Get the FREE Ultimate OpenClaw Setup Guide →

mcp-config-manager

Manage MCP server configs across Claude, Gemini & other AI systems. Interactive CLI for server enable/disable, preset management & config sync.

Installation
Run this command in your terminal to add the MCP server to Claude Code.
Run in terminal:
Command
claude mcp add --transport stdio holstein13-mcp-config-manager python -m mcp_config_manager \
  --env PYTHONUNBUFFERED="1" \
  --env MCP_CONFIG_MANAGER_LOG_LEVEL="INFO"

How to use

MCP Config Manager is a cross-platform Python GUI/CLI tool for managing Model Context Protocol (MCP) server configurations across Claude, Gemini, Codex, and related systems. The project provides a feature-rich GUI for visually editing, validating, backing up, and syncing MCP server configurations, with an interactive CLI as an alternative workflow. After installation, you can launch the GUI for point-and-click configuration management or use the CLI to script common tasks such as validating configurations, listing servers, or performing bulk operations. The application supports automatic project discovery, per-server field editors, configuration validation, and quick presets to streamline common workflows.

Key capabilities include: a dynamic server editor with type-specific field widgets, project discovery from .claude.json, .gemini/settings.json, and Codex config files, automatic backups before changes, and a master checkbox for bulk operations. You can also synchronize configurations across Claude, Gemini, and Codex, restore from backups, and use keyboard shortcuts for rapid editing. The CLI commands available cover status checks, help output, and individual server management alongside interactive modes for guided configuration. This makes it suitable for both developers maintaining multiple MCP instances and operators who prefer a GUI.

How to install

Prerequisites

  • Python 3.8 or higher
  • Git
  • Optional: PyQt6 for enhanced GUI experience (falls back to Tkinter if not installed)

Step 1: Install Python and Git

  • Ensure Python is available on your PATH and git is installed on your system.

Step 2: Clone the repository (or skip if you plan to install via editable mode from PyPI)

git clone https://github.com/holstein13/mcp-config-manager.git
cd mcp-config-manager

Step 3: Install in editable mode and set up dependencies

python -m venv venv
# Activate the virtual environment
# On Windows
venv\Scripts\activate
# On macOS/Linux
source venv/bin/activate

pip install -e .
# Optional: Install PyQt6 for a richer GUI experience (better styling and tooltips)
pip install PyQt6

Step 4: Run the application (GUI by default) and verify

# GUI launcher (from repository root or installed entry point)
mcp-config-manager gui
# Alternate CLI mode examples (from the same environment)
mcp-config-manager status

Step 5: Optional development setup

pip install -r requirements-dev.txt
pytest

Additional notes

Notes and tips:

  • The GUI provides per-server field editors with validation, project discovery, backups, and synchronization across MCP configuration sources.
  • If PyQt6 is unavailable, the app automatically falls back to Tkinter for GUI rendering.
  • Backups are created automatically before changes, and you can restore from previously saved backups via the GUI or CLI.
  • The CLI supports a range of commands including status, help, and interactive modes for guided server management.
  • Environment variables (examples): use MCP_CONFIG_MANAGER_LOG_LEVEL to adjust log verbosity; set PYTHONUNBUFFERED=1 to ensure real-time logging in CLI sessions.
  • When using macOS, you can build a standalone app bundle for easier launching, but this is optional and primarily benefits non-terminal workflows.

Related MCP Servers

Sponsor this space

Reach thousands of developers