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

LibreChat

Native MCP + OAuthNative agent skill

Self-hosted, multi-user chat platform. Native Streamable HTTP MCP with per-user OAuth (DCR + PKCE), plus native SKILL.md Skills uploaded in the UI or shipped from disk.

Step 1 · Tools

Connect the MCP server

  1. Add the server under the top-level mcpServers key in librechat.yaml (requires a restart), or create it in the MCP Settings panel from the right sidebar (no restart needed).
  2. Use the merge fragment below with server key aigamelabs. requiresOAuth: true marks the server as OAuth-protected and startup: false keeps LibreChat from connecting at boot before anyone has signed in.
  3. Do not add an oauth block with client_id/client_secret: per the documented schema, when no client id and secret are provided LibreChat uses OAuth discovery with Dynamic Client Registration (DCR), which is what this server expects. The oauth block also documents code_challenge_methods_supported (S256 supported) if endpoints ever need pinning.
  4. Each user authenticates for themselves: click the aigamelabs entry in the MCP dropdown in chat (or open it in the MCP Settings panel) and complete the Google login + consent screen in the browser tab that opens.
  5. Confirm the status icon shows the green Connected gear; users can also enable the server per agent via Agent Builder → Add tools → MCP and pick individual tools.

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

librechat.yaml — merge into the existing top-level mcpServers key

librechat.yaml
mcpServers:
  aigamelabs:
    type: streamable-http
    url: https://aigamelabs.net/mcp
    requiresOAuth: true
    startup: false
    timeout: 60000
    initTimeout: 150000

Before you connect
  • Multi-user safe: LibreChat documents that each user gets their own isolated MCP connection, and each user completes their own OAuth flow via ${DOMAIN_SERVER}/api/mcp/aigamelabs/oauth/callback — tokens are per user, not shared.
  • DCR registers the callback automatically. Only if you deliberately pin a static client_id/client_secret in an oauth block must you register that exact callback URL with the provider first.
  • Keep this server OAuth-only: when an API key is configured (UI-created servers or customUserVars), LibreChat treats it as API-key authenticated and skips OAuth auto-detection.

Step 2 · Workflow

Add the publishing skill

  1. Download the skill file from https://aigamelabs.net/mcp/skills/SKILL.md (raw Markdown with name/description frontmatter).
  2. Upload path (admin): open the Skills panel from the side panel, press +, and choose Upload a skill — LibreChat accepts a .md, .zip, or .skill containing a SKILL.md (a .zip must hold SKILL.md at its root or exactly one folder deep, e.g. aigamelabs-game-publishing/SKILL.md).
  3. Deployment path: place it as skill/aigamelabs-game-publishing/SKILL.md under DEPLOYMENT_SKILLS_DIR (defaults to ./skill at the project root) and restart LibreChat; deployment skills are read-only.
  4. The skills agent capability is on by default: invoke the skill by typing $ in the message box, or let the model load it on its own from the frontmatter description.

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='skill/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.