Fast cross-platform file search using Everything SDK on Windows macOS and Linux
The Everything Search MCP Server is an advanced, versatile tool designed to provide rapid file search capabilities across Windows, macOS, and Linux operating systems through Model Context Protocol (MCP). This server leverages specific platform-driven methodologies—utilizing the Everything SDK on Windows, native Spotlight database queries on macOS, and locate
/plocate
command searches on Linux—to ensure seamless integration with AI applications like Claude Desktop, Continue, Cursor, and more. By harnessing the power of MCP, developers can create highly effective data search functionalities within their applications, enhancing user experience through faster, more accurate file locators.
The Everything Search MCP Server delivers robust capabilities aligned with MCP standards for seamless integration and high-performance operations:
The protocol flow diagram illustrates how data flows between the AI application (MCP Client), server (Everything Search MCP Server), and underlying data sources:
graph TD
A[AI Application] -->|MCP Client| B[MCP Protocol]
B --> C[MCP Server]
C --> D[Data Source/Tool]
style A fill:#e1f5fe
style C fill:#f3e5f5
style D fill:#e8f5e8
This diagram breaks down the interaction layers, ensuring smooth data transfer and processing.
The server's architecture is built around a modular approach, enabling easy integration with various platforms. The core functionality is powered by platform-specific tools—Everything SDK on Windows and native commands for macOS and Linux—which handle file indexing and retrieval seamlessly.
Windows:
macOS:
mdfind
command for fast searches without additional setup.Linux:
locate
and plocate
commands, with database updates necessary after installation.Starting with the Everything Search MCP Server is straightforward. Use one of these methods to set it up easily:
To install using Smithery:
npx -y @smithery/cli install mcp-server-everything-search --client claude
uv
(recommended)For use with uv
, ensure the command and arguments are correctly configured.
Alternatively, you can install it via pip:
pip install mcp-server-everything-search
Running as a script afterward utilizes these packages efficiently:
python -m mcp_server_everything_search
Real-time Project Management: Developers can quickly locate files within large projects, ensuring seamless workflow continuity by integrating the Everything Search MCP Server.
Data Retrieval for Research Applications: Researchers and developers need fast access to specific data files. The server enhances this process with its rapid query capabilities.
Integrating the Everything Search MCP Server is crucial for leveraging its functionality across different AI applications:
Claude Desktop: Supports both command-line (uvx
) and pip installation methods, depending on setup requirements.
Continue: Compatible through both uvx
commands as well as direct scripting.
Cursor: Limited tool support due to API limitations but still functions efficiently for file searches.
MCP Client | Resources | Tools | Prompts | Status |
---|---|---|---|---|
Claude Desktop | ✅ | ✅ | ✅ | Full Support |
Continue | ✅ | ✅ | ✅ | Full Support |
Cursor | ❌ | ✅ | ❌ | Tools Only |
The performance and compatibility of the Everything Search MCP Server are optimized for various use cases:
locate
/plocate
commands with database management.Configuring the server correctly is essential for optimal performance and security:
Ensure that the Everything SDK DLL path is correctly set:
{
"env": {
"EVERYTHING_SDK_PATH": "path/to/Everything-SDK/dll/Everything64.dll"
}
}
This ensures the server can access the required tools smoothly.
Does it work well with all MCP clients?
How do I configure it for maximum performance on macOS?
mdfind
without additional setup, ensuring native Spotlight database integrity.Can I use regex searches in Windows?
Are there specific limitations with Linux installations?
locate
or plocate
databases are updated post-installation for best results.Is it easy to integrate into custom applications?
Contributions are welcome! Developers can contribute by fixing bugs, enhancing features, and improving documentation. For detailed development instructions:
npx @smithery/cli test
.Explore more resources and tools related to the Model Context Protocol (MCP):
By integrating the Everything Search MCP Server, developers can significantly enhance their AI applications with powerful file search functionalities.
RuinedFooocus is a local AI image generator and chatbot image server for seamless creative control
Learn to set up MCP Airflow Database server for efficient database interactions and querying airflow data
Build stunning one-page websites track engagement create QR codes monetize content easily with Acalytica
Simplify MySQL queries with Java-based MysqlMcpServer for easy standard input-output communication
Explore CoRT MCP server for advanced self-arguing AI with multi-LLM inference and enhanced evaluation methods
Access NASA APIs for space data, images, asteroids, weather, and exoplanets via MCP integration