MCP Server
Connect RankRush to Claude and any MCP-compatible AI client to run visibility checks and audits as tools.
The RankRush MCP server exposes your AI-visibility checks, audits, keywords, blog, and Buzz operations as tools any MCP-compatible client can call. It’s a pure-Node package - no Python - that runs with just your API key.
Authenticate
Generate a scoped key in the dashboard (keys are prefixed rr_live_) - the only secret the server needs. It’s read from the RANKRUSH_API_KEY environment variable. Never commit it.
Configure
The package is @rankrush.ai/mcp, run via npx so there’s nothing to install.
Add RankRush to your claude_desktop_config.json (Settings → Developer → Edit Config), then restart Claude Desktop:
{
"mcpServers": {
"rankrush": {
"command": "npx",
"args": ["-y", "@rankrush.ai/mcp"],
"env": {
"RANKRUSH_API_KEY": "<your-api-key>"
}
}
}
}Add the server from the terminal:
claude mcp add rankrush \
--env RANKRUSH_API_KEY=<your-api-key> \
-- npx -y @rankrush.ai/mcpConfirm it’s connected with claude mcp list.
Point any MCP client at the server over stdio:
command: npx
args: -y @rankrush.ai/mcp
env: RANKRUSH_API_KEY=<your-api-key>Tools
The server surfaces the same api-key operations as the CLI and REST API - AI-visibility checks, audits and audit nodes, keywords, blog topics and posts, content strategy, and Buzz - so an AI client can measure and improve AI visibility directly.
Profiles are selected by business name, not internal ID: tools take a business argument (e.g. “run an audit for Your Business”). List what you can act on with the profilesList tool.