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/mcpStreamable 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.mdOne SKILL.md file · installing it does not authorize an agent
29 client guides
Choose your client
Client configuration
Jan
Personal desktop app. Native OAuth sign-in for remote Streamable HTTP MCP servers: Jan discovers provider metadata, registers dynamically (DCR), and completes authorization-code + PKCE against a loopback redirect. No stable skill loader — SKILL.md support lives in the separate Jan Agent CLI.
Step 1 · Tools
Connect the MCP server
- Open Settings → MCP Servers → + Add MCP Server.
- Set Transport to HTTP (Streamable HTTP) and URL to https://aigamelabs.net/mcp; leave Command/Args/Env empty.
- Enable the server, then run its Auth action: Sign in opens your browser and Jan discovers the provider metadata, registers itself dynamically, and completes the authorization-code flow with PKCE against a loopback redirect — finish the Google login + consent screen there (the wait times out after five minutes).
- Tokens are stored in mcp_oauth.json in the Jan data folder (owner-only permissions, never inside mcp_config.json) and refreshed automatically before expiry; Clear authentication signs the server out.
- When the server shows the green active indicator its tools are live; individual tool calls ask for approval unless "Allow All MCP Tool Permissions" is enabled globally.
Settings → MCP Servers → Add MCP Server — field values
Transport: HTTP (Streamable HTTP)
URL: https://aigamelabs.net/mcp
Command: (empty)
Args: (empty)
Env: (empty)
Auth: leave unset — use the server's "Sign in" action (OAuth: discovery + dynamic registration + PKCE)
→ Toggle the server on, then Sign in- Jan is a single-user desktop app: the OAuth tokens it stores are your own Google-backed grant, kept per machine — this profile does not describe multi-user hosting.
- Do not set a manual Authorization header on this server — Jan uses that credential as-is and never attempts OAuth.
- Changing a server URL invalidates its stored tokens rather than reusing them, and removing the server clears them.
Step 2 · Workflow
Add the publishing skill
- Stable Jan Desktop has no documented SKILL.md loader. Jan's native SKILL.md support is in Jan Agent, the separate command-line agent (user scope ~/.jan/skills/<name>/SKILL.md, project scope per project; /skills lists them and /reload skills refreshes the popup). Jan Desktop's experimental Cowork surface (nightly only) keeps a different store and does not read ~/.jan/skills.
- If you use Jan Agent, download the skill into ~/.jan/skills/aigamelabs-game-publishing/SKILL.md and run /reload skills; invoke it with /aigamelabs-game-publishing or let the agent load it from the description.
- On Jan Desktop only, treat the downloaded SKILL.md as reference reading — nothing auto-loads it. The aigamelabs MCP tools still work once the server is connected and signed in.
Jan Agent CLI only — install into the user skill folder (not stable Jan Desktop)
mkdir -p ~/.jan/skills/aigamelabs-game-publishing
curl -fL -o ~/.jan/skills/aigamelabs-game-publishing/SKILL.md https://aigamelabs.net/mcp/skills/SKILL.md
# Jan Agent only: run /reload skills afterwards (or /skills to list)Reading or attaching the Markdown is a workflow reference, not automatic native skill discovery. It does not connect MCP or grant account access.
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.
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.