Everything Search MCP
Everything Search MCP provides read-only access to Everything's Windows file index for finding paths and metadata, plus backend status checks.
Search indexed files/folders globally or under a root/drive; browse direct children with
recursive:false.Filter by Everything query, entry kind, and regex; sort and paginate results.
Submit 1–8 search requests per call, return up to 1000 rows each, count matches with
count:0, and sum file sizes withkind:"file"plusfields:["size"].Retrieve metadata such as size, modified/created/accessed dates, attributes, and run count.
Check Everything connection, selected instance, version, index readiness, capabilities, and problems.
It does not search file contents or modify files.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Everything Search MCP find quarterly-report PDFs modified last month across my indexed drives"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Everything Search MCP
Search Windows files from your AI assistant using Everything.
Find files across indexed drives by name, path, type, size, or date. Browse folders, compare their sizes, and get counts or total file sizes in a single request. Searches use Everything's existing index, with paginated results and optional metadata.
Prerequisites
OS: Windows (x64, x86, ARM64, ARM)
Node.js: v22.0.0 or newer
Everything: Everything 1.4.1+ or 1.5 Alpha installed and running.
The ES helper is included. The server automatically checks the default Everything instance, 1.5a, and 1.5 and connects through local IPC.
Related MCP server: everything-search-mcp
Installation & Configuration
On Windows, launch npx through cmd.exe as shown below. Choose your client, add the configuration, then reload its MCP connections. (DeepSeek Harness is the exception: it spawns the command directly, so plain npx works — see its section below.)
Add to your Codex configuration file (%USERPROFILE%/.codex/config.toml or project-level .codex/config.toml):
[mcp_servers.everything]
command = "cmd.exe"
args = ["/d", "/c", "npx", "-y", "everything-mcp-server"]Or add via Codex CLI:
codex mcp add everything -- cmd.exe /d /c npx -y everything-mcp-serverAdd to your project's opencode.json:
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"everything": {
"type": "local",
"command": ["cmd.exe", "/d", "/c", "npx", "-y", "everything-mcp-server"]
}
}
}Or run the OpenCode setup wizard and enter the command above:
opencode mcp addInstall the plugin, then restart the profile:
dsh plugin --profile <profile> add dsh-everything-mcpOr install straight from this repository:
dsh plugin --profile <profile> add github:EcRal5t/everything-search-mcp#path:/plugins/dsh-everything-mcpThe tools appear as mcp__everything__search and mcp__everything__status. To wire it by hand instead, add this row to the profile's cordis.patch.yml:
- insert:
- id: mcp-everything
name: '@deepseek-ai/dsh-mcp-client'
config:
serverName: everything
transport: stdio
command: npx
args: ['-y', 'everything-mcp-server']DSH spawns commands directly, so no cmd.exe wrapper is needed. See plugins/dsh-everything-mcp for the bundle itself.
Add to your MCP client configuration (e.g. claude_desktop_config.json):
{
"mcpServers": {
"everything": {
"command": "cmd.exe",
"args": ["/d", "/c", "npx", "-y", "everything-mcp-server"]
}
}
}VS Code uses servers as the top-level key.
What to ask
After connecting, ask your assistant to use Everything for tasks such as:
Locate a missing file: “Find quarterly-report PDFs modified last month across my indexed drives.”
Investigate large files: “Show the ten largest log files or archives over 1 GB on C:, including their paths and sizes.”
Find project artifacts: “Find folders named node_modules or target under D:/Projects and tell me how many there are.”
Compare folder sizes: “Compare the sizes of the folders directly inside D:/Projects.”
Tools
Both tools are read-only.
Tool | Purpose |
| Find paths, browse folders, count matches, and retrieve sizes or other indexed metadata. |
| Check the connection, selected Everything instance, and version. |
Connection settings
Default settings cover common local installations. Use EVERYTHING_INSTANCE for a custom instance name. Setting EVERYTHING_URL selects an Everything HTTP service; credentials go in EVERYTHING_USERNAME and EVERYTHING_PASSWORD when needed.
Variable | Default | Description |
| auto-detect | Probes the default instance, |
|
| Everything HTTP server URL (e.g. |
|
| Basic auth username for HTTP server. |
|
| Basic auth password for HTTP server. |
|
| Row cap for each query and the whole batch (1–1000). |
|
| Maximum output size budget per tool call (4096–65536). |
|
| Query timeout in milliseconds (100–120000). |
| bundled | Custom path to |
CLI & Diagnostics
Test your Everything installation and backend connection:
npx -y everything-mcp-server doctorRun queries from the command line:
npx -y everything-mcp-server search '{"requests": [{"query": "ext:pdf", "count": 5}]}'Tool reference
search
Search, browse directories, count items, and retrieve indexed metadata.
