Foliora for agents, without writing to a site.

One Streamable HTTP server on this URL. Same handlers as /api/v1. An agent can read what Foliora is, hand a human a preview link, or fetch a snapshot the human already started. It cannot crawl, take credentials, or publish.

Start a free preview Pricing

Tools

REST names match the MCP tool names. JSON shapes are identical.

get_product

Return Foliora product facts: brand, plans, canonical URLs, and what this server will not do. Use when the user asks what Foliora is, how much it costs, or which URL to open. Does not crawl a site.

get_snapshot

Fetch a Foliora preview snapshot the human already started. Requires the 32-character hex token from /preview/{token}. Returns public findings and pages only. Unknown tokens are not_found. Does not start a crawl.

create_preview_link

Build a Foliora /preview URL for a public website. Does not crawl, does not take credentials, and does not change the site. Send the human to the returned previewUrl so they can start the snapshot in a browser.

Connect

Point any MCP client at https://www.foliora.ai/mcp. No key for v0.

Claude Code

claude mcp add --transport http foliora https://www.foliora.ai/mcp

Cursor / any mcp.json client

{
  "mcpServers": {
    "foliora": {
      "url": "https://www.foliora.ai/mcp"
    }
  }
}

REST

GET  https://www.foliora.ai/api/v1/product
POST https://www.foliora.ai/api/v1/preview-links
GET  https://www.foliora.ai/api/v1/snapshots/{token}

humans still start the work

The agent sends people to /preview. Foliora reads public pages only.

Run a snapshot