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
Zed
Adds https://aigamelabs.net/mcp as a remote context server in Zed settings. With no Authorization header configured, Zed prompts the standard MCP OAuth flow, and the Zed Agent discovers skills from the project .agents/skills/ folder.
Step 1 · Tools
Connect the MCP server
- Open Settings > AI > MCP Servers, click "Add Server" and choose "Add Remote Server", or open the settings file with the "zed: open settings file" action and merge the aigamelabs entry below under "context_servers".
- Because the entry has no Authorization header, Zed prompts you to authenticate using the standard MCP OAuth flow — complete the Google sign-in and consent to games:read / games:write (plus optional offline_access) in the browser.
- Check the indicator dot next to the server in Settings > AI > MCP Servers: green with the "Server is active" tooltip means connected.
- Tool calls are confirmed by default (agent.tool_permissions.default = "confirm"); per-tool rules use keys like "mcp:aigamelabs:add_game".
Choose the example for your platform and merge the aigamelabs entry into the existing configuration. Keep unrelated servers and settings.
Merge into the Zed settings file (zed: open settings file)
settings.json{
"context_servers": {
"aigamelabs": {
"url": "https://aigamelabs.net/mcp"
}
}
}- Zed currently supports the MCP Tools and Prompts features only (plus tool-list change notifications) — resources, roots and elicitation are not part of its documented support.
- The extension gallery route ("Install from Extensions") only covers packaged servers; aigamelabs is a custom remote server, so the settings entry is the documented path.
- On Zed versions below v0.224.0 tool approval is controlled by agent.always_allow_tool_actions instead of agent.tool_permissions.default.
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 — Zed loads project skills from <worktree>/.agents/skills/ (and ~/.agents/skills/ for global).
- Project-local skills only load from trusted worktrees: grant trust to the freshly cloned project or the skill stays out of the catalog. Skills must sit directly under the skills root — no nesting.
- Skills hot-reload; invoke with /aigamelabs-game-publishing or @skill in the message editor, or let the agent call it autonomously (it asks allow/deny like any tool).
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.