Browser Automation MCP Servers
Browser control, page inspection, screenshots, web tests, and automation.

Agent Webbridge
Published by GitHub account jeet-dhandha
Local MCP server that lets an assistant drive your own signed-in Chrome across multiple profiles, with parallel tabs via DevTools.

AInotate
Published by GitHub account dontpayfull
Local MCP server that captures screenshots and returns them annotated with numbered steps, arrows, boxes and solid redactions so an agent can show where…

MimirAPI
Published by GitHub account Latimer-Woods-Tech
Lets an assistant screenshot web pages with accessibility audits, generate QR codes, charts and preview images, and validate phone numbers.

Clousd Mcp
Published by GitHub account Clousd-Android
Clousd gives an assistant real cloud Android phones: hand a phone a task in plain words, or drive its screen step by step.
SnapSweep
dev.snapsweepOfficial publisher
A remote, read-only web QA agent that scans a site in a real browser and returns evidence-backed findings to an assistant.
Yab, Yet Another Browser
com.yetanotherbrowser
Connects an AI assistant to Yab, a free Mac WebKit browser, so it can open tabs, read pages, click, type and fill forms using the user's own signed-in sessions.

Computer Use Turbo
Published by GitHub account afaaq-io
A local MCP server that lets an AI agent operate desktop apps on macOS, Windows and Linux, running in the background and safely.

macOS MCP Server
Published by GitHub account deploymenttheory
Local MCP server that lets an AI agent perceive and control the macOS desktop through the accessibility tree, input, screenshots, shell and files.

ZennoBrowser MCP Server
Published by GitHub account ZennoLab
Local MCP server that lets an AI agent manage ZennoBrowser antidetect browser profiles, proxies, cookies, threads and browser instances.

StockSharp DesktopDriver
Published by GitHub account StockSharp
Lets an assistant inspect and drive Avalonia, WPF and MAUI desktop apps locally: read windows, tables and trees, then click, type and scroll.

Riffle
io.noetive
Riffle is a local MCP server that drives a real Chrome browser and hands the assistant each page as text, so it can click, fill in and sign in without screensh
Reconstruct
dev.reconstructOfficial publisher
A remote MCP endpoint that gives AI coding agents captured web interfaces, screenshots, flows and structured evidence.

ZennoPoster: tasks
com.zennolab
Local Windows MCP server that lets an assistant create, configure, start and monitor ZennoPoster automation tasks and their sessions.

ZennoDroid: tasks
com.zennolab
Local Windows MCP server that lets an assistant create, configure, start and monitor ZennoDroid automation tasks and their sessions.

ZennoDroid: ProjectMaker
com.zennolab
Connects an AI assistant to ZennoDroid ProjectMaker so it can read and edit the open project, run it, and record actions.

ZennoPoster: ProjectMaker
com.zennolab
Connects an AI assistant to ZennoPoster ProjectMaker so it can read and edit the open project, run it, and record actions.

ZennoPoster: browsers of running tasks
com.zennolab
ZennoPoster Instance MCP server that lets an assistant drive the browsers of running ZennoPoster tasks: open pages, read and click elements, take screenshots.

ZennoPoster: browser in ProjectMaker
com.zennolab
ZennoPoster ProjectMaker browser control server: lets an assistant open pages, read and click elements, and take screenshots in the editor's browser.

ZennoDroid: devices of running tasks
com.zennolab
ZennoLab sidecar that lets an assistant inspect and drive the Android devices of running ZennoDroid tasks: screen, elements, apps and gestures.

ZennoDroid: device in ProjectMaker
com.zennolab
Lets an AI assistant drive the Android device attached to ZennoDroid ProjectMaker: screen, elements, apps and gestures, via a local Windows MCP server.
terminal-use
Published by GitHub account computer-agent-labs
Lets an AI assistant drive real terminal sessions on your machine: type, press keys, click, read the screen and take screenshots, including full-screen TUIs.

chauffeur
Published by GitHub account YashNaj
Drives the iOS Simulator from a coding agent — snapshotting the screen, tapping, typing and verifying each action against what actually changed.

Layout Debug
Published by GitHub account AntonChuraev99
Local MCP server that lets you pick a UI element in a live web page or Android app and hand its anchors, box and measurements to your coding agent.
Web Reader & Search (Tanod)
dev.tanodOfficial publisher
Remote web toolkit that lets an assistant search the web, read pages as Markdown, take screenshots, and run DNS, domain and metadata lookups.