How is eMCP different from LiteMCP?
eMCP extends LiteMCP with an optional built‑in authentication handler and a custom middleware system, while remaining a near drop‑in replacement.
@joeymeere
基本情報
A framework for building simple MCP servers with custom middleware
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": {
"emcp": {
"command": "bun",
"args": [
"run",
"example:basic"
]
}
}
}ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
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。
eMCP is a fork of the LiteMCP TypeScript library that adds built-in authentication handling and custom layered middleware support. It is designed as a near drop-in replacement for LiteMCP, with all added features being optional.
Install via npm or Bun (npm i emcp or bun add emcp). You can run provided examples (bun run example:basic, bun run example:auth, etc.). Create a server instance by passing an authenticationHandler function and use server.use() to add custom middleware that runs before and after the standard MCP handler.
eMCP extends LiteMCP with an optional built‑in authentication handler and a custom middleware system, while remaining a near drop‑in replacement.
Middleware runs in the order it was registered. Each middleware calls `next()`, then the standard MCP handler runs. After the handler completes, middleware code after `next()` executes in reverse order.
eMCP is a TypeScript library that requires Node.js with npm or Bun. It is installed via `npm i emcp` or `bun add emcp`.
No, the authentication handler is optional. If not set, requests proceed without authentication.
The README does not mention specific transports; it inherits the transport capabilities of LiteMCP (e.g., stdio, SSE).
MCP Toolbox for Databases is an open source MCP server for databases.
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.

Soar Flight Booking MCP is a remote MCP server available at https://mcp.soar.flights.
コメント