FixRoast speaks the Model Context Protocol, so Claude and Cursor can audit a landing page and act on what they find without you switching windows. Ask for the conversion gaps on a page, get the fixes back, and apply them in the same breath.
Reads the live HTML and scores schema markup, answer structure, heading hierarchy, trust signals and brand identity. Returns the checks that failed and the fix for each. Runs on any public URL, including your competitors.
Your agent calls this check_ai_citability
Scores across eight dimensions, every detected issue, the quick wins and priorities, and what the page already does well. Your agent reads the findings and can go straight to editing the code.
Your agent calls this get_roast
Your recent analyses with their URLs and scores, so you can say "compare my last two runs" instead of hunting for an ID.
Your agent calls this list_roasts
1. Create a key in Settings
It is shown once and stored only as a hash. Revoke it any time, and anything using it stops immediately.
2. Point your client at it
Claude Code
claude mcp add --transport http fixroast https://fixroast.com/api/mcp \ --header "x-api-key: YOUR_KEY"
Claude Desktop, Cursor and other clients
{
"mcpServers": {
"fixroast": {
"url": "https://fixroast.com/api/mcp",
"headers": { "x-api-key": "YOUR_KEY" }
}
}
}3. Ask it something
“Check whether AI engines can cite our pricing page, then fix whatever fails.” The agent runs the audit, reads the failed checks, and edits the page.
The analysis and the code live in the same conversation. Free to connect, and the citability checker does not spend credits.
Get your key