MCP Catalogs
Home

exstruct vs filesystem

Side-by-side comparison to help you pick between these two MCP servers.

exstruct
by harumiWeb
filesystem
by modelcontextprotocol
Stars★ 144★ 85,748
30d uses
Score4877
Official
Categories
AI / LLM ToolsProductivityDeveloper Tools
File SystemDeveloper ToolsProductivity
LanguagePythonTypeScript
Last committhis monththis month

exstruct · Summary

ExStruct is a Python package that converts Excel files to structured JSON with MCP integration for AI agents.

filesystem · Summary

A feature-rich MCP server for filesystem operations with dynamic directory access control.

exstruct · Use cases

  • Extracting structured data from Excel for RAG systems
  • Editing Excel files through AI agents with patch workflows
  • Converting complex Excel files to JSON for LLM processing

filesystem · Use cases

  • Enable AI models to read and write project files during development
  • Allow Claude or other MCP clients to browse and analyze codebases
  • Provide secure sandboxed access to specific directories for content generation

exstruct · Install

Install the package with pip:

pip install exstruct[mcp]

For Claude Desktop integration, add to claude_desktop_config.json:

{
  "mcpServers": {
    "exstruct": {
      "command": "exstruct-mcp",
      "args": ["--root", "/path/to/your/data", "--on-conflict", "rename"]
    }
  }
}

Alternatively, run directly with uvx:

uvx --from 'exstruct[mcp]' exstruct-mcp --root /path/to/your/data

filesystem · Install

Installation

Using NPX

{
  "mcpServers": {
    "filesystem": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-filesystem",
        "/path/to/allowed/directory"
      ]
    }
  }
}

Using Docker

{
  "mcpServers": {
    "filesystem": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "--mount", "type=bind,src=/path/to/allowed/dir,dst=/projects/allowed/dir",
        "mcp/filesystem",
        "/projects"
      ]
    }
  }
}

VS Code Extension

Click the installation buttons in the README to install directly in VS Code.

Comparison generated from public README + GitHub signals. Last updated automatically.