MCP Manager

# Clone and set up git clone <your-repo-url> cd mcp-manager chmod +x mcp-manager # Run interactive setup (recommended for first-time users) ./mcp-manager setup

- Server installation status overview
- System health monitoring
- Quick access to common operations
- Real-time connection status

- Browse 60+ available MCP servers
- Install/uninstall servers with one click
- View detailed server information
- Category and tag-based filtering

- Health score and system diagnostics
- Dependency status checking
- Configuration validation
- Performance metrics

- Visual Claude Desktop config management
- Backup and restore operations
- Environment settings
- API configuration

- Real-time alerts and updates
- Priority-based notification system
- Action items with one-click solutions
- Notification history and management

# Server Management ./mcp-manager list # Show installed servers ./mcp-manager available # Show available servers ./mcp-manager backup # Create configuration backup # Enhanced Commands ./mcp-manager setup # 🆕 Interactive setup wizard ./mcp-manager scan # 🆕 Scan for updates and new servers ./mcp-manager diagnose # 🆕 Run system health check ./mcp-manager notifications # 🆕 View alerts and updates ./mcp-manager status # Enhanced with notifications

--config-path <path> # Override default config location --verbose # Detailed output --json # Output in JSON format --no-cache # Skip cache for fresh data --force # Skip confirmation prompts

- Python 3.8+(required)
- Node.js 16+and npm (for frontend)
- Git(for version control)

git clone <your-repo-url> cd mcp-manager

cd backend python -m venv venv source venv/bin/activate # Windows: venv\Scripts\activate pip install -r requirements.txt uvicorn app.main:app --host 0.0.0.0 --port 8001 --reload

# Make CLI executable chmod +x mcp-manager # Run setup wizard ./mcp-manager setup

uvicorn app.main:app --reload # Development server uvicorn app.main:app --host 0.0.0.0 # Production server python -m pytest # Run tests

npm run dev # Development server npm run build # Production build npm run preview # Preview production build npm run lint # Lint code

The FastAPI backend provides comprehensive REST endpoints:

- GET /api/health: Health check
- GET /api/servers/available: List available servers
- GET /api/servers/installed: List installed servers
- POST /api/servers/install: Install a server
- DELETE /api/servers/{name}: Uninstall a server
- GET /api/system/status: System health status
- POST /api/system/scan: Run system scan
- GET /api/notifications/: Get notifications
- GET /api/analytics/overview: Analytics dashboard

MCP Manager automatically discovers your Claude Desktop configuration:

- Windows:%APPDATA%\\Claude\\claude_desktop_config.json
- macOS:~/Library/Application Support/Claude/claude_desktop_config.json
- Linux:~/.config/Claude/claude_desktop_config.json

- Zero Learning Curve: Setup wizard eliminates configuration complexity
- Modern Interface: Beautiful web UI alongside powerful CLI
- Stay Current: Never miss important updates or useful new servers
- Reduce Errors: Automatic error detection and intelligent recovery
- Save Time: Smart recommendations and one-click solutions
- Production Ready: Comprehensive safety features and error handling
- Cross-Platform: Works seamlessly on Windows, Mac, and Linux

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

What Shopify did for ecommerce, Chipp does for AI agents. Build, deploy, and monetize AI agents for your business — no engineering team required.

CodeVF MCP lets AI hand off problems to real engineers instantly, so your workflows don’t stall when models hit their limits.

Client implementation for Mastra, providing seamless integration with MCP-compatible AI models and tools.

Agent-native developer Q&A API with MCP + A2A endpoints for citations, job pickup, and answer submission.

On-demand access to 150+ specialist AI agent templates — search, browse, and spawn agents. 150x reduction in context usage vs loading agents locally.

AgentChatBus is a persistent AI communication bus that lets multiple independent AI Agents chat, collaborate, and delegate tasks — across terminals, across IDEs, and across frameworks.

Remote MCP server (Streamable HTTP) at https://mcp.agenticrail.nz/ — deterministic step-order enforcement for AI agents. evaluate_step returns ALLOW or DENY before a step runs; verify_receipt proves a sequence's Ed25519-signed, hash-chained receipt chain is intact. No auth required: omit the bearer token and calls run on the public demo key. That first clause matters — the form has no "remote/hosted" field, and putting the endpoint in the description is the convention on that list ("Fully REMOTE! Just use…"). The rest mirrors your own server card verbatim, so the listing and the card can't drift.

An AI Agent with optional Human-in-the-Loop Safety and Model Context Protocol (MCP) integration.

Agent Mail Rooms is a paid remote MCP endpoint for OpenAI Codex agent coordination MCP. It exposes structured JSON tools, a public server card, token-based access, usage receipts, and audit-