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
VS Code (GitHub Copilot)
Defines https://aigamelabs.net/mcp in .vscode/mcp.json (VS Code format) or .mcp.json (portable format). VS Code connects over the HTTP Stream transport and completes the OAuth flow in a browser, and discovers Agent Skills from .agents/skills/.
Step 1 · Tools
Connect the MCP server
- Run "MCP: Open Workspace Folder MCP Configuration" from the Command Palette (⇧⌘P / Ctrl+Shift+P) to create .vscode/mcp.json, or create .mcp.json at the repository root for the portable format, then merge the aigamelabs entry below.
- When the server first starts, VS Code shows an MCP server trust dialog (workspace servers inherit Workspace Trust) — review and allow it, or tools will not load.
- The server requires OAuth: when VS Code connects it performs the MCP OAuth flow with dynamic client registration and opens a browser for Google sign-in and consent to games:read / games:write (plus optional offline_access). The documented optional "oauth" block with a pre-registered clientId is only for authorization servers without DCR — aigamelabs supports DCR, so leave it out.
- Check state and logs with "MCP: List Servers" → select aigamelabs → Show Output; use "MCP: Reset Trust" only if you rejected the server earlier.
Choose the example for your platform and merge the aigamelabs entry into the existing configuration. Keep unrelated servers and settings.
VS Code format — merge into .vscode/mcp.json
.vscode/mcp.json{
"servers": {
"aigamelabs": {
"type": "http",
"url": "https://aigamelabs.net/mcp"
}
}
}Portable format — merge into .mcp.json (also read by Copilot CLI and Agent Host)
.mcp.json{
"mcpServers": {
"aigamelabs": {
"type": "http",
"url": "https://aigamelabs.net/mcp"
}
}
}- "type": "http" uses the HTTP Stream transport with SSE fallback, which matches this server; "type": "sse" exists only for legacy SSE-only endpoints.
- The portable formats (.mcp.json in the workspace, ~/.copilot/mcp-config.json for the user) are read natively by Agent Host and GitHub Copilot CLI, so the same entry carries over to those surfaces.
- The chat.mcp.discovery.enabled setting can import servers from Cursor and Windsurf configs — disable it if you configure aigamelabs by hand to avoid duplicates.
Step 2 · Workflow
Add the publishing skill
- 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; the documented project skill locations are .github/skills/, .claude/skills/ and .agents/skills/.
- Discovery alone does not guarantee invocation: type /skills (or open Configure Chat > Skills) to confirm the skill is listed.
- Invoke it with /aigamelabs-game-publishing in chat, or ask for a publishing task — Copilot loads skills whose description matches the request.
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"
fiAfter 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.