AI Tools Manager is a local web application designed for seamless management of MCP server configurations. With features like one-click syncing to various AI tools, API credentials management, and easy terminal output viewing, it simplifies the complexities of configuring and maintaining AI environments.
AI Tools Manager
AI Tools Manager is an innovative local web application designed to simplify the management of MCP (Model Context Protocol) server configurations and streamline synchronization with various AI tools, including Cursor, VS Code, Claude Code, and more. This powerful tool offers an intuitive interface to enhance productivity and efficiency in AI development.
Key Features
- Configuration Management: Effortlessly view and edit MCP server configurations, including stdio, http, and sse setups.
- Server Control: Easily enable or disable servers as needed.
- Real-time Output: Monitor terminal output for stdio servers (supporting start, stop, and stream output).
- Instant Syncing: Quickly sync configurations to AI tools like Cursor, VS Code, and Claude Code with a single click.
- Custom Sync Options: Specify custom sync paths for config files.
- Secure API Management: Utilize the dedicated API Credentials tab to store and manage API keys and secrets, keeping sensitive information masked with a reveal toggle.
Development and Production Modes
-
Development Mode: Leverage the power of React hot reload and API integration:
npm run devOpens Vite on http://localhost:5173, with API requests proxied to the backend running on port 3847.
-
Production Build: For production environments, execute the following commands:
npm run build npm startAccess the application via http://localhost:3847.
-
Command-Line Interface Options:
bun start -- --port 3000 # Specify a custom port bun start -- --config ~/my-config.json # Use a custom configuration file
Standalone Executable
For those who prefer a standalone executable, create one using Bun:
bun run compile
This process generates ./ai-tools-manager (or ai-tools-manager.exe for Windows) to be run from the project root, ensuring access to the dist/ folder.
Release Management
Releases are generated automatically upon pushing a tag that adheres to semantic versioning standards (e.g., v1.0.0, v2.1.3, v1.0.0-beta.1). Simply run:
git tag v1.0.0
git push origin v1.0.0
This triggers a GitHub Action that builds cross-platform executables for Linux, macOS, and Windows.
Configuration Files
- Default Configuration: Located at
~/.ai_tools_manager/mcp/config.json - API Credentials: Stored at
~/.ai_tools_manager/creds/creds.json - Override Options: Use
--config <path>or set theMCP_MANAGER_CONFIGenvironment variable.
Upon the first run, if a config file exists at ~/.cursor/mcp.json, it will be automatically imported as the initial configuration.
Supported Sync Targets
| Target | Config Path |
|---|---|
| Cursor | ~/.cursor/mcp.json |
| VS Code | macOS: ~/Library/Application Support/Code/User/mcp.json Windows: %APPDATA%\Code\User\mcp.json Linux: ~/.config/Code/User/mcp.json |
| Claude Code | ~/.claude.json |
| Claude Desktop | macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json Linux: ~/.config/Claude/claude_desktop_config.json |
| OpenCode | ~/.config/opencode/opencode.json |
| Gemini CLI | ~/.gemini/settings.json |
AI Tools Manager elevates the way developers manage and synchronize their AI tools, promoting increased efficiency and streamlined workflows in AI environments.
No comments yet.
Sign in to be the first to comment.