Connect Agents · MCP + agent skills

Connect your AI client.

Give your agent the tools to manage your games, and the instructions to package and publish them. Choose your client for its exact configuration.

MCP server

The connection that reads and changes your game entries.

MCP server URL

https://aigamelabs.net/mcp

Streamable HTTP · OAuth sign-in and consent · no shared API key

Publishing skill

The workflow for metadata, artwork, WebGL packaging, Unity exports and Unreal limitations.

Publishing skill URL

https://aigamelabs.net/mcp/skills/SKILL.md

One SKILL.md file · installing it does not authorize an agent

29 client guides

Choose your client

The configuration and skill instructions below change with this selection.
For clients with a documented project skill directory.

Client configuration

Cherry Studio

OAuth bridge requiredNative agent skill

Cherry Studio has a built-in OAuth client for remote MCP servers, but it completes sign-in via its cherrystudio://oauth deep link, which this server's strict native-callback validation rejects (requires a reverse-domain scheme with no authority), so the tools do NOT run natively against this endpoint. Use the documented mcp-remote stdio bridge, which performs the full OAuth 2.1 flow over a loopback callback this server accepts. Skills are unaffected: Cherry Studio's native agent-skills system watches a managed skills directory — drop the skill folder in and it registers automatically.

Step 1 · Tools

Connect the MCP server

  1. Prerequisite: the bridge runs as a local process via npx, so Node.js must be installed. Everything else happens in Cherry Studio's Settings > "MCP Servers" (中文文档: 设置 > `MCP 服务器`) > "Add Server" ("添加服务器") — the STDIO type uses plain Command and Args fields, no config file.
  2. Do the sign-in once from a terminal first: run npx -y mcp-remote https://aigamelabs.net/mcp, complete the Google sign-in and consent (games:read, games:write) in the browser window it opens, then stop it with Ctrl+C. mcp-remote performs the OAuth 2.1 flow itself (dynamic client registration, PKCE, loopback callback), which this server accepts.
  3. In the Add Server dialog fill in: Name aigamelabs, Type STDIO, Command npx, Args (one per line): -y, mcp-remote, https://aigamelabs.net/mcp — then save.
  4. Enable the aigamelabs server in the chat input's MCP tools. Cherry Studio launches the bridge as a local process; if no cached authorization exists yet, mcp-remote opens the browser for the Google sign-in before tools appear.

First-time login / connectivity check (terminal, outside Cherry Studio)

# Completes the OAuth sign-in once; Ctrl+C after the browser flow succeeds.
npx -y mcp-remote https://aigamelabs.net/mcp

MCP server values (Settings > MCP Servers > Add Server, type STDIO)

Name: aigamelabs
Type: STDIO
Command: npx
Args: -y  mcp-remote  https://aigamelabs.net/mcp   (one argument per line)

Before you connect
  • Why a bridge: Cherry Studio's cherrystudio://oauth callback fails this server's private-use URI rules: its scheme is not reverse-domain and it contains an authority. No documented Cherry setting changes that callback. Native HTTP loopback callbacks are accepted, which is the flow mcp-remote uses.
  • MCP servers and skills can execute code with broad permissions — only enable servers and skills you trust, and review tool approvals in chat.
  • mcp-remote is an independent third-party npm package run on your machine (local Node.js required); it caches OAuth state such as debug logs under ~/.mcp-auth in your user profile. After changing the server entry, re-save it in Settings > MCP Servers so the new arguments take effect.

Step 2 · Workflow

Add the publishing skill

  1. Cherry Studio keeps a managed skills directory that it syncs with a catalog automatically — there is no register step and no ZIP import needed; a folder containing SKILL.md is enough.
  2. Locate the managed directory by running `echo "$CHERRY_STUDIO_SKILLS_DIR"` (Cherry's bundled skill docs resolve it this way, e.g. via the agent's terminal).
  3. Create a lowercase-hyphenated folder aigamelabs-game-publishing inside it and save the Markdown from https://aigamelabs.net/mcp/skills/SKILL.md as SKILL.md within it — the folder name must match the skill's frontmatter name, which it does.
  4. The next skills sync registers it in the catalog and lists it in the app; enable it there. The raw URL is Markdown, not a prebuilt .skill package — if you already downloaded a .skill installer, it was built by someone else, not shipped by this server.
  5. Skills apply in Cherry Studio's agent mode and run with the agent's permissions; invocation and confirmations follow the active permission mode.

Install into the managed skills directory (bash)

: "${CHERRY_STUDIO_SKILLS_DIR:?Run in the Cherry agent terminal with its managed skills directory configured}"
mkdir -p "$CHERRY_STUDIO_SKILLS_DIR/aigamelabs-game-publishing"
curl --fail --show-error --location -o "$CHERRY_STUDIO_SKILLS_DIR/aigamelabs-game-publishing/SKILL.md" https://aigamelabs.net/mcp/skills/SKILL.md
# Cherry Studio registers the folder on its next skills sync; enable it in the app.

Download SKILL.mdRead the skill

After setup

Try a read-only first request

First prompt for your agent

Read the aigamelabs-game-publishing skill, then use AIGameLabs list_games to show my game entries. Do not create, publish or remove anything yet.

Once the connection works, the agent can use add_game, update_game and remove_game, plus build, artwork and release tools. Removing a game archives it and revokes delivery; publishing still requires an approved release. Publication is manual by default; explicitly opt in when freezing a release only if you want that exact snapshot to publish automatically on approval.

Your approval remains in control

Sign in on aigamelabs.net and inspect the client's name, callback and requested scopes. Grant games:read for reading and games:write for changes; offline_access permits refresh tokens. Never paste browser cookies, Google credentials or an access token into shared configuration. Creator access, upload limits and human review still apply.

Manage or disconnect an agent in Settings → Connected agents. A recent sign-in is required to disconnect. Review game metadata and ask for confirmation before destructive actions, rights attestations or automatic-publication opt-ins.

Connection help

The URL shows “missing authorization header”

That is the expected OAuth challenge, not a page to sign in on. Add the URL in your client's MCP settings, then use its Connect or Authenticate action to open the consent flow.

The sign-in link expired or the callback was rejected

Reconnect from the MCP client to request a fresh authorization link. Do not bookmark a signed consent URL. Older clients that omit the native application type are inferred from loopback or private-use callbacks; explicitly configured web clients must use HTTPS callbacks. Unsafe callbacks remain rejected.

The client has HTTP support but cannot authenticate

HTTP transport alone is insufficient: this server requires OAuth. Follow the selected guide's native OAuth or documented bridge instructions. A stdio bridge runs locally and stores its own authorization state; do not share that cache or use one person's login for a multi-user server. This server uses dynamic client registration, not URL-based client metadata discovery.

The skill is not listed

Keep the exact filename SKILL.md inside the directory shown for your client, preserve its frontmatter, then reload or start a new session as that client's instructions require. A reference-only app will not show it as an installed native skill.

A game operation is denied after connection

OAuth grants access only to your own workspaces. Creator enrollment, quotas and human review gates remain in force. Read-only consent cannot authorize writes. Ask for the required scope rather than copying a token into configuration or trying to bypass review.