A reverse proxy gateway for managing and accessing multiple MCP servers through a single entry point, deployable via Docker.
The MCP gateway is a reverse proxy server that forwards requests from clients to the MCP server or uses all MCP servers under the gateway through a unified portal.
At present, STDIO turns to the supergateway used by SSE, and we will implement this function ourselves later https://github.com/supercorp-ai/supergateway
docker pull ghcr.io/lucky-aeon/mcp-gateway:latest
docker build -t mcp-gateway .
run github docker container
docker run -d --name mcp-gateway -p 8080:8080 ghcr.io/lucky-aeon/mcp-gateway
run self build docker container
docker run -d --name mcp-gateway -p 8080:8080 mcp-gateway
support: uvx, npx. or sse url
POST /deploy HTTP/1.1
Host: localhost:8080
Content-Type: application/json
{
"mcpServers": {
"time": {
"url": "http://mcp-server:8080", // url 和 command 二选一
"command": "uvx", // url 和 command 二选一
"args": ["mcp-server-time", "--local-timezone=America/New_York"], // 可选,command 的参数
"env": { // 可选,环境变量
"KEY1": "VALUE1",
"KEY2": "VALUE2"
}
}
}
}
GET /{mcp-server-name}/sse HTTP/1.1
Host: localhost:8080
POST /{mcp-server-name}/message HTTP/1.1
Host: localhost:8080
Content-Type: application/json
{
"method": "tools/call",
"params": {
"name": "get_current_time",
"arguments": {
"timezone": "Asia/Seoul"
}
},
"jsonrpc": "2.0",
"id": 2
}
网关和直连MCP的区别在于,只需要与网关交互,网关会自动将请求转发到对应的MCP服务器。在call 时,需要在method前面添加 mcpServerName
内容,标识该请求来自哪个 MCP 服务器。
GET /sse HTTP/1.1
Host: localhost:8080
这里 sse 是整个网关下所有的 MCP 服务器的 SSE 流。
当客户端订阅 sse 时,网关会为每个 MCP 服务器创建一个 SSE 连接,并将所有 MCP 服务器的 SSE 流合并到一起。
在响应的所有tools/call 的结果中,会在method前面添加 mcpServerName
内容,标识该结果来自哪个 MCP 服务器。
POST /message HTTP/1.1
Host: localhost:8080
Content-Type: application/json
{
"method": "tools/call",
"params": {
"name": "{mcp-server-name}-get_current_time",
"arguments": {
"timezone": "Asia/Seoul"
}
},
"jsonrpc": "2.0",
"id": 2
}
获取网关下所有工具
POST /message HTTP/1.1
Host: localhost:8080
Content-Type: application/json
{
"method": "tools/list",
"jsonrpc": "2.0",
"id": 1
}
# SSE 响应 message event
{
"jsonrpc": "2.0",
"id": 1,
"result": {
"tools": [
{
"name": "{mcpServerName}-get_current_time",
"description": "Get current time in a specific timezones",
"inputSchema": {
"type": "object",
"properties": {
"timezone": {
"type": "string",
"description": "IANA timezone name (e.g., 'America/New_York', 'Europe/London'). Use 'America/New_York' as local timezone if no timezone provided by the user."
}
},
"required": [
"timezone"
]
}
},
{
"name": "{mcpServerName}-convert_time",
"description": "Convert time between timezones",
"inputSchema": {
"type": "object",
"properties": {
"source_timezone": {
"type": "string",
"description": "Source IANA timezone name (e.g., 'America/New_York', 'Europe/London'). Use 'America/New_York' as local timezone if no source timezone provided by the user."
},
"time": {
"type": "string",
"description": "Time to convert in 24-hour format (HH:MM)"
},
"target_timezone": {
"type": "string",
"description": "Target IANA timezone name (e.g., 'Asia/Tokyo', 'America/San_Francisco'). Use 'America/New_York' as local timezone if no target timezone provided by the user."
}
},
"required": [
"source_timezone",
"time",
"target_timezone"
]
}
}
]
}
}
Fetches comprehensive information about Composer packages from Packagist, including READMEs, metadata, and search functionality.
A toolkit for interacting with the Sui blockchain and integrating MCP SDK features, with support for multiple network environments.
Gru-sandbox(gbox) is an open source project that provides a self-hostable sandbox for MCP integration or other AI agent usecases.
An MCP server that integrates with Ollama to provide tools for file operations, calculations, and text processing. Requires a running Ollama instance.
Test web pages and HTML for accessibility issues and WCAG compliance using Axe-core and Puppeteer.
Execute secure shell commands from AI assistants and other MCP clients, with configurable security settings.
Retrieves essential network information from devices using gNMI and OpenConfig models.
An AI-driven platform for frontend semantic cognition and automation.
An integrated MCP server combining Azure DevOps, Gmail, Browser, and Gemini AI functionalities on a Node.js server.
A server for JavaScript/TypeScript development with intelligent project tooling and testing capabilities.