# andrewschreiber/desktopinsights-mcp [Health: Active]

**Category:** 🖥️ OS Automation  
**Repository:** https://github.com/andrewschreiber/desktopinsights-mcp  
**GitHub Stars:** 3  
**npm Downloads (last month):** 3825  
**Views:** 3  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/andrewschreiber-desktopinsights-mcp

## Description
Look up SDKs, frameworks, and dependencies used by 12,000+ macOS and Windows desktop apps. Search by technology adoption, compare stacks, and discover SDK usage patterns via the Desktop Insights API.

## Claude Desktop Quick Installation
Install path detected from listing signals. Uses `npx` (confidence: high):

```json
"mcpServers": {
  "desktopinsights-mcp": {
    "command": "npx",
    "args": ["-y","desktopinsights-mcp"],
    "env": {
      "DESKTOPINSIGHTS_API_KEY": "",
      "DESKTOPINSIGHTS_API_URL": ""
    }
  }
}
```

**Requires environment variables:** `DESKTOPINSIGHTS_API_KEY`, `DESKTOPINSIGHTS_API_URL` — the values above are empty placeholders; fill in real credentials before running (see the repository for what each one is for).

## Documentation

## What the andrewschreiber/desktopinsights-mcp MCP server does

andrewschreiber/desktopinsights-mcp MCP server exposes Desktop Insights data through the Model Context Protocol. Desktop Insights catalogs SDKs, frameworks, and dependencies associated with more than 12,000 desktop applications on macOS and Windows.

The server is intended for questions about application technology stacks. You can investigate the dependencies of a named product, identify applications using a particular SDK, filter results by runtime or platform, and compare the technologies used by two applications. It can also list the tracked SDK categories and example values, which helps identify available search dimensions before running a more specific query.

Typical research questions include which applications use Sentry, whether Electron apps use Stripe, what SDKs Figma uses, or how the stacks of Slack and Discord differ.

## How it works

The process runs as an MCP server and communicates with an MCP client over the command launched by `npx -y desktopinsights-mcp`. Requests are sent to Desktop Insights using the configured API key. The API base URL defaults to `https://desktopinsights.com`, but it can be changed through configuration.

The available operations are organized around four tools:

- `lookup_app` retrieves SDK and dependency information for a specific application.
- `search_apps` finds applications using SDKs or other supported filters, including runtime, platform, or developer.
- `compare_apps` returns a side-by-side technology stack comparison for two applications.
- `list_sdk_categories` shows the 11 tracked SDK categories and example values for discovery.

This makes the andrewschreiber/desktopinsights-mcp MCP server suitable for technology research, stack comparison, and SDK adoption analysis rather than local desktop control or application automation.

## Setup and configuration

Create an API key at the Desktop Insights API settings page before starting the server. Set it as `DESKTOPINSIGHTS_API_KEY`; this variable is required. `DESKTOPINSIGHTS_API_URL` is optional and uses `https://desktopinsights.com` when omitted.

Claude Code can register the server with:

```bash
claude mcp add desktopinsights -e DESKTOPINSIGHTS_API_KEY=your-api-key -- npx -y desktopinsights-mcp
```

For Claude Desktop, add a `desktopinsights` entry to `claude_desktop_config.json` with `npx` as the command, `-y` and `desktopinsights-mcp` as arguments, and the API key in the `env` object. Cursor uses the same command and environment layout in `.cursor/mcp.json`.

For local development, install the npm dependencies, build the project, and run `node build/index.js` with `DESKTOPINSIGHTS_API_KEY` set.

## Tools and capabilities

The andrewschreiber/desktopinsights-mcp MCP server supports four focused capabilities. App lookup answers questions about one product's SDKs and dependencies. App search supports discovery based on technology adoption, runtime, platform, or publisher. Comparison is designed for evaluating two named applications side by side. Category listing provides the available SDK taxonomy and example filter values.

These tools can support competitive technology research, dependency investigation, and finding desktop applications that share a runtime or third-party SDK. The material does not describe write operations or changes to Desktop Insights data.

## Limitations and notes

An API key is needed to use the service. The documented dataset covers macOS and Windows desktop applications, so the server should not be assumed to provide mobile, web, or other software coverage. Search filters are limited to the dimensions exposed by Desktop Insights; the README specifically documents SDK usage, runtime, platform, and developer filters. No client-specific setup is described beyond Claude Code, Claude Desktop, and Cursor.

_Full upstream README: https://allmcps.com/mcp/andrewschreiber-desktopinsights-mcp/readme_