MCP server for AI agents

HELIX expects most worlds to be built by AI agents. The MCP server (@helix/mcp) gives an agent a structured, typed interface to the platform — discovery, validation, and publishing as callable tools — instead of scraping a CLI's stdout.

What it exposes

• Discovery — list available systems, abilities, templates, and package manifests so the agent builds on what already exists instead of reinventing it.
• Validation — check a world against the manifest schema and platform rules before publishing.
• Publishing — create builds and publish worlds.
• Docs — read these docs as structured Markdown (the same content behind /llms.txt).

Connect it

Point your agent host at the server (example for a Claude/Cursor-style MCP config):

{
  "mcpServers": {
    "helix": {
      "command": "npx",
      "args": ["-y", "@helix/mcp"]
    }
  }
}

Why agents like these docs

These docs are built to be machine-readable from day one:

• Every page is available as clean Markdown (the Copy Markdown button, and content routes).
• /llms.txt is a structured index of the whole site.
• /llms-full.txt is the entire corpus in one file for context windows.
• Every parameter and error is typed and described — what's obvious to a human reader is spelled out for an LLM.

Together with the MCP server, an agent can read the docs, scaffold a world, validate it, and publish it without a human in the loop.