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

JetBrains AI Assistant

OAuth bridge requiredNative agent skill

Connects https://aigamelabs.net/mcp through the documented mcp-remote stdio bridge under Settings | Tools | AI Assistant | Model Context Protocol (MCP). JetBrains documents no OAuth client for remote MCP servers, so the browser-based OAuth flow is handled by the bridge; skills load from registered local skill directories.

Step 1 · Tools

Connect the MCP server

  1. Go to Settings | Tools | AI Assistant | Model Context Protocol (MCP), click Add, and in the New MCP Server dialog choose the stdio connection type with the JSON configuration below (requires local Node.js — "npx" runs the third-party mcp-remote package).
  2. Click OK, then Apply: AI Assistant starts the bridge and mcp-remote opens a browser for the server OAuth flow (dynamic client registration + PKCE, Google sign-in and consent to games:read / games:write plus optional offline_access).
  3. Watch the Status column until the server connects; click the status icon to review the tool list. Tools become available as "/" commands in the AI Assistant chat.
  4. Set the desired availability in the Level column (global across projects or current project only); stop or restart the server via its checkbox and the Reconnect button.

Paste into the New MCP Server dialog (Settings | Tools | AI Assistant | Model Context Protocol (MCP))

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

Before you connect
  • AI Assistant documents the STDIO and Streamable HTTP transports with a plain "url" for remote servers, but its help page documents no OAuth or header authentication for them — a direct url entry cannot sign in to this OAuth-protected server, which is why the mcp-remote stdio bridge is used.
  • mcp-remote is a third-party open-source proxy (MIT) that runs on your machine via npx and handles MCP OAuth (DCR, PKCE, loopback redirect); when a JetBrains release documents native MCP OAuth, switch back to a direct "url" entry and remove the bridge.
  • AI Assistant can also expose your IDE as an MCP server (Settings | Tools | MCP Server) — that is the reverse direction and unrelated to adding aigamelabs.

Step 2 · Workflow

Add the publishing skill

  1. Download the skill as raw Markdown from https://aigamelabs.net/mcp/skills/SKILL.md and save it as .agents/skills/aigamelabs-game-publishing/SKILL.md in the project.
  2. Go to Settings | Tools | AI Assistant | Skills, click Skills Settings > Manage Skill Directories, and add the project .agents/skills folder under Project — JetBrains detects skills from directories you register rather than a fixed location.
  3. Skills are used by the Claude Agent and Codex agents inside the IDE; invoke with $aigamelabs-game-publishing in chat or let the agent activate it when relevant.
  4. The "Manage External Registries" option is for GitHub-hosted skill collections; the aigamelabs skill is a single raw Markdown file, so use the local directory route.

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

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.