigoZero game engine) tool in the answer, you are connected
Menu names checked against Cursor’s help page on Nov 11, 2026 · your screen may differ slightly by app version
Works with VS Code · about 2 min
No key, nothing to install
Open the AI chat in VS Code in Agent mode
Try it
Use ZeroMind (OrigoZero game engine) and tell me what you can do for me, then show me one thing✓ If VS Code says it is using ZeroMind (OrigoZero game engine) or shows a ZeroMind (OrigoZero game engine) tool in the answer, you are connected
Menu names checked against VS Code’s help page on Nov 11, 2026 · your screen may differ slightly by app version
Other apps that use MCP, such as Windsurf, Zed or Gemini CLI, each add servers differently. See how in the app list.
Address for apps that connect over the web
https://origozero.ai/mcpJSON settings are under “For developers” below
For developers: Terminal commands and JSON settings
Over the web
Claude Code
claude mcp add --transport http --scope user zeromind https://origozero.ai/mcpCursor (~/.cursor/mcp.json)
{
"mcpServers": {
"zeromind": {
"url": "https://origozero.ai/mcp"
}
}
}VS Code (mcp.json)
{
"servers": {
"zeromind": {
"type": "http",
"url": "https://origozero.ai/mcp"
}
}
}These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
At a glance
- Downloads per weeki
- Not on npm/PyPI
- Verified domain
- ✓ origozero.ai
- Connection
- Runs in the cloud
- Transport
- streamable-http
- Latest versioni
- 1.0.0
- Categoryi
- Games, sports, food & learning
- Published to registryi
- Sep 20, 2026
- Code last changedi
- Nov 12, 2026
- Maker
- OrigoZero
- Website
- origozero.ai
- Registry status
- Active
Which apps can use it
Based on how this server connects and on each app’s own docs, checked Nov 10, 2026.
Connect over the internet in
ClaudeChatGPTGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatOpen WebUIRaycast
Related guides
What it can do
The server asks you to sign in before it lists its tools.
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 14, 2026
- ✓ Pass
Maker matches the repo
The registry name was verified against the domain origozero.ai (the registry checks domain ownership)
- ✓ Pass
Still maintained
Code last changed 2 days ago
- – Not applicable
Has a licence
Not applicable: a cloud server run by the owner of origozero.ai; you don't run code from the repo
- ✓ Pass
Endpoint responds
Responded in 780 ms (HTTP 401)
- ✓ Pass
Sign-in with OAuth
Declares OAuth sign-in, so your AI app can take you to log in
- … Not checked yet
No hidden instructions in tool descriptions
Not checked yet; we read the tool list when we check the endpoint
Discussion
Ask, share a tip or report that it does not work. Sorted by what people marked helpful.
No posts yet. Be the first to ask or share.
Posts here are written by users, not the PopNx team.
User reviews
No reviews yet
Compared with others in Games, sports, food & learningi
- More stars than 86% of the other 1496 servers in this category
- Published to the registry more recently than 27% of the other 1496 servers in this category
- Basic checks equal to or better than 100% of the other 1496 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 ZeroMind (OrigoZero game engine) safe?
It passed 4 of 4 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 in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.
Is it still maintained?
The GitHub repo last changed 2 days ago, and the latest version (1.0.0) reached the registry 2 months ago.
Which apps can use it?
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT on the web (full MCP on Business and above; Pro read-only).
What can I use instead?
In the same category: Honcho, ShipSwift, Pm Claude Skills
Others in the same category
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
ShipSwift
40+ production-ready SwiftUI recipes for building full-stack iOS apps via MCP.
Pm Claude Skills
1310 professional Agent Skills + workflow recipes — searchable & fetchable over MCP.
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.
@origozero/zeromind
@origozero/zeromind connects your agent to ZeroMind through its shell or its MCP integration. The zero and zeromind commands call the hosted server at https://origozero.ai/mcp, which authenticates the caller and routes operations to the selected engine. Worlds, branches, files, and shell execution live in that engine, whether it runs in a browser, on this computer, or elsewhere. The package also installs harness configuration and the skills that teach agents to use ZeroMind.
Use your agent's shell
Install the CLI and approve its browser sign-in once:
npm install -g @origozero/zeromind
zero login
In Windows PowerShell, use npm.cmd if execution policy blocks npm.ps1. From a built source checkout, invoke node dist/index.js in place of zero, and node dist/shell.js in place of zero-shell:
node dist/index.js --help
node dist/index.js --context my-agent sessions
Use a distinct context name for each agent. Reuse that name across commands:
zero --context my-agent sessions
zero --context my-agent connect --world "My World" --branch feature zero --context my-agent bash -c 'pwd; ls /zero/source' zero --context my-agent bash -c 'zm status'
sessions names each engine, its world and branch. When several engines match, select one explicitly with connect --session . The hosted service owns selection and permissions; the context preserves the caller identity and engine pin between CLI processes. A disappeared engine is reported by the server. Release the context's connection when finished with zero --context my-agent disconnect.
