LessAI ToolsAI plugin directory
← Back to plugins

Tool connections (MCP)

MCP Reference Servers

modelcontextprotocol/servers

Official MCP reference examples, with a Filesystem server for working inside folders you explicitly allow.

Install

macOS / Linux · Claude Desktop configuration fileConfiguration to paste

This installs Filesystem · Node.js 24+

  • Use a macOS or Linux terminal for these commands.
  • Install Node.js and npm first; follow the project’s required version.
  • Merge into the existing configuration; keep other tools and settings.
  • Replace the placeholder values below before running or saving.
  • Save the configuration, then restart or reload your assistant or editor.

Claude Desktop configuration file

Configuration file ~/Library/Application Support/Claude/claude_desktop_config.json

Replace these values: YOUR_ALLOWED_FOLDER

{
  "mcpServers": {
    "filesystem": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-filesystem",
        "YOUR_ALLOWED_FOLDER"
      ]
    }
  }
}
Windows PowerShell · Claude Desktop configuration fileConfiguration to paste

This installs Filesystem · Node.js 24+

  • Run these commands in Windows PowerShell, not Command Prompt.
  • Install Node.js and npm first; follow the project’s required version.
  • Merge into the existing configuration; keep other tools and settings.
  • Replace the placeholder values below before running or saving.
  • Save the configuration, then restart or reload your assistant or editor.

Claude Desktop configuration file

Configuration file %APPDATA%\Claude\claude_desktop_config.json

Replace these values: YOUR_ALLOWED_FOLDER

{
  "mcpServers": {
    "filesystem": {
      "command": "cmd",
      "args": [
        "/c",
        "npx",
        "-y",
        "@modelcontextprotocol/server-filesystem",
        "YOUR_ALLOWED_FOLDER"
      ]
    }
  }
}
Official installation guide ↗
Requirements, costs and detailed steps

MCP Reference Servers setup documentation

What you need

  • The current Filesystem package requires Node.js 24 or later and npm.
  • Use a client that supports MCP over stdio, such as Claude Desktop.
  • Replace YOUR_ALLOWED_FOLDER with an existing absolute folder path before saving the configuration; authorize only the files needed for the task.

Limitations and costs

  • The repository explicitly describes these servers as reference implementations, not production-ready solutions.
  • Filesystem can change or delete allowed files; check proposed operations and keep backups.
  • Installing Filesystem does not install the other reference servers. The repository is transitioning from MIT to Apache-2.0; remaining MIT code and CC-BY-4.0 documentation retain their stated terms.

Based on public documentation; not individually installed and tested here.

What is MCP Reference Servers?

MCP Reference Servers collects examples maintained by the MCP project. Start with Filesystem if you want an assistant to read, search and edit local files in a small, explicitly allowed folder. Other examples cover tasks such as fetching pages, Git and memory. This listing keeps the repository as one collection; the installation example adds only Filesystem. These are learning references, not a promise of production readiness.

MCP Reference Servers use cases

  • Read, search, edit and organize local files through the Filesystem example.
  • Limit Filesystem access to explicit directory paths in its startup configuration.
  • Explore separate reference servers for fetching pages, Git, memory and other tasks.

Official project & documentation

Alternatives to MCP Reference Servers for similar tasks

Compare plugins for similar tasks and check their setup requirements.

  • REA — Reverse Engineer Anything — Let AI investigate how an application's features work and return code and runtime evidence you can check.
  • Claude-Mem — Save coding-session history so an agent can retrieve earlier decisions and fixes in a new conversation.
  • GitHub MCP Server — Let your AI assistant work with GitHub code, issues, and pull requests.

Sources and ranking

This directory lists AI development plugins with public source code and a clear purpose. Browse by task, then open an introduction to learn what a project does, who it is for, and what you need to get started. It covers selected projects, not every AI plugin.

How do the three plugin types differ?

Tool connections (MCP) let AI assistants use external tools such as browsers, code repositories and databases. MCP is the protocol used for these connections.

Reusable skills give a compatible AI assistant instructions and guidance for a particular task.

Editor plugins run inside the software you use to write code, adding AI chat, completions or suggested edits.

How does “Most starred” work?

Projects are sorted by their total GitHub stars. Stars indicate interest; they are not downloads, active users or quality scores. A skill pack counts as one project.

What does “Recently updated” mean?

It uses the most recent code push, which may not be a new release. The 7-day filter checks that project update time; ranking still uses all-time stars. Each introduction shows when its star count was collected.

Introductions are based on public project documentation. These projects have not each been installed and tested here. Check the project documentation for setup, compatibility and service costs.

UTC+8

Pass a useful find along

Pick a draft and a platform. You can edit before posting.