Agents
Connect an AI assistant to Eddyline
If you want an assistant to answer questions about Eddyline without pasting pages into a chat, point it at our MCP endpoint. It is read-only, needs no account and no key, and serves the same facts as this site.
What it offers
The endpoint is https://eddyline.app/api/mcp. It speaks MCP over HTTP, one request per call, with no sessions. It limits each address to 60 requests a minute.
The tools only read; none of them changes anything. For your own install, the REST API is a separate thing.
get_product: Eddyline as data: editions, who counts as a team member, prices, install line, what leaves the server, support and the latest release.get_pricing: Prices for every edition, the managed plans, the setup service and the design partner offer with places left, with checkout links.search_docs: Search the Eddyline docs. Returns the top 5 pages with a title, URL and snippet.latest_release: The newest Eddyline version, its date, a link to the notes and recent versions.
Claude Code
Run this once in a terminal.
claude mcp add --transport http eddyline https://eddyline.app/api/mcp claude.ai
Open Settings, then Connectors, then add a custom connector. Paste this URL and leave the sign-in fields empty.
https://eddyline.app/api/mcp Cursor
Add this to .cursor/mcp.json in your project, or to the same file in your home folder.
{
"mcpServers": {
"eddyline": {
"url": "https://eddyline.app/api/mcp"
}
}
} Check it with curl
A working endpoint answers with the server name and the protocol version it will use.
curl -s https://eddyline.app/api/mcp \
-H 'content-type: application/json' \
-d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-06-18","capabilities":{},"clientInfo":{"name":"curl","version":"1"}}}' Other ways to read the site
The endpoint is listed at /.well-known/mcp.json. If your tool prefers plain files, read
llms.txt, or fetch product.json, pricing.json
and releases.json. Every page also has a .json twin at its own path. The full guide is in the docs.