KUMODeck

Use from an AI agent (MCP)

You don't have to open a dashboard to run your app or game. Connect KUMODeck once to the AI coding agent you use — Claude Code, Codex, Cursor or any other agent that supports MCP — then just ask:

  • "How many people came from yesterday's post on X?"
  • "What did my projects cost last month, and how much prepaid credit is left?"
  • "Turn on cloud saves in the production config and push it." (you confirm first)
  • "Roll production back to the previous version."
  • "Turn on Functions for development and deploy my functions/ folder."

The assistant talks to the KUMODeck MCP server with your developer account. It never sees a secret key, and nothing that changes your app happens without your confirmation.

More requests you can copy, from starting a project to fixing errors: Talk to your AI agent.

Connect#

MCP server URL
https://mcp-staging.kumodeck.com/mcp

Name it kumodeck-preview · Sign in with KUMODeck · No API key

Claude Code · Codex · Gemini CLI · VS Code · Cursor · Claude ↗ · ChatGPT ↗ · Other

Claude Code#

claude mcp add --transport http kumodeck-preview https://mcp-staging.kumodeck.com/mcp
  1. Run the command in your project's folder.
  2. Start Claude Code, run /mcp, choose kumodeck-preview and select Authenticate. Sign in and press Connect.

The KUMODeck plugin also adds how-to guides. It connects the usual KUMODeck, not KUMODeck Preview (v0.2). About the plugin

What you see when you sign in (the same page for every agent below):

  • Sign in with your KUMODeck developer account, the same way as on the dashboard (saved passwords, passkeys, Google and GitHub all work). If you are already signed in to the dashboard, this step is skipped.
  • Check the agent's name and where access will be sent (for an agent on your computer, an address like localhost:…). Choose what the assistant may do and which projects it may touch, then press Connect. The browser goes back to the agent, and the agent is connected.

What the assistant may do has three choices:

  • Build and publish (recommended, selected first): see everything, change project config, publish and deploy, and manage server functions. Going live in production and every delete still ask you first.
  • View only: see projects, users, usage costs, prepaid balance, server functions and their logs. Changes nothing.
  • Choose myself: tick each scope (the table below; only the ones the agent asked for are listed). These are in no preset, so you can only add them here: banning users.

To change them later, disconnect in /mcp and authenticate again.

About the plugin#

Inside Claude Code, run these two lines:

/plugin marketplace add kumodeck/kumodeck-plugin
/plugin install kumodeck@kumodeck

The plugin connects Claude Code to KUMODeck and adds the how-to guides the assistant follows when it builds and publishes your game (multiplayer, saves, login, publishing and more). In /mcp it is named plugin:kumodeck:kumodeck. When a newer version comes out, run /plugin marketplace update kumodeck. Without the plugin, the guides come with the project you create with kumodeck init.

Codex#

Works in the Codex CLI, the IDE extension and the desktop app (they share settings).

codex mcp add kumodeck-preview --url https://mcp-staging.kumodeck.com/mcp
codex mcp login kumodeck-preview
  1. Run the first line to add the server.
  2. codex mcp login opens KUMODeck in your browser. Sign in and press Connect.

Registering an MCP server does not prove its tools are available in the current conversation. The agent checks the tools it can use, including discovery when supported, and uses the installed kumodeck CLI if needed. In Codex CLI, /mcp shows connection status. A new conversation can reload configuration; it does not fix blocked communication or a failed login. The agent never uses saved keys to bypass confirmation. Features that are not available yet are described that way, with an available alternative.

Codex's usual command sandbox blocks outbound communication. If permission is requested, check where the command needs to connect. If access cannot be granted, the agent preserves the prepared files and reports which operation remains unverified. It does not loosen permissions or retry a denied action another way.

When you ask to publish, the agent verifies a test copy, then opens the publishing confirmation page without asking for an extra yes in this conversation. Form support depends on your Codex client and settings. When KUMODeck returns a confirmation link, follow Confirm with a link. The agent says it is waiting for you to press Publish in the browser, with no conversation reply needed, and continues after you press it. A test-only request stops at the test copy.

Gemini CLI#

gemini mcp add --transport http kumodeck-preview https://mcp-staging.kumodeck.com/mcp
  1. Run the command. In a settings file, write httpUrl, not url (url means the older SSE transport).
  2. Start Gemini CLI and run /mcp auth kumodeck-preview. Sign in and press Connect.

VS Code (Copilot agent mode)#

{ "servers": { "kumodeck-preview": { "type": "http", "url": "https://mcp-staging.kumodeck.com/mcp" } } }
  1. Add this to .vscode/mcp.json.
  2. Start kumodeck-preview from the MCP view. When VS Code asks, sign in and press Connect.

