MCP Server Hub / Gateway

Created By
bsmi021a year ago
This project provides a central gateway to manage multiple MCP (Model Context Protocol) servers, preventing the need to configure and run duplicate server processes for each LLM client (like Cline, Cursor, etc.). Connect your LLM client to the single gateway-client endpoint provided by this project to access tools from all your managed MCP servers
Overview

What is MCP Server Hub / Gateway?

MCP Server Hub / Gateway is a project that provides a central gateway to manage multiple Model Context Protocol (MCP) servers, allowing users to connect their LLM clients to a single endpoint without the need for duplicate server processes.

How to use MCP Server Hub / Gateway?

To use the MCP Server Hub, clone the repository, install dependencies, build the project, configure the mcp_hub_config.json file, and start the server. Connect your LLM client to the gateway-client endpoint to access tools from all managed MCP servers.

Key features of MCP Server Hub / Gateway?

  • Centralized management of multiple MCP servers.
  • Dynamic configuration reloading without server restarts.
  • WebSocket support for real-time communication with LLM clients.
  • Namespaced tool access for organized tool management.

Use cases of MCP Server Hub / Gateway?

  1. Managing multiple LLM clients like Cline and Cursor through a single gateway.
  2. Dynamically updating server configurations and tools without downtime.
  3. Simplifying the integration of various tools and services in a unified interface.

FAQ from MCP Server Hub / Gateway?

  • What is the purpose of the MCP Server Hub?

It centralizes the management of multiple MCP servers, making it easier to connect LLM clients to various tools.

  • Is it necessary to configure each MCP server individually?

No, you can manage all servers through the central gateway configuration.

  • Can I use this with any LLM client?

Yes, as long as the client supports the Model Context Protocol.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
bsmi021
Star
0
Language
TypeScript
License
GPL-3.0 license

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago