mcpField
D
Drengr

Drengr

Local
github.com/SharminSirajudeenDeveloper Tools0Updated 10w ago
Repository

About Drengr

Drengr is an MCP server that lets AI agents observe and interact with Android and iOS apps. It combines annotated screenshots, compact text output, action reports, app navigation mapping, and network capture for mobile testing and exploration.

Key features

  1. 01Observe screens and perform actions
  2. 02Android and iOS support
  3. 03Annotated screenshot-based vision
  4. 04Compact text screen output
  5. 05Action reports and navigation mapping
  6. 06Capture network calls during actions

Use cases

  1. 01Navigate and interact with mobile apps
  2. 02Explore an app's navigation structure
  3. 03Check changes after an app action
  4. 04Observe HTTP calls during app use

MCP support

Exposes three tools—`drengr_look`, `drengr_do`, and `drengr_query`—for MCP clients to observe screens, act on apps, and ask questions.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "dev-drengr-server": {
      "command": "npx",
      "args": [
        "-y",
        "drengr"
      ]
    }
  }
}
Run commandnpx -y drengr

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmdrengr0.10.8

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Drengr

Eyes and hands for AI agents on mobile devices.

Drengr is an MCP server that gives AI agents (Claude, GPT, Gemini) the ability to see, tap, type, and navigate mobile apps — Android and iOS.

Install

npm install -g drengr

Or run without installing:

npx drengr

Or via shell script:

curl -fsSL https://drengr.dev/install.sh | bash

Quick Setup

# Check your system
drengr doctor

# Configure your MCP client (Claude Desktop, Claude Code, Cursor, etc.)
drengr setup

Add to Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "drengr": {
      "command": "drengr",
      "args": ["mcp"]
    }
  }
}

Add to Claude Code

claude mcp add drengr -- drengr mcp

Add to Cursor

Add to .cursor/mcp.json in your project:

{
  "mcpServers": {
    "drengr": {
      "command": "drengr",
      "args": ["mcp"]
    }
  }
}

What Drengr does

  • 3 MCP tools: drengr_look (observe screen), drengr_do (take action), drengr_query (ask questions)
  • Android & iOS — ADB for Android, simctl for iOS, Appium for cloud devices
  • Vision-first — sees your app like a human via annotated screenshots
  • Text mode — ~300 tokens per screen instead of 100KB images
  • Situation reports — after every action: what changed, what's new, is it stuck?
  • Screen exploration — auto-maps your app's navigation graph
  • Network capture — sees HTTP calls during each action

Supported platforms

PlatformArchitectureSupported
macOSarm64 (M1+)✓
macOSx64✓
Linuxx64✓
Linuxarm64✓

Documentation

Full documentation at drengr.dev

License

Proprietary — © 2026 Drengr. All rights reserved. See LICENSE for details.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.