Browser Automation

Multi-platform UI/mobile automation for AI agents — MCP server + shipped skills.

Model Context Protocol server for Corpusctl — let an assistant read your content types, draft entries and publish, bounded by your API token's scopes

MCP server for Panera Bread - browse menu, customize orders, place pickup

Napster Edge MCP — polyfills the WebMCP standard (document.modelContext) cross-browser and adds live state on top. Write standard registerTool calls with standard annotations; any compatible agent (including Napster's) can operate your app.

MCP server that screenshots the screens you build locally and collects them in one shared gallery

MCP server for Taco Bell - browse menu, customize orders, place pickup

A real interactive terminal for AI agents (MCP). Run and test vim, htop, gdb, REPLs, and any TUI — things the built-in fire-and-forget terminal can't touch.

MCP server for the nightglass screenshot API. Take website screenshots from any MCP-compatible client (Claude Desktop, Cursor, Windsurf, etc).

Extenshi MCP server — bring the extension catalog (search, security, market research) and pre-publish scanning into your AI tools

Spatial DOM maps for AI agent browser navigation with anti-bot stealth.

Drive your real Chrome browser over MCP — real logins, real cookies. A stdio MCP server (CLI) plus an MV3 extension, driving Chrome via chrome.scripting/chrome.tabs. Multi-tab batch automation, accessibility snapshots, deny-all security by default.

Xiaohongshu (rednote / 小红书) MCP server for Claude Desktop, Cursor and AI agents — search, read, comment, like and publish notes via npx. Node.js + Playwright port of xiaohongshu-mcp.

Build, deploy, and operate hosted web apps on VibeKit (vibekit.bot) from any MCP client.

MCP server for Shotpipe — hosted, SSRF-safe, cached screenshots and Open Graph images for AI agents. No headless Chrome to run.

Capture polished DOM element screenshots for AI agents, CLI workflows, and MCP hosts.

MCP server that screenshots a live URL and diffs it against a static design image (PNG/JPG), returning grouped diff regions with severity scores. Deterministic capture: animations disabled, fonts fully loaded, fixed locale/timezone.

Agent-native browser control through a Skill + CLI: share your existing, logged-in Chrome locally or across multiple machines.

MCP server that lets AI read Notion, Google Docs, Jira & any login-protected page via a real browser

MCP server that exposes Codex Desktop's Chrome browser bridge for Claude Code and other agents.

Browser automation for AI agents - integrates agent-browser with claude-flow swarms