ACTIVE DEVELOPMENT - WORK IN PROGRESS
@agentic-community
ACTIVE DEVELOPMENT - WORK IN PROGRESS について
MCP Gateway and Registry
基本情報
設定
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"mcp-gateway-registry": {
"command": "docker",
"args": [
"build",
"-t",
"mcp-gateway",
"."
]
}
}
}ツール
ツールは検出されませんでした
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
概要
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.
「その他」の他のコンテンツ
Awesome Mlops
visengerA curated list of references for MLOps
Blender
ahujasidOpen-source MCP to use Blender with any LLM
ghidraMCP
LaurieWiredMCP Server for Ghidra
ACI: Open-Source Infra to Power Unified MCP Servers
aipotheosis-labsACI.dev is the open source tool-calling platform that hooks up 600+ tools into any agentic IDE or custom AI agent through direct function calling or a unified MCP server. The birthplace of VibeOps.
XcodeBuildMCP
cameroncookeA Model Context Protocol (MCP) server and CLI that provides tools for agent use when working on iOS and macOS projects.
コメント