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

Claude Code

Native MCP + OAuthNative agent skill

Anthropic's terminal coding agent. Adds remote Streamable HTTP MCP servers with OAuth browser login and loads Agent Skills from .claude/skills/<name>/SKILL.md.

Step 1 · Tools

Connect the MCP server

  1. Add the remote server: claude mcp add --transport http aigamelabs https://aigamelabs.net/mcp (local scope by default, stored in ~/.claude.json for the current directory).
  2. Run /mcp inside Claude Code and follow the browser login flow — aigamelabs uses OAuth 2.1 dynamic client registration with PKCE, so no --client-id/--client-secret or Authorization header is needed. claude mcp login aigamelabs starts the same flow from the shell.
  3. Verify with claude mcp get aigamelabs (shows transport and OAuth status) or /mcp in the session.
  4. For team sharing use project scope instead: claude mcp add --transport http --scope project aigamelabs https://aigamelabs.net/mcp, which writes .mcp.json at the repo root (each user approves it once). --scope user makes it available across all your projects.

Choose the example for your platform and merge the aigamelabs entry into the existing configuration. Keep unrelated servers and settings.

Add and authenticate (shell)

claude mcp add --transport http aigamelabs https://aigamelabs.net/mcp
claude mcp login aigamelabs   # or run /mcp in the session and sign in

Project-scope .mcp.json entry

.mcp.json
{
  "mcpServers": {
    "aigamelabs": {
      "type": "http",
      "url": "https://aigamelabs.net/mcp"
    }
  }
}

Before you connect
  • In JSON configs the type field is mandatory: an entry with url but no type is read as a stdio server and skipped with an error; streamable-http is accepted as an alias for http.
  • Project-scoped servers require one-time user approval before Claude Code loads them in interactive sessions.
  • No manually supplied bearer token is needed: browser OAuth via /mcp lets the client obtain and refresh its own token automatically.

Step 2 · Workflow

Add the publishing skill

  1. Save the skill to .claude/skills/aigamelabs-game-publishing/SKILL.md (project — commit it so the whole team gets it) or ~/.claude/skills/aigamelabs-game-publishing/SKILL.md (personal, all projects on this machine).
  2. Claude Code lists it automatically: it runs when a task matches the frontmatter description, or invoke it directly with /aigamelabs-game-publishing.
  3. Sessions watch the standard skills directories and pick up changes live; if you created the folder after the session started, run /reload-skills.

Run from your project root. This downloads Markdown only, does not execute it, and will not overwrite an existing skill. Review the file before using it.

Download the skill with Bash

skill_dir='.claude/skills/aigamelabs-game-publishing'
mkdir -p "$skill_dir"
if [ -e "$skill_dir/SKILL.md" ]; then
  printf '%s\n' 'SKILL.md already exists. Review or back it up before replacing it.'
else
  curl --fail --show-error --location 'https://aigamelabs.net/mcp/skills/SKILL.md' --output "$skill_dir/SKILL.md"
fi

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.