Pass 1–8 queries in the required requests array:
{"requests": [{"query": "ext:pdf", "count": 5}]}Parameters for each query:
Parameter | Type | Default | Description |
| string |
| Everything search query (e.g. |
| string | optional | Directory to search within (e.g. |
| boolean |
| When |
| string |
| Filter entry type: |
| boolean |
| Treat |
| number |
| Maximum rows to return (max 1000). Use |
| number |
| Zero-based pagination offset. |
| string |
| Sort field: |
| boolean |
| Sort ascending ( |
| string[] |
| Additional columns: |
IPC provides all listed fields and sorts. HTTP sorts by name, path, size, or modified time; it provides size and modified-time fields, with other metadata depending on the service.
Output Format:
Results label columns once, followed by row arrays:
{
"results": [
{
"base": "D:/Projects",
"total": 42,
"next_offset": 2,
"columns": ["path", "type", "size_bytes"],
"rows": [
["src/index.ts", "file", 1024],
["package.json", "file", 512]
],
"size_basis": "indexed_logical"
}
]
}Combine base with relative paths in rows to obtain full file paths.
File and folder sizes use logical byte counts from Everything's index.
status
Check backend connectivity, Everything version, selected instance, and index status.
Parameters:
verbose(boolean, defaultfalse): Include total indexed items and limits.
Local Development
git clone https://github.com/EcRal5t/everything-search-mcp.git
cd everything-search-mcp
npm install
npm testTo configure an MCP client with a local checkout:
{
"mcpServers": {
"everything": {
"command": "node",
"args": ["D:/path/to/everything-search-mcp/src/cli.js"]
}
}
}License
MIT. Bundled es.exe is also MIT licensed by voidtools. See THIRD_PARTY_NOTICES.md.
Available Tools
2 toolseverything_searchARead-onlyIdempotent
Find file/folder paths and indexed metadata across drives or within root. Use workspace search or rg for file contents. Submit 1–8 requests; recursive:false browses; count:0 counts; add kind:"file", fields:["size"] to sum matched bytes.
Inputs: requests (required). Returns: results
everything_statusBRead-onlyIdempotent
Check connection status, selected instance, version, and index readiness.
Inputs: verbose. Returns: ready, details, version, instance, +3 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
The two tools have clearly distinct purposes: one performs file/folder searches, while the other reports server connection and index status. There is no meaningful overlap that would cause an agent to misselect between them.
Both names follow the same predictable snake_case convention with a consistent 'everything_' prefix and clear action/state nouns. The naming is easy to parse and internally consistent.
Two tools is on the thin side for a standalone MCP server, though the scope is narrow and each tool earns its place. The search tool is feature-rich, but the surface still feels borderline minimal.
The core domain operations are covered: searching indexed files/folders and checking connection/index readiness. Minor gaps exist, such as no explicit tool for listing or switching indexed instances or drives, but agents can likely work around them.
Maintenance
Related MCP Connectors
Read and search folders on your own computer with explicit consent. Files are never uploaded.
- DNS-DATA RemoteDeprecatedcom.dns-data
Connect AI assistants to authorized Windows and macOS devices for files, commands, and management.
Securely search and manage workspace context files for AI agents and teams.
Search photos and video moments by visual meaning, people, dates, and folders across local libraries, Apple Photos, and OneDrive. Manage collections, groups, favorites, people, and duplicate review. Synced metadata remains searchable while the desktop is offline; local and Apple Photos media access needs the owning device online with remote access enabled. OneDrive media can be accessed directly from the cloud. OAuth or Bearer API keys. Paid Cloud Access required; hosted visual search uses prepaid credits. Text-in-image search is semantic matching, not guaranteed exact OCR. Setup: https://organizewith.ai/en/guides/connect-ai-assistants
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceProvides AI assistants with semantic search and read access to local files and directories, enabling knowledge retrieval from indexed content.12 npm17MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to search local files on Windows using the Everything search engine, supporting basic and complex file searches with filters like date, size, media type, and document type.4MIT
- AlicenseBqualityBmaintenancePathgate is a MCP server which gives AI tools access to your filesystem102MIT
- AlicenseAqualityBmaintenanceEnables AI assistants to search local files and folders via the Everything search engine, with support for advanced queries, file metadata, text previews, and service status.6113 npmMIT