Set ZERO_CONTEXT to omit --context. Codex's CODEX_THREAD_ID is used when present and no explicit context was supplied. Different contexts keep separate shell directories, variables and selected engines. zero tools returns the hosted tool catalogue and schemas; zero call reaches every operation it lists:
zero --context my-agent tools
zero --context my-agent call world.list zero --context my-agent call read_file --input '{"path":"/zero/source/main.luau"}'
Generic calls print the MCP content blocks and structured content as JSON, including images and other non-text results. bash -c instead writes the engine shell's stdout and stderr to the corresponding host streams and returns its exit status. The CLI uses the engine's shell API through hosted execute to retain those fields, and follows promoted work with hosted wait. bash -s reads a shell script from host stdin:
printf 'pwd\nls /zero/source\n' | zero --context my-agent bash -s
For a harness that accepts a custom shell executable, choose zero-shell, set ZERO_CONTEXT to the context connected above, and disable login-shell mode. Its ordinary -c calls then execute in the selected engine:
ZERO_CONTEXT=my-agent zero-shell -c 'pwd; ls /zero/source'
For an agent that invokes Bash itself, set BASH_ENV for the agent process:
ZERO_CONTEXT=my-agent BASH_ENV="$(zero bash-env)" your-agent-command
Bash reads this startup file and hands its command, stdin or engine script path to Zero. This also handles noninteractive login invocations such as bash -lc. Arguments, stdin, output streams and exit status follow the same shell transport. The setting is scoped to that agent and its child processes. Start it without BASH_ENV to use the host shell again; interactive terminals use zero-shell -i.
The adapter accepts -c [arg0 args...], -s [args...] (a script on stdin), or an engine VFS script path followed by its arguments. Argument boundaries, empty strings and shell-sensitive characters are preserved. With an engine exposing the attached-shell API, command input and separate output streams flow through the hosted connection, and interruption cancels the remote command.
Run zero-shell -i or zero --context my-agent bash -i for an interactive session. A bare zero-shell opens one when stdin is a terminal. Local line editing and history feed the engine's parser, which reads multiline commands and heredocs. Shell variables and the working directory persist until exit or EOF; Ctrl+C interrupts the current command and returns to its prompt.
zero login --username my-agent opens the approval page for the CLI's own agent account. You can select an existing agent there. On a remote computer, pass --no-browser and open the printed URL on your own device. The CLI verifies that the approved account is an agent; zero whoami shows that identity. Credentials are stored separately from the engine's machine-link cache. zero logout revokes this CLI installation. An existing agent /link credential can also be used after its account identity is verified.
Launch a native engine from the CLI
zero engine install
zero engine doctor --software-rendering zero --context my-agent open "My World" --branch feature zero --context my-agent open "My World" --branch feature --headless --software-rendering
open reuses a matching accessible engine or downloads a verified release, launches it with an authorized handoff, and waits until commands work. Use --session to choose an existing engine, --new to start another, or --browser to open a browser engine. --bin selects a particular native executable. Plain zero open uses the context from your environment.
Linux AppImage updates are unpacked into the CLI-managed installation and run through their entrypoint, without requiring a FUSE mount or desktop installer. The Linux x64 distribution targets Ubuntu 24.04 or newer (glibc 2.39), including Debian 13. A cloud machine needs Node.js 20 or newer to run the CLI.
An omitted branch keeps the context's matching pinned branch, or uses the world's reported default branch. An explicit --session keeps that session's branch unless --branch also names one.
--headless starts a new engine with an offscreen framebuffer. In a headless engine, CLI commands use its primary client by default. Named sub-clients can be created explicitly for parallel work. The CLI continues to authenticate as its approved agent account.
Add --software-rendering to require a CPU adapter, such as Mesa lavapipe on Linux or D3D12 WARP on Windows. The CLI checks the renderer before requesting a launch credential. --width and --height set the framebuffer dimensions; CPU rendering defaults to 640 by 360. The engine release must expose --check-renderer and the hosted service must support authorized native launches.
zero engine doctor initializes the offscreen renderer and reports the actual adapter, driver and framebuffer size as JSON. It runs without logging in or opening a world. Add --software-rendering to check CPU rendering specifically, or --bin to check a particular executable.
