How do I install MCP Middleware Adapter for Express Servers?
Install it using npm, yarn, or pnpm: `npm install mcp-express-adapter@latest`. Note that if installing from a private GitHub Packages registry, you must authenticate.
@Moe03
基本信息
Run multiple MCP clients on a NodeJS Express server (adapter/middleware)
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"mcp-express-adapter": {
"command": "npx",
"args": [
"mcp-express-adapter@latest",
"--host",
"http://localhost:3000/mcp/sse",
"--header",
"Authorization: Bearer 000000"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
点击上方按钮,在临时沙箱中运行此服务器并实时获取工具列表。
It is a lightweight adapter that creates MCP (Model Context Protocol) servers using Express.js, allowing developers to host and serve MCP tools via SSE (Server-Sent Events) on an Express server. It targets developers who need to deploy, scale, and maintain multiple MCP clients efficiently.
Install via npm with npm install mcp-express-adapter@latest. Then define tools using the mcpTool helper with Zod schemas, create an MCPClient with an endpoint and tools, mount its middleware on an Express app, and connect to the SSE endpoint (e.g., http://localhost:3000/mcp/sse). To test with Claude Desktop, configure mcpServers using npx -y mcp-express-adapter --host <url>.
@langchain/mcp-adaptersInstall it using npm, yarn, or pnpm: `npm install mcp-express-adapter@latest`. Note that if installing from a private GitHub Packages registry, you must authenticate.
Currently only SSE (Server‑Sent Events) is implemented and working. WebSocket support is planned but not yet available.
Yes, you can create multiple `MCPClient` instances, each with a different endpoint (e.g., `/weather-mcp`, `/calculator-mcp`), and mount their middleware separately.

Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.

Catch intent conflicts before code conflicts. The open-source coordination protocol for coding agents, built above Git.

Let your cloud agents talk to you. Grok Bot, Meta Muse, ChatGPT, Claude, Devin and others report progress to Heard, which reads it out loud on your Mac, and they pick up the replies you send back.

Turn Perfex CRM into an AI-ready workspace. This MCP server exposes your full REST API to Claude, ChatGPT and any AI agent, so leads, invoices and tasks are one prompt away.

SSH MCP server for AI agents: remote commands, file transfer, log search and server audits through OpenSSH.
评论