MCP Catalogs
Home

gen-ai-starter vs filesystem

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

gen-ai-starter
by jbsoftware-io
filesystem
by modelcontextprotocol
Stars★ 3★ 85,748
30d uses
Score3677
Official
Categories
AI / LLM ToolsDeveloper ToolsOther
File SystemDeveloper ToolsProductivity
LanguagePythonTypeScript
Last committhis monththis month

gen-ai-starter · Summary

Generative AI starter with MCP integration for converting REST APIs to standardized tools.

filesystem · Summary

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

gen-ai-starter · Use cases

  • Building custom agentic LLM applications with RAG capabilities
  • Converting existing REST API services into MCP tools for AI agents
  • Developing and testing LLM applications with Streamlit web interface

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

gen-ai-starter · Install

Installation

  1. Prerequisites:

- Docker Engine (>= 12 GB memory or >= 8 GB with Ollama executable) - Optional: Brave Search API key for web search example

  1. Quick start with CPU:

``bash docker compose --profile=cpu up -d ``

  1. Access the applications:

- Streamlit App: http://localhost:8501/ - Open WebUI: http://localhost:3000/

  1. For MCP server generation:

``bash npm install -g openapi-mcp-generator openapi-mcp-generator --input path/to/openapi.json --output my-mcp-server --transport streamable-http ``

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.