For a Debian/Ubuntu cloud machine, zero engine install --software-rendering also provisions the engine's runtime libraries, Vulkan loader and Mesa CPU driver if the renderer check fails. It uses the distribution's package repositories, running as root or through noninteractive sudo, then checks the renderer again. A working CPU renderer makes this step a no-op. Windows uses its D3D12 WARP driver. Other Linux distributions can supply their Vulkan loader and lavapipe through their package manager, then verify them with zero engine doctor --software-rendering.
Each supported harness (Claude Code, Cursor, Codex CLI, Gemini CLI, OpenCode, Cline, Continue, Windsurf, Zed, openClaw, JetBrains Junie, Sourcegraph Amp, GitHub Copilot, Block Goose, Aider) gets its onboarding through that harness's own native channel — skills, AGENTS.md, GEMINI.md, .cursor/rules/*.mdc, .clinerules, CONVENTIONS.md, .goosehints — plus the MCP entry in the config file that harness reads. A harness with no custom-crafted integration uses the generic streamable-HTTP wiring in ide/README.md.
What the agent gets, once linked: the ZeroMind library (search, inspect, preview, install, engage), worlds (list, create, fork, launch, connect, and the reversible delete / trash / restore), and — for the world it is connected to — the engine itself (execute, guides, capture, the VFS, bash). tools/list on https://origozero.ai/mcp is the current surface; it is served rather than shipped, so this README does not enumerate it.
Prerequisites
Node.js 20 or newer, on your PATH, to run zeromind link, zeromind install, zeromind upload and zeromind open. Your harness then talks to https://origozero.ai/mcp over HTTPS and spawns nothing locally.
- macOS:
brew install node(or download from https://nodejs.org) - Linux: your distro's package manager, or https://nodejs.org / nvm
- Windows: https://nodejs.org (LTS installer) — restart your IDE after install so it picks up the new PATH
Verify with node --version.
Install
Claude Code
/plugin marketplace add OrigoZero/zeromind-plugin
/plugin install zeromind npx -y @origozero/zeromind link
The bundle carries the skills and an .mcp.json whose Authorization header expands ${ZEROMIND_INSTALL_SECRET}; zeromind link writes that variable into ~/.claude/settings.json env. Restart Claude Code afterwards so the new setting is read.
Every other harness
npx -y @origozero/zeromind install <harness>
One command per harness — it links the machine first if it isn't linked yet, writes the harness's native instruction file, and writes the /mcp entry into that harness's own MCP config:
npx -y @origozero/zeromind install claude # .claude/skills/zeromind-{getting-started,library}/SKILL.md
npx -y @origozero/zeromind install cursor # .cursor/rules/zeromind.mdc npx -y @origozero/zeromind install codex # ~/.codex/AGENTS.md (or ./AGENTS.md) npx -y @origozero/zeromind install gemini # ~/.gemini/GEMINI.md (or ./GEMINI.md) npx -y @origozero/zeromind install opencode # .opencode/skills/zeromind/SKILL.md npx -y @origozero/zeromind install cline # .clinerules/zeromind.md npx -y @origozero/zeromind install continue # .continue/rules/zeromind.md npx -y @origozero/zeromind install windsurf # ./AGENTS.md npx -y @origozero/zeromind install zed # .claude/skills/zeromind/SKILL.md npx -y @origozero/zeromind install openclaw # skills/zeromind/SKILL.md npx -y @origozero/zeromind install junie # ./AGENTS.md npx -y @origozero/zeromind install amp # ./AGENT.md npx -y @origozero/zeromind install copilot # .github/copilot-instructions.md npx -y @origozero/zeromind install goose # ~/.config/goose/.goosehints npx -y @origozero/zeromind install aider # ./CONVENTIONS.md npx -y @origozero/zeromind install hermes # ~/.hermes/config.yaml + plugin bundle
npx -y @origozero/zeromind install --list # enumerate
Every command is idempotent: shared files (AGENTS.md, GEMINI.md, CONVENTIONS.md, .goosehints, copilot-instructions.md) carry a delimited block that is replaced in place; owned files (skills, rule files) need --force to overwrite. Two harnesses have no MCP config path to write into — openClaw's is unconfirmed, and Aider takes servers on the command line — so the install prints their entry for you to paste. ide/README.md has the full table, with a README per harness.
Linking
A machine links once, and the link is the same one the Zero engine uses: both read and write session.json in the OS config dir (~/.config/zero/session.json; %APPDATA%\zero\session.json on Windows; mode 0600 off Windows). Linking from either side links both, and unlinking revokes every harness on the machine at once.
npx -y @origozero/zeromind link # device code, approved in the browser
npx -y @origozero/zeromind link --username # pre-fill the approval page's