everything-mcp
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-mcp find pdfs modified today in Downloads"
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-mcp
MCP server that exposes Everything (voidtools) instant file search to LLM agents such as Claude Code. It searches file and folder names across the entire disk in milliseconds using Everything's index — a complement to Glob/Grep, which only see the current project.
Features
Whole-disk filename search in milliseconds via Everything's live index.
Native Everything query syntax (
ext:,path:,dm:today,size:>10mb,folder:,file:,|,!) passed straight through — no need for extra tools.Pagination with
offsetand atotal_resultscount, so an agent knows when to page.everything_statusdiagnostic tool to check the index is ready before searching.Windows via the Everything SDK dll over local IPC — no open ports, no per-search subprocess.
Related MCP server: everything-search-mcp
Requirements
Windows with Everything running (living in the tray is enough).
Everything64.dllfrom the Everything SDK.Python ≥3.11 and uv.
Setup
Clone the repo
git clone https://github.com/Santisoutoo/everything-mcp.git cd everything-mcpProvide the DLL. Download the Everything SDK and copy
dll/Everything64.dllintolib/(not versioned in the repo), or point theEVERYTHING_DLLenvironment variable at the dll wherever it lives.Register it in Claude Code (user scope, available in every session):
claude mcp add --scope user everything -- uv run --directory C:\path\to\everything-mcp everything-mcpReplace
C:\path\to\everything-mcpwith the absolute path where you cloned the repo.
Tools
search_files
search_files(query, max_results=50, offset=0, match_case=False,
match_whole_word=False, match_path=False, regex=False, sort="default")Parameter | Meaning |
| Everything query. Space = AND; wildcards |
| Cap on returned rows (1–1000). |
| Skip N results (pagination). |
| Case-sensitive matching. |
| Require each term to match a whole word. |
| Match terms against the full path, not just the name. |
| Treat |
| One of |
Returns {total_results, results: [{path, is_folder, size, modified}]}. total_results is the full
match count; page with offset when it exceeds max_results. Searches names only, not file contents.
everything_status
Returns {available, db_loaded, version, indexed_items}, or {available: false, error} when
Everything is not running. Useful for an agent to confirm the index is ready before searching.
Development
uv sync
uv run pytest # smoke tests (self-skip when Everything is not running)
uv run ruff check . # lint
uv run mypy src # type-check
uv run everything-mcp # start the server over stdioLicense
Released under the MIT License.
Available Tools
2 toolseverything_statusA
Report whether Everything is reachable and its index is ready.
Call this to self-diagnose before searching: returns available (bool),
db_loaded (False while Everything is still building its index),
version, and indexed_items (total files+folders indexed). On failure
returns available: False with an actionable error message.
Inputs: no named parameters. Returns: object
search_filesA
Instantly search file and folder NAMES across the entire disk using the Everything index (use this instead of recursive directory listings when the target is outside the current project).
query uses Everything's native syntax — exploit it instead of filtering
results yourself:
Plain words match anywhere in the name:
informe tfg(space = AND).Wildcards:
*.sfz,foto_202?.jpg. Extension filter:ext:pdf;docx.Scope to a folder tree:
path:"C:\Users\santi\Documents" factura. Direct children only:parent:"C:\Users\santi\Desktop".Only folders / only files:
folder:node_modules,file:*.log.Dates:
dm:today,dm:lastweek,dm:2026. Size:size:>10mb.Operators:
|(OR),!(NOT), quotes for exact phrases.
Searches names only, NOT file contents. total_results in the response is
the full match count; page with offset if it exceeds max_results.
match_whole_word requires each search term to match a whole word.
match_path matches the terms against the full path, not just the name.
sort is one of: default (index order), name, path, size (largest first),
date_modified (newest first).
Inputs: query (required), sort, regex, offset, +4 more. Returns: object
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 serve clearly distinct purposes: one checks the status of the Everything index, the other performs searches. There is no overlap or ambiguity between them.
The tool names follow different patterns: 'search_files' is verb_noun, while 'everything_status' is a noun phrase. Both are readable and use snake_case, but the inconsistency in pattern is noticeable.
With only two tools, the server is minimal. The search tool is the core functionality and the status tool is a useful helper, but the set feels slightly thin for a full-featured server.
The server fully covers its stated purpose of searching file names via the Everything index. The search tool offers extensive query syntax and pagination, while the status tool provides essential readiness information. No obvious gaps for the intended use case.
Maintenance
Related MCP Connectors
Search verified AI agents, MCP servers, and native llms.txt documentation endpoints.
Securely search and manage workspace context files for AI agents and teams.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
Agentic search over your Dewey document collections from any MCP-compatible client.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables instant file and folder searching on Windows using Everything's blazing-fast search engine, supporting powerful search syntax including wildcards, regex, size filters, date filters, and comprehensive file information retrieval.64 npm15MIT
- 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
- 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
- FlicenseAqualityBmaintenanceEnables fast Windows file and directory lookups through the local Everything index, supporting exact, keyword, wildcard, regex, fuzzy, pinyin, and typo-tolerant searches with filters, pagination, directory browsing, counting, and status checks.12-