Skip to main content
Glama

โšก SuperGateway Pro

Centralized MCP Gateway Daemon, Vercel-Style Live Activity Dashboard & macOS Menu Bar Suite for AI Coding Agents

License: MIT Node.js Python Platform


๐ŸŒŸ Overview

SuperGateway Pro is an open-source, high-performance Model Context Protocol (MCP) gateway, connection pooler, and real-time observability console.

Instead of every AI developer client (Codex / ChatGPT, Claude Desktop, Antigravity, OpenCode / Codeg) spinning up its own isolated Node.js/Python runtimes for the exact same tools (wasting 500MB โ€“ 1.5GB of RAM and hundreds of threads), SuperGateway Pro maintains a single, pre-warmed shared server pool and multiplexes requests in sub-millisecond time.

โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”
โ”‚     AI Clients: Codex | Claude Desktop | Antigravity | Codeg  โ”‚
โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜
                                โ”‚ (Lightweight stdio / SSE)
                                โ–ผ
โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”
โ”‚       โšก SuperGateway Pro Daemon (Port 8080 / <25MB RAM)       โ”‚
โ”‚  โ”œโ”€ ๐Ÿ“Š Vercel-Style Live Console (SSE Tool Stream)           โ”‚
โ”‚  โ”œโ”€ โšก macOS Menu Bar Status Item (RAM Footprint Tracker)     โ”‚
โ”‚  โ””โ”€ ๐Ÿ“ฆ Universal 1-Click Config Backup & Diff Engine          โ”‚
โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜
                                โ–ผ
โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”
โ”‚   Shared Server Pool: SSH | K8s | Tabularis | Grafana | AWS   โ”‚
โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜

Related MCP server: Shared MCP Gateway

โœจ Features

  • ๐ŸŽ๏ธ ~83% Memory Footprint Reduction: Consolidates 15+ duplicate MCP runtime child processes into a single shared pool (~85 MB total vs ~520 MB duplicate).

  • โšก Sub-5ms Execution Latency: Persistent, pre-warmed JSON-RPC connection pooling delivers median P50 response times under 2 ms.

  • ๐Ÿ–ค Vercel-Inspired Live Console:

    • Pure black dark theme & crisp light theme with instant switcher.

    • Custom UI & monospace code font customizer (Geist, Inter, Fira Code, JetBrains Mono).

    • Real-time Server-Sent Events (SSE) tool activity feed.

    • Interactive Tool Execution Sandbox for instant JSON-RPC testing.

  • ๐Ÿ Native macOS Menu Bar App:

    • โšก MCP ๐ŸŸข status item in the macOS status bar.

    • Live RAM savings counter.

    • 1-click dashboard launcher and background process management.

  • ๐Ÿ›ก๏ธ Universal 1-Click Backup & Restore:

    • Automatically snapshots configurations across Codex (~/.codex/config.toml), Claude Desktop (claude_desktop_config.json), Antigravity, and OpenCode with SHA-256 integrity manifests and interactive visual diffs.

  • ๐Ÿค– Multi-Agent Compatibility: Works with Codex (ChatGPT), Claude Code / Claude Desktop, Google Antigravity, and OpenCode / Codeg out of the box.


๐Ÿ“Š Benchmark Telemetry

Real benchmark metrics collected across 20 serial and 20 parallel (5 concurrent threads) read-only tool calls (ssh-manager, kubernetes-readonly, tabularis):

Metric

Serial Execution (20 calls)

Parallel Execution (5 Threads)

Total Duration

0.369 s

0.240 s

Throughput

54.24 calls/sec

83.21 calls/sec

Success Rate

100.0% (20/20)

100.0% (20/20)

P50 (Median) Latency

1.36 ms

3.10 ms

P95 Latency

181.28 ms

164.89 ms

Net Memory Saved

~435 MB (from ~520 MB down to ~85 MB, 83.6% reduction)


๐Ÿš€ Quickstart

1. Installation

# Clone repository
git clone https://github.com/dhomane/supergateway-pro.git
cd supergateway-pro

# Install Node and Python dependencies
npm install
pip install -r requirements.txt

2. Start the Gateway Daemon

# Start SuperGateway server on http://127.0.0.1:8080
node gateway_server.js

Open http://localhost:8080/ in your browser to access the Vercel-style live activity dashboard.

3. Launch macOS Menu Bar App (Optional)

python3 menubar_cocoa.py

๐Ÿ”Œ AI Agent Integration

A. Codex (ChatGPT)

Add the proxy to ~/.codex/config.toml:

[mcp_servers.supergateway]
command = "node"
args = ["/path/to/supergateway-pro/unified_mcp_server.js"]
enabled = true

B. Claude Desktop

Add the proxy to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "supergateway": {
      "command": "node",
      "args": ["/path/to/supergateway-pro/unified_mcp_server.js"]
    }
  }
}

๐Ÿ“ฆ Universal Backup & Restore Suite

# Create a timestamped safety backup snapshot
python3 mcp_backup_manager.py backup --tag "my_checkpoint"

# View diff between current active configs and latest backup
python3 mcp_backup_manager.py diff

# List all available backup snapshots
python3 mcp_backup_manager.py list

# Restore from latest (or specific) snapshot
python3 mcp_backup_manager.py restore

๐Ÿงช Running Benchmarks

python3 benchmark_mcp.py

๐Ÿ“‹ Checklist & Roadmap

  • Centralized JSON-RPC & SSE proxy router

  • Vercel-style real-time web console with SSE streaming

  • Light / Dark theme switcher with persistence

  • Custom UI and code font customizer

  • Native macOS status bar tray app (AppKit / PyObjC)

  • Universal 1-click config backup & diff engine

  • Codex & Claude Desktop stdio client proxies

  • Automated latency & throughput benchmark suite

  • Agent Skill (SKILL.md) integration


๐Ÿ“„ License

MIT ยฉ SuperGateway Contributors

F
license - not found
Not graded
quality - not tested
C
maintenance

Maintenance

โ€“Maintainers
โ€“Response time
โ€“Release cycle
โ€“Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • A
    license
    Not graded
    quality
    Not graded
    maintenance
    A unified gateway and dashboard that aggregates multiple MCP servers into a single endpoint for streamlined management by AI clients. It features a centralized YAML configuration, a web-based monitoring dashboard, and hot-reload support for managing filesystem, GitHub, and database tools.
  • F
    license
    Not graded
    quality
    C
    maintenance
    Aggregates multiple shared MCP servers into a single HTTP gateway, providing a unified, observable, and reusable MCP access layer for multiple AI clients like Codex, OpenCode, and OpenClaw. It centralizes configuration management, logging, health checks, and circuit breaking to simplify multi-client MCP deployments.
    5
  • A
    license
    A
    quality
    A
    maintenance
    One local gateway for all your MCP servers โ€” shared by every AI coding tool (Claude, Cursor, VS Code, Codex). Set up each server once; keys stay in the OS keychain; lazy discovery keeps agent context small. Local-first, open source.
    4
    204
    184
    MIT

View all related MCP servers

Related MCP Connectors

  • Real-time chat hub for AI agents โ€” Claude Code, Cursor, Cline, Codex over MCP or REST.

  • Hosted MCP server for LLM cost estimation, model comparison, and budget-aware routing.

  • Self-hosted MCP gateway: turn any API, database or MCP server into AI connectors โ€” no code.

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/dhomane/supergateway-pro'

If you have feedback or need assistance with the MCP directory API, please join our Discord server