AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
Dev Tooling/
autonomo
autonomo logo

autonomo

Active·★ 36·NOASSERTION·Updated 2026-03-04

Autonomo MCP lets AI coding assistants observe the state of a running app, drive several devices at once, and check cross-device interactions inside one iterative development loop. Instead of reading screenshots, the assistant gets a structured snapshot after every action: UI state, app state and network calls. The README compares about 50 ms and roughly 50 tokens per state report with 2 to 5 seconds and 1000+ tokens for screenshot analysis.

Your app embeds a small test bridge, and elements are addressed by semantic IDs rather than screen coordinates, so tests survive redesigns. Multi-device runs allow scenarios such as sending a message on device A and verifying it arrives on device B, and custom actions such as a devLogin action can bypass OTP or OAuth during local testing. Packages exist for React, React Native, Swift, Flutter, Python, Ruby, Kotlin, C# and Deno Fresh, and the quick start is a prompt that asks your assistant to read the QUICKSTART guide and install it. It works with GitHub Copilot, Claude Code, Cursor, Windsurf and other MCP clients.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool. Data as of 2026-10-17.

License
Not detected by GitHub
Latest release
v2.1.0 · 2026-03-04
Last commit
2026-03-04
Contributors
2
Forks
2
Open issues and PRs
0
First published
2026-02-05

Source: GitHub, npm and PyPI public APIs.

#AI-Assisted Development#End-to-End Testing#Multi-Device Testing#Application State Introspection#Developer Tools#Local Development#AI Hallucination Reduction#Cross-Platform
$ Install
$ npm install github:sebringj/autonomo#packages/@autonomo/mcp-server
↗ Visit site★ GitHub
01

Features

01AI-driven end-to-end testing with real-time app state observation.
02Multi-device testing for simultaneous interactions (e.g., User A → User B flows).
03Unified snapshot of UI, app state, network, and errors after every action.
04Reduces AI hallucinations by enabling LLMs to verify code outcomes directly.
05100% local development workflow, language-agnostic via HTTP protocol.
02

Why choose it

+Structured state reports are faster and cheaper in tokens than screenshot-based testing, by the README's figures.
+One protocol covers web, mobile and desktop stacks, with packages for nine platforms.
+Multi-device scenarios let you test flows that span two users or devices.
+Semantic element IDs and custom actions make tests more stable and let you skip OTP or OAuth locally.
03

Trade-offs

!You must add a test bridge to your app, so it is not a drop-in tool for apps you cannot modify.
!It is dual-licensed under AGPL-3.0 and a commercial licence, which is free for companies under $1M annual revenue but needs terms above that.
!The performance and token figures are the project's own comparison, and the repository was last updated in March 2026.
04

Maintenance check

SlowingChecked: 2026-10-19
Last commit
2026-03-01
Commits, last 90 days
0
Releases, last 90 days
0
Latest release
v2.1.0 (2026-03-04)
Open issues
0
Recent issues with at least one comment
—
Commits per week, last 12 weeks
Commits per week, last 12 weeks: 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0

Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

05

Compatibility

React
Frontend Framework
Verified via docs
React Native
Mobile Framework
Verified via docs
Swift/iOS
Mobile Framework
Verified via docs
Flutter
Mobile Framework
Verified via docs
Python
Backend Runtime
Verified via docs
Ruby
Backend Runtime
Verified via docs
06

Quick start

1
$ npm install github:sebringj/autonomo#packages/@autonomo/mcp-server
07

Use cases

↳Automating user flow testing across multiple devices or user roles.
↳Bypassing complex authentication (e.g., OTP/OAuth) for faster local AI-driven testing.
↳Enabling AI to debug and fix code by observing real-time application failures.
↳Validating UI changes and semantic element interactions without brittle vision-based tests.
↳Testing backend API endpoints as "elements" in a unified AI-driven loop.
08

Alternatives

⚡Top VS:
VScarabiner★30→VSfigwright★1.1k→VSDebugMCP★573→VSdsh-desktop★483→
carabiner logo
carabiner★ 30
Simple Screen Capture and Remote Control App for Streaming Devices
VSCompare→
figwright logo
figwright★ 1.1k
Free, two-way Figma MCP server. Turn designs into framework-aware code, and push code back to the canvas. Works with Claude Code, Cursor, Codex, and any MCP client.
VSCompare→
DebugMCP logo
DebugMCP★ 573
Gift your VS Code agent a real debugger: breakpoints, stepping, inspection.
VSCompare→
dsh-desktop logo
dsh-desktop★ 483
DeepSeek Harness Desktop App: a local AI desktop workspace for DSH Sessions, projects, files, web research, plugins, and Office artifacts.
VSCompare→
copilot-mcp logo
copilot-mcp★ 505
A VSCode extension that lets you find and install Agent Skills and MCP Apps to use with GitHub Copilot, Claude Code, and Codex CLI.
VSCompare→
agentic-tools logo
agentic-tools★ 227
Agent Skills for Meta Quest/Horizon OS VR Development
VSCompare→
Gearcoleco logo
Gearcoleco★ 143
ColecoVision emulator, debugger and embedded MCP server for macOS, Windows, Linux, BSD and RetroArch.
VSCompare→
lnwjud logo
lnwjud★ 205
Windows-first local AI-agent runtime & MCP gateway with 214 configurable tools (208 advertised by default) for files, Git, processes, WSL, desktop/browser automation, MCP Tasks, observability, and Secure MCP Tunnel.
VSCompare→
See all alternatives →

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Maintenance check05Compatibility06Quick start07Use cases08Alternatives
sebringj /
autonomo
↗

MCP server that lets AI assistants drive and test running apps across devices

362
Last commit7mo ago
StatusActive
CategoryDev Tooling
Contributors2
Latest releasev2.1.0
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.