MCP server for fast file search using Everything (Windows) with cross-platform fallbacks for macOS (Spotlight) and Linux (ripgrep/locate)
Most search and retrieval work still happens through a UI a human drives. Everything MCP server moves it into the conversation instead. MCP server for fast file search using Everything (Windows) with cross-platform fallbacks for macOS (Spotlight) and Linux (ripgrep/locate).
This MCP server implements comprehensive security measures to protect against common vulnerabilities: - Command Injection Protection: All user inputs are sanitized to remove shell metacharacters (;, &, |, $, (, ), `, ~) - Path Traversal Protection: Detects and blocks .. sequences and home directory access (~) - Input Validation: Strict validation of query length (max 1000 chars), path length (max 4096 chars), and parameter bounds - Resource Limits: Command timeouts (30 seconds) and buffer size limits (50MB) prevent DoS attacks - Error Handling: Secure error messages
everything-search-mcp on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.
The server publishes 9 tools. What each one is for:
search_files — Search for files and folders using platform's search engineget_file_info — The get_file_info tool exposed by this servercheck_status — The check_status tool exposed by this serverOverview — This MCP server implements comprehensive security measures to protect against common vulnerabilities: - Command Injection Protection: All userWindows — The es.exe CLI tool should be automatically downloaded during npm install. If you see this error:macOS — The macOS tool exposed by this serverLinux — The Linux tool exposed by this serverBuilding — The Building tool exposed by this serverTesting — The Testing tool exposed by this serverPlenty of search and retrieval servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Everything's toolset — search_files, get_file_info, check_status and 6 more — is a fair guide to whether it matches your workflow. It is maintained by kanishka-namdeo; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| search_files | Search for files and folders using platform's search engine. |
| get_file_info | The get_file_info tool exposed by this server. |
| check_status | The check_status tool exposed by this server. |
| Overview | This MCP server implements comprehensive security measures to protect against common vulnerabilities: - **Command Injection Protection**: All user inputs are sanitized to remove shell metacharacters (;, &, |, $, (, ), , |
| Windows | The es.exe CLI tool should be automatically downloaded during npm install. If you see this error: |
| macOS | The macOS tool exposed by this server. |
| Linux | The Linux tool exposed by this server. |
| Building | The Building tool exposed by this server. |
| Testing | The Testing tool exposed by this server. |
{
"mcpServers": {
"everything-search": {
"command": "everything-search-mcp",
"args": []
}
}
}Configuration as documented by the project. Restart the client after saving.
The simplest web tool that matters — fetch any URL and get model-ready markdown back.
Industrial-strength web extraction — render, scrape, crawl and search entire sites into clean markdown.
Puppeteer-powered browser control that drives pages from the accessibility tree instead of pixels.
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.
Answers, not links — delegate questions to Perplexity's search-grounded models and get cited responses back.
Put 6,000+ pre-built scrapers at your assistant's fingertips through one MCP endpoint.