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

Roo Code

OAuth bridge requiredNative agent skill

Open-source VS Code coding agent. Streamable HTTP remote MCP is supported, but Roo documents only static header auth — OAuth needs the labeled mcp-remote bridge. Native SKILL.md skills live in .roo/skills/.

Step 1 · Tools

Connect the MCP server

  1. Install Node.js 18+ (the bridge runs via npx), then create .roo/mcp.json in the project root — or open it from the MCP panel (servers icon in the Roo Code pane) with Edit Project MCP.
  2. Merge the fragment below: the aigamelabs entry is a local stdio command that mcp-remote bridges to https://aigamelabs.net/mcp.
  3. Connect: mcp-remote opens the aigamelabs sign-in in your browser (Google login + consent for games:read, games:write, optional offline_access) and caches tokens under ~/.mcp-auth; afterwards the server connects on start.
  4. Verify the aigamelabs server appears in the MCP panel with its tools listed; alwaysAllow is left empty so tool calls keep asking for approval.

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

.roo/mcp.json — macOS/Linux, project-level (global alternative: mcp_settings.json via Edit Global MCP)

.roo/mcp.json
{
  "mcpServers": {
    "aigamelabs": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://aigamelabs.net/mcp"]
    }
  }
}

.roo/mcp.json — Windows (cmd wrapper per Roo docs for npx commands)

.roo/mcp.json
{
  "mcpServers": {
    "aigamelabs": {
      "command": "cmd",
      "args": ["/c", "npx", "-y", "mcp-remote", "https://aigamelabs.net/mcp"]
    }
  }
}

One-off login / connectivity check (runs the full OAuth flow and lists tools)

npx -p mcp-remote@latest mcp-remote-client https://aigamelabs.net/mcp

Before you connect
  • Roo Code has no documented native OAuth for remote MCP servers (current docs cover static headers and env-token injection only), so this profile uses the explicitly labeled third-party mcp-remote stdio bridge: a locally run Node package that performs MCP OAuth discovery with DCR + PKCE and caches tokens in ~/.mcp-auth. Revisit if Roo documents a native flow.
  • mcp-remote registers a loopback HTTP callback (localhost/127.0.0.1) — the aigamelabs authorization server infers a native application_type for such registrations, which is exactly this pattern. Do not repoint the callback at HTTPS web URLs.
  • Do not add an Authorization header manually: there is no shared API key, and the bridge obtains the per-user access token through OAuth.

Step 2 · Workflow

Add the publishing skill

  1. Download https://aigamelabs.net/mcp/skills/SKILL.md and save it as SKILL.md inside .roo/skills/aigamelabs-game-publishing/ — the frontmatter name must match the directory name (1–64 chars, lowercase letters/numbers/hyphens).
  2. Roo indexes skills at startup and watches SKILL.md files for changes, so no registration or restart is needed.
  3. Trigger by making a request that matches the description, or explicitly ask Roo to use the aigamelabs-game-publishing skill; Roo loads the full SKILL.md on demand.
  4. Cross-agent alternative documented by Roo: .agents/skills/aigamelabs-game-publishing/ — .roo/ paths take precedence over .agents/ paths at the same level.

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='.roo/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

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.