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

OpenAI Codex

Native MCP + OAuthNative agent skill

OpenAI's coding agent — CLI, IDE extension, and ChatGPT desktop app share one config.toml. Streamable HTTP MCP with OAuth (DCR/CIMD) and Agent Skills in .agents/skills/.

Step 1 · Tools

Connect the MCP server

  1. Add the server: codex mcp add aigamelabs --url https://aigamelabs.net/mcp — this writes [mcp_servers.aigamelabs] to ~/.codex/config.toml.
  2. Log in: codex mcp login aigamelabs. Codex performs OAuth dynamic client registration, so no client ID is needed; codex mcp list shows configured servers and login status.
  3. In the Codex TUI, /mcp shows connected servers. The IDE extension and ChatGPT desktop app read the same config: after adding a server there, select Restart (app) or Restart extension (IDE), then Authenticate when the server list flags OAuth.
  4. Project-scoped configuration goes in .codex/config.toml (trusted projects only) if you want the server limited to one repository.

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

Add and log in (shell)

codex mcp add aigamelabs --url https://aigamelabs.net/mcp
codex mcp login aigamelabs
codex mcp list

config.toml entry

~/.codex/config.toml
[mcp_servers.aigamelabs]
url = "https://aigamelabs.net/mcp"

Before you connect
  • Auth defaults to oauth for HTTP servers — do not set bearer_token_env_var or http_headers for aigamelabs; the OAuth login supplies and refreshes the token.
  • Codex also supports CIMD and pre-registered clients (--oauth-client-id, --oauth-client-registration AUTO|CIMD|DCR), but plain login uses DCR against this server. If a callback must be registered with the provider, register exactly the callback URL codex mcp add displays (http://127.0.0.1/callback, or with a server-specific callback ID when the server does not advertise issuer support).
  • Per-server options such as enabled, startup_timeout_sec, tool_timeout_sec, and enabled_tools/disabled_tools live in the same [mcp_servers.aigamelabs] table.

Step 2 · Workflow

Add the publishing skill

  1. Save the skill to .agents/skills/aigamelabs-game-publishing/SKILL.md — Codex scans .agents/skills/ in every directory from the current working directory up to the repository root, plus ~/.agents/skills/ for user-wide skills (the older $CODEX_HOME/skills location still works for backward compatibility).
  2. Invoke with $aigamelabs-game-publishing in the prompt or pick it from /skills; Codex also activates it implicitly when the task matches the description.
  3. Codex detects newly added skills automatically; restart Codex if it does not appear. A skill can be disabled without deleting it via a [[skills.config]] entry (path + enabled = false) in ~/.codex/config.toml, then restart.

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='.agents/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.