Meta AI enhances machine learning, NLP, and computer vision capabilities.
Everything MCP
$0.07Starting price
0Popularity
About Everything MCP
Everything MCP is a Model Context Protocol (MCP) server that bridges the Everything desktop search engine to AI coding assistants such as Cursor, Claude Desktop, and Windsurf. It enables AI tools to perform fast, local file and folder lookups directly within the editor, eliminating the need for cloud-based searches or leaving the development environment. The server runs as a lightweight process and communicates over MCP, allowing AI agents to issue search queries and retrieve real-time results without exposing sensitive local data to external services. Developers can use it to quickly locate project files, configuration artifacts, logs, or any other local content referenced during coding sessions, making it particularly useful for offline workflows or environments where cloud connectivity is restricted. The integration is configured by adding the server to the AI assistant’s MCP configuration, with support for multiple transport methods including stdio, SSE, and streamable HTTP. While primarily intended as a demonstration of MCP features, it provides a practical solution for local file discovery within AI-assisted development workflows.
GitHub, Inc.
San Francisco, California, US · Founded 2008
- Founders
- Tom Preston-Werner, Chris Wanstrath, PJ Hyett, Scott Chacon
- Founded
- 2008
- Headquarters
- San Francisco, California, US
- Legal status
- Subsidiary of Microsoft (NASDAQ: MSFT)
Key features
- Exposes Everything search engine via MCP
- Supports Windows desktop file and folder lookups
- Integrates with Cursor, Claude Desktop and Windsurf
- Real-time search results within the AI coding environment
- Lightweight server process running locally
- No cloud dependency for file discovery
- Fast indexed search of local file system
Use cases
- Locate project files during coding sessions
- Find configuration files or logs referenced by AI agents
- Enable offline file discovery in AI coding tools
Pros
- Enables real-time local file and folder searches on Windows systems
- Integrates with major AI coding assistants via Model Context Protocol (MCP)
- Operates as a lightweight process, minimizing system resource usage
- Supports offline and local-only search to keep sensitive data secure
- Provides fast, desktop-level search performance within AI coding environments
Cons
- Primarily designed as a test server to demonstrate MCP capabilities rather than a production-ready tool
- Limited to Windows systems due to dependency on the Everything desktop search engine
- Requires manual configuration in AI coding assistant settings for integration
- No official graphical user interface or standalone application
Frequently asked questions about Everything MCP
What is Everything MCP and what does it do?
Everything MCP is a Model Context Protocol server that connects the Everything desktop search engine to AI coding assistants, enabling fast local file and folder searches directly within the editor.
Which AI coding assistants are compatible with Everything MCP?
Everything MCP integrates with major AI coding assistants that support the Model Context Protocol, including Cursor, Claude Desktop, and Windsurf.
How do I install and configure Everything MCP?
Installation can be done via npm or by running the server from source. Configuration involves adding the server to your AI assistant's MCP settings, typically in a configuration file like claude_desktop_config.json or mcp.json.
Does Everything MCP work offline?
Yes, Everything MCP performs local searches and does not require an internet connection, making it suitable for offline workflows or environments with restricted cloud access.
What operating systems does Everything MCP support?
Everything MCP is designed for Windows systems, as it relies on the Everything desktop search engine which is Windows-specific.
Is Everything MCP a production-ready tool?
While it provides functional local search capabilities, Everything MCP is primarily intended as a test server to demonstrate MCP protocol features rather than a full-featured production tool.
