io.github.wvdsh/wavedash

Official8 tools

by wvdsh · JavaScript

Wavedash

Wavedash docs and workflow guidance for building and publishing browser games.

Access Wavedash docs and workflow guidance for building and publishing browser games.

Topics

agent-skillsai-agentsclaude-code-plugincodex-plugincursor-plugingame-developmentgamedevwavedashgemini-cli-extension

Captured live from the server via tools/list.

wavedash_implementation_planner

Plan a Wavedash game implementation from the user's goal, engine, and requested features. Use this before making architecture claims, selecting SDK features, or writing Wavedash integration code. Read-only and unauthenticated.

Parameters (3)

goalstringrequired
What the user wants to build or integrate, including the game type and Wavedash-related outcome.
enginestring
Optional engine/framework, for example phaser, unity, godot, three.js, react, rust, or custom.
featuresarray
Optional requested Wavedash features, for example multiplayer, achievements, leaderboards, cloud-saves, ugc, players, paid-content, upload, or publishing.

wavedash_get_agent_workflow

Return a concise end-to-end workflow for AI agents creating a browser game from scratch and preparing it for Wavedash upload. Read-only and unauthenticated; upload still happens through the Wavedash CLI or Developer Portal.

Parameters (2)

enginestring
Optional engine/framework, for example javascript, phaser, unity, godot, three.js, react, or custom.
featuresarray
Optional requested Wavedash features, for example multiplayer, achievements, leaderboards, cloud-saves, ugc, players.

wavedash_search_docs

Search official Wavedash docs for browser game development, SDK integration, engines, CLI, upload, and publishing. Read-only and unauthenticated.

Parameters (2)

querystringrequired
Search query, for example: sdk setup, multiplayer lobbies, unity webgl, build push.
limitinteger
Maximum number of results to return.

wavedash_get_doc

Fetch a full Wavedash docs page as Markdown by path or docs.wavedash.com URL. Read-only and unauthenticated.

Parameters (1)

pathstringrequired
Docs path or URL, for example sdk/setup, engines/phaser, publishing/upload, or https://docs.wavedash.com/sdk/setup.

wavedash_get_quickstart

Return the Wavedash setup path for a browser game, optionally including an engine and SDK features. Read-only and unauthenticated.

Parameters (2)

enginestring
Optional engine/framework, for example phaser, unity, godot, three.js, react, rust, or custom.
featuresarray
Optional Wavedash features, for example multiplayer, achievements, leaderboards, cloud-saves, ugc, players.

wavedash_get_sdk_reference

Fetch Wavedash SDK docs for a specific feature such as setup, multiplayer, achievements, leaderboards, cloud saves, UGC, players, events, or types. Read-only and unauthenticated.

Parameters (1)

topicstringrequired
SDK topic, for example setup, multiplayer, lobbies, p2p, achievements, stats, leaderboards, cloud-saves, ugc, players, cli, config.

wavedash_get_publishing_checklist

Return Wavedash upload and publishing checklist guidance, optionally including an engine-specific docs page. Read-only and unauthenticated.

Parameters (1)

enginestring
Optional engine/framework, for example unity, godot, phaser, three.js, react, rust, or custom.

wavedash_validate_config

Validate pasted wavedash.toml text for basic Wavedash CLI config issues. This does not read files; provide the config text as input.

Parameters (1)

tomlstringrequired
Contents of wavedash.toml.

README.md2 KBView on GitHub

Wavedash AI

AI integration assets for Wavedash.

The canonical skill source lives in the Wavedash docs repo under skills/ and is served from https://docs.wavedash.com/.well-known/skills/index.json. This repo syncs that source into skills/ so agent platforms can install or index the published assets from GitHub.

The mcp/ package contains a read-only, unauthenticated remote MCP server for public Wavedash docs. It does not access user accounts, local files, builds, or private Wavedash data.

Provider plugins include Wavedash skills and, where supported, bundled config for the hosted remote MCP server.

Layout

skills/ - synced canonical skills for platforms that consume skills directly.
providers/claude/plugin/ - Claude Code plugin package.
providers/cursor/plugin/ - Cursor plugin package.
providers/openai/plugin/ - Codex plugin package.
mcp/ - read-only remote MCP server for public Wavedash docs.
.claude-plugin/marketplace.json - Claude Code marketplace manifest.
.cursor-plugin/marketplace.json - Cursor marketplace manifest.
.agents/plugins/marketplace.json - Codex marketplace manifest.
gemini-extension.json - Gemini CLI extension manifest using the root skills/ directory.

Sync skills

Pull from the public docs endpoint:

bash

npm run sync:skills

Pull from a local docs checkout:

bash

WAVEDASH_SKILLS_SOURCE_DIR=/path/to/wvdsh/docs/skills npm run sync:skills

GitHub Actions runs the same sync daily and commits changes when docs updates change the generated skill files.

MCP server

The Wavedash remote MCP server is live at:

text

https://mcp.wavedash.com/mcp

It is read-only and unauthenticated. It exposes public Wavedash docs, SDK guidance, engine setup help, and publishing checklists for agents.

Remote MCP clients that support Streamable HTTP can connect directly to the endpoint above.

Run the docs-only MCP server locally:

bash

cd mcp
npm install
npm start

The endpoint is http://localhost:3000/mcp.

Validate the Cloudflare Worker bundle without publishing:

bash

npm run mcp:deploy:dry-run

Deploy the MCP Worker from an environment that provides Cloudflare credentials:

bash

npm run mcp:deploy

License

MIT

Install

claude_desktop_config.json

{
  "mcpServers": {
    "wavedash": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.wavedash.com/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.