Everywhere
Context-aware AI assistant for your desktop. Ready to respond intelligently, seamlessly integrating multiple LLMs and MCP tools.
What is Everywhere?
Everywhere is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to context-aware ai assistant for your desktop. ready to respond intelligently, seamlessly integrating multiple llms and mcp tools.
Context-aware AI assistant for your desktop. Ready to respond intelligently, seamlessly integrating multiple LLMs and MCP tools.
This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Context-aware AI assistant for your desktop. Ready to respon
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx everywhereConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Everywhere
Everywhere is a cross-platform desktop AI assistant built with Avalonia that brings context-aware AI to your fingertips on Windows and macOS, integrating multiple LLM providers including Claude, OpenAI, Gemini, DeepSeek, and local Ollama models in a single interface. It exposes MCP tool support, a web browser agent, local file system access, terminal script execution, and sub-agent dispatch to create a seamless AI workflow without switching apps. Users install it to get a lightweight AI overlay that can read screen context, answer questions, translate text, summarise content, and run agents — all without leaving their current workflow.
Prerequisites
- Windows 10 (build 19041+) or macOS Monterey 12.0 or later (Apple Silicon or Intel)
- An API key from at least one supported provider: Anthropic (Claude), OpenAI, Google Gemini, or DeepSeek — or a local Ollama installation
- Downloaded installer from https://everywhere.sylinko.com/download
Download the installer for your platform
Visit the official download page and grab the installer appropriate for your system. Apple Silicon Macs should use the arm64 pkg; Intel Macs use x64.
# Visit: https://everywhere.sylinko.com/download
# macOS Apple Silicon: Everywhere-macOS-arm64-vX.X.X.pkg
# macOS Intel: Everywhere-macOS-x64-vX.X.X.pkg
# Windows: Everywhere-Windows-x64-Setup-vX.X.X.exeRun the installer
On macOS, open the .pkg file and follow the installation wizard. On Windows, run the .exe setup wizard. A portable ZIP is also available for Windows if you prefer no-install usage.
Launch Everywhere and open Settings
After installation, launch Everywhere and navigate to the Settings screen to configure your AI provider and API keys.
Add your API key
In Settings, select your preferred AI provider and enter the corresponding API key. You can configure multiple providers and switch between them mid-session.
# Supported providers and their key environment:
# Anthropic Claude → ANTHROPIC_API_KEY
# OpenAI → OPENAI_API_KEY
# Google Gemini → GEMINI_API_KEY
# DeepSeek → DEEPSEEK_API_KEY
# Ollama → no key needed, set base URL (default: http://localhost:11434)Enable MCP tools
Open the MCP section in Everywhere's settings to add and configure MCP servers. Everywhere will connect to these servers and make their tools available to the AI assistant.
Everywhere Examples
Client configuration
Everywhere is a standalone desktop application, not configured via a JSON file. MCP server connections are managed through the in-app settings UI. An example MCP server entry (using Desktop Commander) looks like this in the underlying config:
{
"mcpServers": {
"desktop-commander": {
"command": "npx",
"args": ["-y", "@wonderwhy-er/desktop-commander@latest"]
}
}
}Prompts to try
Everywhere is designed for quick, context-aware interactions triggered from any screen.
- "What is this error? How do I fix it?" (with error text selected)
- "Translate this paragraph to Spanish"
- "Make this email more professional"
- "Summarise the key points from this document"
- "Run a web search for the latest release of this library and tell me what changed"Troubleshooting Everywhere
Everywhere does not launch on macOS with 'app is damaged' error
This is a macOS Gatekeeper issue. Right-click the app in Finder, choose Open, then confirm you want to open it. Alternatively run: xattr -cr /Applications/Everywhere.app in Terminal.
AI provider returns authentication error
Double-check the API key in Settings — ensure there are no leading/trailing spaces. For Ollama, confirm the daemon is running locally with `ollama serve` and that the base URL in settings matches (default http://localhost:11434).
MCP tools are not available in the assistant
Ensure the MCP server command is valid and the server process starts cleanly. Test the server independently in a terminal (e.g., npx -y @wonderwhy-er/desktop-commander@latest) before adding it to Everywhere's MCP settings.
Frequently Asked Questions about Everywhere
What is Everywhere?
Everywhere is a Model Context Protocol (MCP) server that context-aware ai assistant for your desktop. ready to respond intelligently, seamlessly integrating multiple llms and mcp tools. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Everywhere?
Follow the installation instructions on the Everywhere GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Everywhere?
Everywhere works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Everywhere free to use?
Yes, Everywhere is open source and available under the NOASSERTION license. You can use it freely in both personal and commercial projects.
Everywhere Alternatives — Similar Developer Tools Servers
Looking for alternatives to Everywhere? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.
Ecc
★ 188.2kThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Javaguide
★ 155.8kJava 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Gemini CLI
★ 104.5kA secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command in
Awesome MCP Servers
★ 87.3k⭐ Curated list of Model Context Protocol (MCP) servers - tools that extend Claude Desktop, Cursor, Windsurf, and other MCP clients with custom capabilities.
MCP Servers
★ 86.0kModel Context Protocol Servers
CC Switch
★ 77.5kA cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io
Browse More Developer Tools MCP Servers
Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Everywhere in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Everywhere?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.