FRENES

Files and documents · MCP server

Everything Search: MCP server, setup and security

Everything Search is an open-source MCP server that lets an AI agent search for files on Windows using the Everything SDK. Its repository has 367 stars and its last commit is from October 17, 2026 and it is licensed under MIT.

Score
76/100
Adoption (stars) 26/40
Maintenance 30/30
Framework (licence, registry, official) 20/30
Actively maintainedSystem access

What Everything Search does

According to its repository: “Windows file search using the Everything SDK.”

An MCP server gives an AI agent extra tools it calls during the conversation: the agent reads their description, decides to use them and gets the result back. Everything Search is listed under Files and documents, a category of 55 servers in the directory, where it ranks #11 by stars.

Installing and connecting Everything Search

Distribution modes declared in the official MCP registry:

  • PyPI package (Python, started with uvx or pip)

Like any MCP server, you declare it in your client's configuration (Claude Desktop, Claude Code, Cursor, VS Code, Codex…): a name, the command that starts it or its URL, and any environment variables. The client then starts it and lists its tools. Project language: Python. Listed systems: Windows.

Security: what to check

An MCP server runs code with the rights you give it, and the model reads its tool descriptions: a malicious or compromised server can hijack the agent. Read the code, or pick a maintained and widely used server, before connecting it.

Points found for Everything Search:

  • System access: the Files and documents category gives the agent control over files, a terminal, code or a browser. A booby-trapped instruction in content the agent reads (prompt injection) can then turn into an action.

Good practice: grant only the rights needed (least privilege), require human approval for irreversible actions, and run the AI agent security check.

Project activity and maintenance

Created on December 14, 2024, the mamertofabian/mcp-everything-search repository has 367 stars and 40 forks, with 5 open issues. It has more stars than 85% of the servers in the directory. It received changes this month. Version published in the registry: 0.3.3 (October 17, 2026).

Stars measure attention, not quality: a recent, heavily promoted project can collect them fast, while a useful but niche server will have few.

MarkitdownMarkitdown : 191.9K191.9KPuterPuter : 43.9K43.9KFilestashFilestash : 14.8K14.8KRevoGrid DataGrid MCPRevoGrid DataGrid MCP : 3.5K3.5KDocling MCPDocling MCP : 777777MCP filesystem serverMCP filesystem server : 692692Haiku.ragHaiku.rag : 636636MuMu : 436436Everything SearchEverything Search : 367367
GitHub stars of the most followed servers in the category (log scale); Everything Search in orange. Checked October 25, 2026.

Verdict

Everything Search is one of the most solid servers in its category: followed, maintained and well framed.

Strengths

  • Active project: recent commit
  • Widely followed: 367 stars
  • Listed in the official MCP registry
  • Permissive licence (MIT)

Avoid if…

  • You cannot isolate the agent (sandbox, container)

Frequently asked questions

How do I install Everything Search?

Everything Search is distributed as PyPI package (Python, started with uvx or pip). Add it to your client's MCP configuration (Claude Desktop, Cursor, VS Code…) following the README of mamertofabian/mcp-everything-search.

Is Everything Search free?

The code is published under the MIT licence and can be used free of charge.

Is Everything Search safe?

Points to watch: system access. Give it minimum rights and approve sensitive actions.

Is it an official server?

Nothing says so: it is a project published by mamertofabian on GitHub. Check who maintains it before giving it access.

What are the alternatives to Everything Search?

In the same category: Markitdown, Puter, Filestash, and RevoGrid DataGrid MCP. Markitdown and Puter score higher on our grid.

Related articles

Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score