Wavedash AI

MCP serverWeb & browsing

Your AI can build and publish browser games using Wavedash. Once added, it can consult the Wavedash docs and follow the recommended workflows, so it knows how to take a game from building to publishing.

Use Wavedash AI in Claude, ChatGPT or Ahel Desktop

Free. Sign in, add Wavedash AI and connect your AI. About a minute.

Claude ChatGPT Ahel Desktop

Also: Claude Code · Cursor · Codex

Then ask your AI: use the wavedash implementation planner tool from Wavedash AI

No key or account is asked for. Not verified by us yet: Ahel has not run a call through it.

Details

Available today. Use it from your connected AI after setup.

No key or account is asked for. Not verified by us yet: Ahel has not run a call through it.

Ask your AI to walk you through building a browser game with Wavedash, or to explain the steps for publishing one.

Wavedash AIStart free

What your AI can do with it

Look up Wavedash documentation while working on a game
Follow Wavedash workflows for building browser games
Get guidance on publishing a finished browser game
Answer questions about how Wavedash works

Install Wavedash AI

The server’s own address, for the clients that take one directly. Or connect Ahel once and every client you use reads it from one address, with the account kept on Ahel rather than in each client’s config.

Claude Code
claude mcp add --transport http --scope user wavedash-ai 'https://mcp.wavedash.com/mcp'
Run it once in your project, then open /mcp to approve any sign-in the server asks for.
Claude Desktop
https://mcp.wavedash.com/mcp
Add a custom connector in Settings, paste this address, and approve the sign-in.
Cursor
cursor://anysphere.cursor-deeplink/mcp/install?name=wavedash-ai&config=eyJ1cmwiOiJodHRwczovL21jcC53YXZlZGFzaC5jb20vbWNwIn0=
Open the link and Cursor adds the server at that address.
ChatGPT
https://mcp.wavedash.com/mcp
In Settings, enable Developer mode, create an MCP app, and paste this address. Your plan and workspace must allow custom apps.
Codex
codex mcp add wavedash-ai --url 'https://mcp.wavedash.com/mcp'
Run it once, then sign in with codex mcp login wavedash-ai if the server asks for an account.

From the project's README

As published by wvdsh/ai in README.md.

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:

npm run sync:skills

Pull from a local docs checkout:

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:

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:

cd mcp
npm install
npm start

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

Validate the Cloudflare Worker bundle without publishing:

npm run mcp:deploy:dry-run

Pushes to main automatically deploy the MCP Worker when MCP source, dependencies, Worker configuration, root package scripts, or the deployment workflow change. Documentation, skills, and submission files do not trigger a deployment. The Deploy MCP to Production GitHub Actions workflow also supports manual runs and loads deployment credentials through Doppler.

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

npm run mcp:deploy

License

MIT

Tools it offers (4)

What this server listed when Ahel dialed its public endpoint in Oct 2026, with no key and no account of yours. The names are the server’s own.

wavedash_implementation_planner
search_wavedash_docs
get_wavedash_doc
validate_wavedash_config

Signals

GitHub stars: 2
Last commit: Sep 2026

Advanced

Delivery: wavedash MCP server → your Ahel connector (mcp.ahel.ai) → your AI.
Item type: mcp-server
Key: io-github-wvdsh-wavedash
Source: github.com/wvdsh/ai
Hosted endpoint: https://mcp.wavedash.com/mcp

github.com/wvdsh/ai

More in Web & browsing

Web Search
MCP server
More in Web & browsing firecrawl-mcp-server
MCP server · firecrawl
More in Web & browsing apify-mcp-server
MCP server · apify
More in Web & browsing Browserbase
MCP server · browserbase
More in Web & browsing inspo
MCP server · nutlope
More in Web & browsing playwright-mcp
MCP server · microsoft
More in Web & browsing