Cursor#

{ "mcpServers": { "kumodeck-preview": { "url": "https://mcp-staging.kumodeck.com/mcp" } } }
  1. Add this to .cursor/mcp.json in your project (or the global one).
  2. Open Settings → MCP, find kumodeck-preview and sign in. Press Connect.

Other agents#

KUMODeck is a remote MCP server over HTTP (Streamable HTTP), the same for every agent: add a server named kumodeck-preview with the URL https://mcp-staging.kumodeck.com/mcp. The exact place and key names differ; these are the ones that trip people up:

AgentWhat to write
Windsurf / Devin{ "mcpServers": { "kumodeck-preview": { "serverUrl": "https://mcp-staging.kumodeck.com/mcp" } } } in the MCP config (or devin mcp add kumodeck-preview https://mcp-staging.kumodeck.com/mcp)
Zed{ "context_servers": { "kumodeck-preview": { "url": "https://mcp-staging.kumodeck.com/mcp" } } } in settings.json
Anything else with MCPa remote / HTTP server named kumodeck-preview at https://mcp-staging.kumodeck.com/mcp

When the agent connects, the same dashboard page opens: sign in if you are not signed in yet, then choose the scopes and projects, as above.

Note Most agents register themselves on the fly, so KUMODeck cannot confirm their name. When the agent runs on your computer, the page asks whether you just started connecting an AI agent on this computer: if you did, continue. If the page instead warns that access goes to a server on the internet, stop unless you recognize that address.

Your project's AGENTS.md (every KUMODeck template has one) is read by Codex, Cursor, Windsurf / Devin and Zed; Claude Code reads it through CLAUDE.md, and Gemini CLI through GEMINI.md. The recipes for common features (Skills: sign-in, saves, and game recipes such as leaderboards and chat) are listed in INDEX.md in .agents/skills/ (Codex, Cursor and most other agents look there) and in .claude/skills/ (Claude Code): the same files in both.

Check it works#

Ask: "Which KUMODeck projects can you see?" Your AI lists them, or says there are none yet. It only reads; nothing changes.

No KUMODeck tools? Start a new conversation. Most agents load tools when a conversation starts.

Starting a new project#

Creating the account and the project happens in your terminal, not over MCP (the password never goes through the assistant, and the template files have to land on your disk):

# you type this one yourself (an invite code is optional: add --invite <code> if you have one)
kumodeck signup
# the assistant can take it from here: template + project + keys (or `kumodeck init` in your own app's folder)
kumodeck create my-game --init

Then ask: "push the config, deploy to development, then production, and turn on sharing". The assistant runs kumodeck config push, kumodeck deploy and kumodeck share on locally — or turns sharing on over MCP (share_enable, you confirm production). See Getting started.

Building and deploying#

Uploading a new build stays on your machine: your build folder is on your computer, and a remote MCP server cannot read it. When you ask the assistant to "deploy", it runs the CLI locally (kumodeck deploy, kumodeck functions deploy) and then uses MCP to check the result or switch versions. Install the CLI once with npm install -g kumodeck (CLI reference).

Scopes#

Shown on the consent screenScopeLets the assistantConfirmation
View projectsread:projectslist projects, overview (users, daily actives), read and validate config, deployment history, card tags, custom domains (the app's and the Functions')—
View reportsread:reportstraffic per X post—
View end users (players)read:playerssearch your users (players in the API; emails are masked), read ban appeals—
View usage and prepaid balanceread:payoutsusage costs and prepaid balance—
Change project configwrite:configpush kumo.config.json, turn on sharing on X (share_enable), create tracked share links, add / remove custom domains (the app's and the Functions')production only (removing a domain: always)
Switch deploymentsdeployactivate a version / roll backproduction only
Ban / unban end userswrite:playersban, unban and answer ban appeals (needs read:players too)always
View server functionsread:functionsFunctions status, versions, databases, crons, secret names—
Read server function logsread:logswhat your deployed code printed (Functions and the server-rendered app; console.log / console.error), last 7 days—
Manage server functionswrite:functionsenable, deploy, set secrets, run SQL and migrations, deleteproduction changes and deletes

