MCP Catalogs
Home

filesystem vs deep-research-mcp-server

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

filesystem
by modelcontextprotocol
deep-research-mcp-server
by ssdeanx
Stars★ 85,748★ 70
30d uses
Score7743
Official
Categories
File SystemDeveloper ToolsProductivity
AI / LLM ToolsDeveloper ToolsProductivity
LanguageTypeScriptTypeScript
Last committhis month9 mo ago

filesystem · Summary

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

deep-research-mcp-server · Summary

MCP server for deep research using Google Gemini 2.5 Flash, providing iterative research capabilities with web grounding.

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

deep-research-mcp-server · Use cases

  • Conducting in-depth research on complex technical topics with iterative refinement
  • Generating comprehensive research reports with citations and methodology
  • Integrating advanced research capabilities into AI agent workflows via MCP

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.

deep-research-mcp-server · Install

Installation

  1. Clone the repository:
git clone https://github.com/ssdeanx/deep-research-mcp-server
cd deep-research-mcp-server
  1. Install dependencies:
npm install
  1. Set up environment variables:

Create a .env.local file with:

GEMINI_API_KEY="your_gemini_key"
GEMINI_MODEL=gemini-2.5-flash
CONCURRENCY_LIMIT=5
  1. Build the project:
npm run build
  1. Run as MCP server:
node --env-file .env.local dist/mcp-server.js

**Claude Desktop Configuration:** Add to claude_desktop_config.json:

{
  "mcpServers": {
    "deep-research": {
      "command": "node",
      "args": ["--env-file", ".env.local", "dist/mcp-server.js"]
    }
  }
}
Comparison generated from public README + GitHub signals. Last updated automatically.