# Model Context Protocol (MCP)

Connect AI agents to Wavedash docs and workflow guidance with the hosted remote MCP server.

Source: https://docs.wavedash.com/mcp

The Wavedash remote MCP server lets AI agents search public Wavedash docs, fetch
engine and SDK guidance, validate pasted `wavedash.toml` content, and explain
the upload and publishing workflow.

## Connect

Use this server URL with any MCP client that supports Streamable HTTP:

```text
https://mcp.wavedash.com/mcp
```

Health/info endpoint:

```text
https://mcp.wavedash.com/
```

The server is unauthenticated because it only exposes public documentation. It
does not access user accounts, private projects, builds, local files, API keys,
or Wavedash account data.

## Tools

The MCP server exposes tools for:

- Searching official Wavedash docs.
- Fetching docs pages as Markdown.
- Getting an end-to-end agent workflow for building and preparing a browser
  game for Wavedash.
- Getting quickstarts for engines and SDK features.
- Getting upload and publishing checklists.
- Validating pasted `wavedash.toml` text.

## Authenticated steps

For authenticated actions, the MCP server tells the human which Wavedash CLI or
Developer Portal step to perform. It cannot sign in, create projects, create API
keys, upload builds, publish builds, or read local files.

Use the [Wavedash CLI](/cli) for local project actions such as authentication,
initialization, local testing, build upload, and publish.

## See also

- [Agents and AI](/agents)
- [Agent skills](/skills)
- [Wavedash CLI](/cli)