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

Kilo Code

Native MCP + OAuthNative agent skill

VS Code extension built on the Kilo CLI. Remote MCP with automatic OAuth 2.0 for OAuth-capable servers, configured in kilo.jsonc; native Agent Skills from .kilo/skills/ (or .agents/skills/) with slash-command invocation.

Step 1 · Tools

Connect the MCP server

  1. In the Kilo Code settings open Agent Behaviour → MCP Servers → Add Server → Remote (HTTP) and enter https://aigamelabs.net/mcp, or edit the config file directly.
  2. Merge the fragment below into the project config .kilo/kilo.jsonc (project config overrides global); use ~/.config/kilo/kilo.jsonc instead to enable the server in every workspace.
  3. Connect: Kilo Code automatically starts the OAuth flow when the remote server supports it — complete the aigamelabs Google login + consent (games:read, games:write, optional offline_access) in the browser tab that opens.
  4. Verify the tools appear. Tool calls surface in the permission dock; Approve Always saves an allow rule (permission keys look like aigamelabs_list_games) to the config.

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

kilo.jsonc — merge into the existing top-level mcp key

.kilo/kilo.jsonc
{
  "mcp": {
    "aigamelabs": {
      "type": "remote",
      "url": "https://aigamelabs.net/mcp",
      "enabled": true
    }
  }
}

Before you connect
  • Kilo Code tries StreamableHTTP first and falls back to SSE automatically, so no transport flag is needed for this stateless Streamable HTTP server.
  • OAuth starts automatically for remote servers; "oauth": false would disable it, so leave that key unset for aigamelabs. Do not supply an API key or bearer token manually; Kilo manages its OAuth token.
  • MCP servers live under the top-level mcp key of kilo.jsonc (JSONC), not a separate mcp_settings-style file; the Settings UI writes the same keys.

Step 2 · Workflow

Add the publishing skill

  1. Download https://aigamelabs.net/mcp/skills/SKILL.md and save it as SKILL.md inside .kilo/skills/aigamelabs-game-publishing/ — the name must match the directory name.
  2. Skills are scanned at the start of each session (in the VS Code extension, when it connects to the CLI server); run /reload or start a new session to pick the skill up.
  3. Invoke via the / menu — every loaded skill is listed as a slash command (/aigamelabs-game-publishing) — or rely on description matching.
  4. Alternatives documented by Kilo: .agents/skills/ is loaded by default without config, and skills.paths / skills.urls can add locations in kilo.jsonc. The remote URL manifest does not apply here: aigamelabs publishes a single SKILL.md, not an index.json directory.

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='.kilo/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.