Local Rank Map Pack Tracker MCP server

Local Rank and Map Pack Tracker MCP Server

An MCP server for the Mamba Labs Local Rank and Map Pack Tracker actor on Apify. Give it keywords, locations, and a domain or business name. Each run searches Google from each location and returns one row per keyword and location with the organic position, the map pack position, and the local finder position.

What's Inside

• What it does
• Quick start
• Prerequisites
• Example prompts
• Tool
• Inputs
• Pricing
• Your keys
• Full actor documentation
• License

What it does

• Each place name is turned into coordinates and the Google search is placed at that point, so a check for Austin returns the Austin map pack.
• Per row: organicposition (up to 50 deep), localpackposition (1 to 3), localfinder_position (top 20), and the matched listing's rating, review count, category, phone, website, and address.
• toporganicdomains and toplocalbusinesses name who holds the top spots.
• With state_key, each row carries the previous positions and the change, so a weekly schedule becomes a rank history.
• An empty position means not found in the positions checked. Blocked rows come back free with a row_status saying so.

All of the work runs on Apify. This package is a thin client that starts the actor run, waits for it, and hands back the dataset rows.

Quick start

You need Node.js 18 or newer and an Apify account with an API token.

Add this to your Claude Desktop config (claudedesktopconfig.json), Cursor, or any MCP client:

{
  "mcpServers": {
    "mamba-local-rank-map-pack-tracker": {
      "command": "npx",
      "args": [
        "-y",
        "@mambalabsdev/mcp-local-rank-map-pack-tracker"
      ],
      "env": {
        "APIFY_TOKEN": "your-apify-token"
      }
    }
  }
}

Restart the client. The tracklocalrankings tool appears.

Prerequisites

• Node.js 18 or newer.
• An Apify API token from console.apify.com/account/integrations, set as APIFY_TOKEN. The server lists its tool without a token; a call needs one.

Example prompts

Shortened. The full README is on GitHub.