AgentIndex icon
AgentIndex
ToolsCategoriesTrendingNewCompare
Submit Tool
Home/
Vision / Multimodal/
native-devtools-mcp
native-devtools-mcp logo

native-devtools-mcp

Active·★ 105·MIT·Updated 2026-05-02
★ Trending★ Browser Automation★ Workflow Automation

MCP server for computer use & browser automation - screenshot, OCR, click, type, find_text, Chrome/Electron CDP, template matching. macOS, Windows & Android. Works with Claude, Cursor, and any MCP client.

native-devtools-mcp gives AI agents direct control over native desktop apps, Chrome/Electron browsers, and Android devices via a single local MCP server. It supports screenshots, OCR, accessibility-driven element lookup, input simulation, window management, CDP, and ADB. Compatible with Claude Desktop, Claude Code, Cursor, and other MCP clients.

#adb#ai-agent#android#browser-automation#cdp#chrome-devtools-protocol#claude#claude-code
$ Install
$ npx -y native-devtools-mcp
↗ Visit site★ GitHub
01

Features

01Computer vision with screenshots and OCR
02Input simulation: click, drag, scroll, type
03Element-precise AX Dispatch on macOS (focus-preserving)
04Browser automation via Chrome DevTools Protocol (CDP)
05Android device support via ADB (screenshots, input, uiautomator)
02

Compatibility

macOS
Native
Verified via docs
Windows
Native
Verified via docs
Android
Built-in via ADB
Verified via docs
Chrome/Electron
Via CDP
Verified via docs
03

Quick start

1
$ npx -y native-devtools-mcp
04

Use cases

↳Universal app automation via visual screenshots and OCR
↳Precise control of native macOS apps using Accessibility dispatch
↳Automate Chrome and Electron apps via CDP (DOM-level)
05

Alternatives

ragflow logo
ragflow★ 81.5k
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
vs →
n8n logo
n8n★ 190.2k
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
vs →
context-mode logo
context-mode★ 16.0k
Context window optimization for AI coding agents. Sandboxes tool output, 98% reduction. 12 platforms
vs →
Auto-claude-code-research-in-sleep logo
Auto-claude-code-research-in-sleep★ 11.0k
ARIS ⚔️ (Auto-Research-In-Sleep) — Claude Code skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation via Codex MCP
vs →
agents-best-practices logo
agents-best-practices★ 1.1k
Provider-neutral Agent Skill for Codex, Claude Code, and agentic harness design.
vs →
holaOS logo
holaOS★ 5.4k
The agent environment for long-horizon work, continuity, and self-evolution.
vs →
openagent logo
openagent★ 5.1k
⚡️AI Cloud OS: Open-source enterprise-level AI knowledge base and MCP (model-context-protocol)/A2A (agent-to-agent) management platform with admin UI, user management and Single-Sign-On⚡️, supports ChatGPT, Claude, Llama, Ollama, HuggingFace, etc., chat bot demo: https://ai.casibase.com, admin UI demo: https://ai-admin.casibase.com
vs →
awesome-claude logo
awesome-claude★ 250
HeyClaude is a curated registry and distribution surface for Claude and AI-workflow assets: agents, MCP servers, skills, commands, hooks, rules, guides, tools, jobs, Raycast feeds, static data exports, and an npm MCP package.
vs →
See all alternatives →

Related searches

native-devtools-mcp AlternativesBest Vision / Multimodal Tools 2026Open Source Vision / Multimodalnative-devtools-mcp Tutorialnative-devtools-mcp Vs Competitorsadbai-agentandroid

Comments

Log in to leave a comment
  • E
    Emerson JacksonMay 23, 2026

    Chrome CDP integration is solid — actual browser automation, not simulated clicks.

  • R
    River NguyenMay 18, 2026

    Works on macOS, Windows, and Android. The cross-platform support is production-tested.

  • R
    Robin ThompsonMay 7, 2026

    Useful for automated UI testing workflows where pixel-level verification matters.

  • S
    Sam MartinezMar 12, 2026

    Screenshot + OCR + CDP in one server covers most computer use cases without needing multiple tools.

  • P
    Parker ChenMar 11, 2026

    Template matching for click targets is more reliable than coordinate-based approaches.

On this page
01Features02Compatibility03Quick start04Use cases05Alternatives
Stats
GitHub Stars★ 105
Last commit4w ago
StatusActive
LicenseMIT
CategoryVision / Multimodal
Trend (30d)
+4.2↑ 0.8%
Links
Documentation↗Discussion↗Issues↗Releases↗

Deploy on DigitalOcean — Get $200 Free Credit

Ad
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
QYSGitHubBuy me a coffee ☕

Browse by Category

Code AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.