Astro

An MCP (Model Context Protocol) server that provides access to Astro ASO (App Store Optimization) data for LLMs.
  • javascript

13

GitHub Stars

javascript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs
{
  "mcpServers": {
    "timbroddin-astro-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "astro-mcp-server"
      ]
    }
  }
}

You run an MCP server that exposes Astro ASO data so you can query current rankings, track history, compare positions, and discover keyword opportunities. This server makes it easy to connect with MCP-enabled clients to power AI-driven insights using real App Store data.

How to use

Connect to the Astro ASO MCP server from your MCP client. Use the standard stdio or http methods supported by your client, and run the available tools to query rankings, trends, app keywords, ratings, and competitive intelligence. You can perform actions like searching current rankings for keywords, fetching historical data, listing tracked apps, getting keywords for an app, analyzing trends, comparing rankings across dates, and identifying keyword opportunities.

How to install

Prerequisites you need before installing the MCP server: you must have the Astro app installed on your Mac with data in its database and Node.js 18 or higher.

Install and run the MCP server locally by following these steps.

  1. Clone the project repository.

  2. Install dependencies.

  3. Build the project.

  4. Run the server in development or production mode as you prefer.

# Step 1: Clone the repository
git clone https://example.com/astro-mcp-server.git
cd astro-mcp-server

# Step 2: Install dependencies
npm install

# Step 3: Build the project
npm run build

# Step 4: Run in development mode (auto-reload)
npm run dev
# Or run in production mode
npm start

Additional setup and usage notes

If you plan to use Claude Code or Claude Desktop as your MCP client, you can register the server with the following example configurations.

Claude Code users can add the MCP server with a single command that wires the client to the local MCP server. Use the stdio method to run the server via npx.

Claude Desktop users can place a configuration entry that points to the MCP server and ensures the proper command is used to start the server.

Security and best practices

Ensure the MCP server has read access to Astro’s SQLite database and that the database path is accessible and protected. Run the server on a trusted machine and limit access to the MCP endpoint to your organization or trusted clients.

Troubleshooting

Common issues include database not found, permission denied, or data not appearing. Verify that Astro has been run at least once and that you are querying with the correct app names or IDs and the correct store (default is US). The server automatically reloads database changes, and WAL-mode databases are merged automatically through checkpoints.

Available tools

search_rankings

Query current keyword rankings for apps with filters for store and app name or ID.

get_historical_rankings

Retrieve historical ranking data over a configurable period to track changes over time.

list_apps

List all tracked apps with details like names, IDs, platforms, and keyword counts.

get_app_keywords

Get all keywords for a specific app, including current and prior rankings, difficulty, popularity, and ranking changes.

get_keyword_trends

Analyze keyword ranking trends with statistics and trend direction over configurable periods.

compare_rankings

Compare rankings between two dates and compute percentage changes.

get_app_ratings

Fetch app rating history with counts over time for an app.

get_keyword_competitors

Identify real App Store competitors for keywords, aggregating data across multiple stores.

get_keyword_recommendations

Generate related keyword recommendations based on current tracking data.

analyze_competitive_landscape

Perform a comprehensive competitive analysis across tracked keywords and competitors.

calculate_keyword_opportunity

Identify high-opportunity keywords by combining popularity, difficulty, and competition metrics.

detect_ranking_anomalies

Detect unusual ranking changes, provide context, and categorize anomaly severity.

predict_ranking_trends

Forecast future ranking movements using linear regression with confidence scores.

find_low_competition_keywords

Discover underutilized keywords by balancing difficulty and popularity.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational