ACTIVE DEVELOPMENT - WORK IN PROGRESS

Name: ACTIVE DEVELOPMENT - WORK IN PROGRESS
Author: agentic-community

@agentic-community

代码仓库

关于 ACTIVE DEVELOPMENT - WORK IN PROGRESS

MCP Gateway and Registry

#mcp #agents #agentic-ai #mcp-server #mcp-gateway #mcp-registry

基本信息

分类

其他

许可证

Apache-2.0 license

运行时

python

传输方式

stdio

发布者

agentic-community

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "mcp-gateway-registry": {
      "command": "docker",
      "args": [
        "build",
        "-t",
        "mcp-gateway",
        "."
      ]
    }
  }
}

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is MCP Gateway & Registry?

MCP Gateway & Registry is a unified platform that combines centralized access control with intelligent tool discovery for Model Context Protocol (MCP) servers. It consists of a Registry providing visual and programmatic interfaces for exploring available MCP servers and tools, and a Gateway (NGINX reverse proxy) ensuring secure, governed access to all services. It is designed for enterprises and developers building AI agents that need to discover, access, and manage multiple MCP servers through a single endpoint.

How to use MCP Gateway & Registry?

Deploy the Gateway and Registry on Amazon EC2 or Amazon EKS. For EC2, clone the repository, build the Docker container, and run it with environment variables for admin credentials and API keys. Access the Registry web UI at http://localhost:7860. AI agents connect to MCP servers via the Gateway's single endpoint by appending the server-specific path (e.g., https://my-mcp-gateway.enterprise.net/weather/). The Gateway supports both SSE and Streamable HTTP transports.

Key features of MCP Gateway & Registry

MCP tool discovery via natural language queries
Unified access to a governed list of MCP servers
Service registration via JSON files, web UI, or API
Web UI for managing services, status, and health
Secure login for web UI and API access
Periodic health checks with real-time WebSocket updates
Dynamic NGINX reverse proxy configuration generation

Use cases of MCP Gateway & Registry

Centralize enterprise MCP server access behind a single secure gateway
Enable AI agents to dynamically discover and invoke new tools
Govern which MCP servers are available to developers and agents
Simplify multi-server MCP client configuration for agent frameworks

FAQ from MCP Gateway & Registry

What runtime dependencies are required?

An Amazon EC2 instance (recommended ml.t3.2xlarge) with Ubuntu, Docker, and an SSL certificate (self-signed or real). Example MCP servers may require third-party API keys (e.g., Polygon.io).

Which MCP transports are supported?

The Gateway supports both SSE (Server‑Sent Events) and Streamable HTTP transports.

Can I deploy on Kubernetes?

Yes, the repository provides installation instructions for Amazon EKS (Elastic Kubernetes Service) for production environments.

Is authentication supported?

Yes, the Registry includes a secure login system for both the web UI and API access.

What is the current stability of the project?

The repository is under active development with frequent updates and breaking changes. The API is considered experimental. Pin to specific versions for production use.