Velven
Publish browser games, worlds, tools and wonders built with AI to Velven's hosting, and manage them.
Connect it
Settings → Connectors → Add custom connector
URL: https://mcp.velven.ai/mcpSettings → Apps & Connectors → Advanced → Developer mode
Create connector with URL: https://mcp.velven.ai/mcp{
"mcpServers": {
"velven": {
"url": "https://mcp.velven.ai/mcp"
}
}
}claude mcp add --transport http velven https://mcp.velven.ai/mcp{
"servers": {
"velven": {
"type": "http",
"url": "https://mcp.velven.ai/mcp"
}
}
}5 tools, verified live
publishPublish a browser game or any other page made to play or use on Velven's hosting, from one HTML page or a small set of files (3 MB in all). Signed in: a private preview by default, or with prod: true the next live version, live on its Velven page within seconds. Not signed in: an unlisted page, live the same way, returned with a claim token that keeps it. A new space needs title and devices from t
my_spacesread-onlyList the spaces of the signed-in Velven account: slug, title, status, whether Velven hosts it, and its page. Needs sign-in; called without it, the app asks the person to sign in to Velven.
versionsread-onlyList a hosted space's versions, newest first: number, status (uploading, preview, publishing, live, refused, unjudged, replaced), size, and whether rollback can pick it. Refused versions carry the reason. Needs sign-in.
rollbackcan modifyMake an earlier version of a hosted space live again. Only a version that was live before (rollback: true in versions) can be picked; it goes live at once. Needs sign-in.
search_docsread-onlySearch Velven's documentation: publishing and hosting, velven.json, the CLI, the SDK (sign-in, leaderboards, saves, achievements, rooms), claiming a page, the agent API and limits. Returns the best matching sections with links.
Alternatives in Browser & Scraping
Compare →
Writ CloudB
Read, crawl and act on websites, signed in as the user, and turn any site into an API.
SHShadowCrawlB
Stealth scraping & search. Bypasses Cloudflare, DataDome & LinkedIn via Cyborg HITL approach.
OBOya BrowserB
Real Chrome for agents: start a browser, read pages as numbered markdown, click, type, hand off.
BRBrowserlessB
Official Browserless MCP server: browser automation, scraping, screenshots and PDFs for AI agents.
BRBrowserstackB
BrowserStack's Official MCP Server
SupadataB
Video transcripts, metadata and structured data from YouTube, TikTok, Instagram, X; web scraping.