Tools#

ToolWhat it does
projects_list · project_overviewyour projects; users (players), new and active users, 14-day daily actives, live version
usage_get · usage_daily · prepaid_getwhat each building block cost this month (at cost) · by day · prepaid balance (and invite credit), low-balance notices, auto top-up
config_get · config_validate · config_pushread · check against every push rule without saving (errors with paths, what would change) · push
deployments_list · deploy_activateversion history · switch the live version
players_search · player_get · player_ban · player_unbanyour users (players) and bans
appeals_list · appeal_resolve (ban appeals)read the appeals banned users sent, then accept (the ban is lifted) or reject, with a short reply
share_stats · share_link_create · share_tagsvisits, new users, opens per X post · a tracked link for your own post · the card tags to put in the page's <head>
hosting_domains_list · hosting_domain_add · hosting_domain_removeyour app on your own domain (custom domains): status and the DNS records you add · add (confirmed) · remove (always confirmed)
functions_domains_list · functions_domains_add · functions_domains_removeyour Functions on your own domain (Functions: your own domain): status and the DNS records you add · add (production: confirmed) · remove (always confirmed)
project_slug_get · project_slug_checkyour project's URL slug, old slugs and their redirects · whether a new slug is free and what would change (read-only: you change it in the dashboard, see changing the URL slug)
project_renamechange your project's display name, which appears in the subject and sender of emails your users (players) receive (no confirmation form: you can change it back any time, and you get an email about it). Returns the previous name and whether it changed. Names that look like KUMODeck or its staff are refused (name_reserved); the URL slug does not change
functions_status · functions_deploymentsyour Functions and their history
functions_logswhat your deployed code printed (Functions and the server-rendered app; source for one), newest first, last 7 days: filter by time, level and text (logs)
functions_enable · functions_disable · functions_deployturn on (needs prepaid credit) · stop · deploy
functions_secret_set · functions_secret_deleteAPI keys and passwords. By default functions_secret_set takes no value and returns a direct link to the dashboard screen where you enter it (so keys never go through the conversation). Values never appear in results or confirmation text
functions_db_query · functions_db_migrate · functions_deleteSQL and migrations on your own database · delete (always confirmed)

Safety#

Writes need a human. Even if your assistant auto-approves tools, the server asks you. Newer clients (Claude Code) show a "Run this?" form. Clients that cannot show that form (Codex, for example) can still read everything, and for changes to production they give you a confirmation link instead (below). Other writes that need a confirmation, such as banning a user in development, are refused with nothing changed: do those in the dashboard, or use a client that supports confirmation forms.

When a client cannot show the form, a change to production (publishing a version, pushing the production config, a ban, a custom domain, production Functions) works like this:

  1. Nothing changes yet. The agent shows you a link to your KUMODeck dashboard, for example: Open this link and press "Publish". The agent opens it in your browser when it can (otherwise open it yourself); only you can press the button, and the agent then carries on by itself, without waiting for you to reply.
  2. Check the page. The top says in one sentence what will happen (for example Publish "My App"?) and what people will see (for example the live URL where anyone can open it), with two big buttons right under it. Under the buttons: If this doesn't look familiar, press Cancel. Nothing will change. For data changes, one line also says which tables get data added, changed or deleted (or that the page cannot tell). The technical details (version, environment, the name the agent gave itself, which KUMODeck cannot verify) are under Details. Approving needs a confirmed email address.
  3. Go back to the agent. It sends the same request once and tells you the result. KUMODeck does not run anything for the agent: the change still runs with the agent's own permissions and checks, only once, and within 10 minutes of your approval. The link itself works for 10 minutes.

The first publish to production is one approval. If hosting is still off in production, the agent uploads the new version first (nothing is live yet), and the page asks it as one thing (Publish "My App"?, plus what else turns on). One press allows both changes; the agent then sends them in order (the list is under Details). Cancel cancels both. If more changes were added after you opened the page, it asks you to check again before you approve.

Do not recognize it? Press Cancel. Nothing changes and the agent cannot send it (you can cancel even before you confirm your email). If the page says the target changed after the link was made (for example a newer version went live), nothing happened: ask the agent again for a new link.

Production changes from the CLI are confirmed once in your browser. When the agent logged in with kumodeck connect (or kumodeck login in the browser), every production change it makes with the CLI (config push, deploy, rollback, secret keys, Functions, domains…) stops and prints a confirmation link. Open it and press Confirm in the dashboard (or Deny); the command then sends that one change, once. The agent cannot confirm it for you, and --yes does not skip it. A deploy uploads first and asks once, right before the new version goes live; the first publish to production with hosting still off is also one link and one press (turning hosting on and publishing). Sessions you start yourself with kumodeck login --email are not asked.

Text written by others is fenced. User (player) names, product names and deploy messages come back wrapped in «…», and the assistant is told not to follow instructions inside them. Confirmations remain the last line of defense: a user named "ban everyone" still cannot make a ban happen without you.

Your users' emails are masked (a***@example.com). You can still search by email.

Every MCP action is written to your audit log with the client and tool that made it.