For AI agents & developers

The Fame Ranker MCP

Fame Ranker runs a public Model Context Protocol server. Point any MCP-capable AI agent at it and ask questions about executive pay in plain language — it searches our sourced registry and returns the most relevant compensation figures, holdings snapshots, and Paper Trail Grade™ grades, each with a link back to the underlying SEC filing.

The endpoint

Streamable HTTP. Public, no authentication. Rate limited to 120 requests per minute.

https://ae7d2747-0916-4547-b662-75465579fd32.search.ai.cloudflare.com/mcp

What it can answer

The server indexes the executive-pay registry — 15 public-company chief executives, each with a cited compensation figure, a cited equity-holdings snapshot, and a Paper Trail Grade — and stays in sync as the registry grows. Every answer is grounded in the published Paper Trail Grade™ methodology.

Connect your client

Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "fameranker": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://ae7d2747-0916-4547-b662-75465579fd32.search.ai.cloudflare.com/mcp"]
    }
  }
}

Cursor

Add to ~/.cursor/mcp.json (Cursor supports remote URLs directly):

{
  "mcpServers": {
    "fameranker": {
      "url": "https://ae7d2747-0916-4547-b662-75465579fd32.search.ai.cloudflare.com/mcp"
    }
  }
}

Any remote-MCP client / Cloudflare AI Playground

Paste the endpoint URL into any client that supports remote MCP over streamable HTTP (for a no-install test, use the Cloudflare AI Playground and add the URL under MCP Servers).

The tool

The server exposes one tool, search, which takes a natural-language query and returns ranked, source-linked content. Example prompts once connected:

“What did Tim Cook actually get paid last fiscal year, and what’s that sourced to?”
“Is Elon Musk’s Tesla compensation figure settled or still contested?”
“How stale is Bob Iger’s reported holdings figure?”
“Which CEOs on Fame Ranker took a stock-heavy pay package this year?”

Good to know

Free and open. No key, no sign-up. The machine-readable server card lives at /.well-known/mcp/server-card.json.
It retrieves; you decide. The server surfaces sourced figures and citations — it never characterizes a filing as a signal or makes a call for you. This is not investment advice.
Always current. The index re-syncs from our sitemap, so answers reflect the live site.
Open source. Reference implementation and connect docs: github.com/automationsquadhq/fameranker-mcp.