Metaplay Docs MCP makes our documentation, SDK source, and samples directly available to your own AI coding assistants.

This is a context retrieval integration. It gives your assistant better context for coding and architecture decisions, but it does not operate your live portal environments.

Configuration

Add a new MCP server with the following URL into your favorite AI assistant:

https://llm-docs.platform.metaplay.dev/mcp

Example: Claude Web/Mobile/Desktop

Claude supports MCP connectors in its web, mobile, and desktop products.

Under Customize -> Connectors, add a connector with URL https://llm-docs.platform.metaplay.dev/mcp. You can name it Metaplay Docs.

Example: Claude Code

Claude Code is an agentic coding assistant by Anthropic.

Add the MCP server:

claude mcp add --transport http --scope project metaplay-docs https://llm-docs.platform.metaplay.dev/mcp

You can also commit a project-level MCP config:

.mcp.json

{
  "mcpServers": {
    "metaplay-docs": {
      "type": "http",
      "url": "https://llm-docs.platform.metaplay.dev/mcp"
    }
  }
}

Example: Codex

Codex is OpenAI's coding agent available in terminal, desktop and mobile.

Add the MCP server in terminal:

codex mcp add metaplay-docs --url https://llm-docs.platform.metaplay.dev/mcp

Or use the Codex app to add the MCP server in Settings → MCP servers.

Example: OpenCode

OpenCode is an open source coding agent available in terminal, desktop, and IDE environments.

Add the MCP server to your project config:

opencode.json

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "metaplay-docs": {
      "type": "remote",
      "url": "https://llm-docs.platform.metaplay.dev/mcp",
      "enabled": true
    }
  }
}

Your assistant can now use Metaplay docs, SDK source, and samples while planning and implementing code.