codebase-mcp vs filesystem

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

	codebase-mcp by danyQe	filesystem by modelcontextprotocol
Stars	★ 43	★ 85,748
30d uses	—	—
Score	42	77
Official	—	✓
Categories	Developer ToolsAI / LLM ToolsProductivity	File SystemDeveloper ToolsProductivity
Language	Python	TypeScript
Last commit	7 mo ago	this month

codebase-mcp · Summary

Privacy-first AI coding assistant that turns Claude into a powerful MCP-based development tool with semantic search, memory, and quality-checked code generation.

filesystem · Summary

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

codebase-mcp · Use cases

Creating new features with auto-formatting and quality-scoped code generation
Refactoring existing code with AI assistance and dependency injection patterns
Continuing development with persistent memory that recalls previous progress and mistakes

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

codebase-mcp · Install

Prerequisites

Python 3.11+
Claude Desktop (or any MCP-compatible client)
Git installed
[uv](https://github.com/astral-sh/uv) package manager (recommended)

Installation

**Clone the repository:**

git clone https://github.com/danyQe/codebase-mcp.git
cd codebase-mcp

**Install globally:**

# Install uv if you haven't
pip install uv

# Create virtual environment and install dependencies
uv venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate
uv pip install -r requirements.txt

# Install formatters globally
pip install black ruff

**Configure Gemini API:**

cp .env.example .env
# Get free API key from: https://aistudio.google.com/app/apikey
# Add to .env:
GEMINI_API_KEY=your_api_key_here

**Configure Claude Desktop:**

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "codebase-manager": {
      "command": "/path/to/your/.venv/bin/python",
      "args": [
        "/path/to/codebase-mcp/mcp_server.py"
      ]
    }
  }
}

**Start the FastAPI server:**

python main.py /path/to/your/project

Use with Claude Desktop by restarting it and starting to chat - Claude now has access to 13+ MCP tools!

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.