What is this project?
It is a proof of concept (PoC) for a custom MCP OAuth flow using Next.js, Neon, Upstash Redis, and Neon Auth.
@andrelandgraf
基本情報
PoC of an MCP server in a Next.js app with Neon Auth and custom OAuth flow for MCP.
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": {
"echo": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://neon-auth-mcp-oauth-6zf3o859s-andrelandgraf.vercel.app"
]
}
}
}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。
上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。
A proof-of-concept implementation of a custom MCP OAuth flow built with Next.js, Neon, Upstash Redis, and Neon Auth. It is designed for developers who want to experiment with MCP authentication using Neon Auth and OAuth.
Add the provided MCP configuration to Cursor, Windsurf, Claude Desktop, or any MCP client. For local development, replace the URL in the config with http://localhost:3000/api/v1/mcp and run npm run dev.
It is a proof of concept (PoC) for a custom MCP OAuth flow using Next.js, Neon, Upstash Redis, and Neon Auth.
You need to set up a Neon database and Neon Auth, deploy to Vercel, and configure Upstash Redis via the Vercel Upstash Integration. Environment variables are required (see `./lib/config.ts`).
Run `rm -rf ~/.mcp-auth` to clear stored authentication data from the `mcp-remote` package. MCP auth is noted as still flaky.
Yes, clone the repository, set up the environment, and run `npm run dev`. Use `npm run playground` to start the MCP Inspector for debugging.
It uses a custom OAuth flow over HTTP/HTTPS (the MCP server endpoint is `/api/v1/mcp`). Authentication is handled via Neon Auth and OAuth tokens.

MCP server for AI Agents — exposes Yocoolab feedback threads and design selections as tools

Nebelus is an enterprise agentic-AI platform for regulated industries. This MCP server exposes the Nebelus Construction API: ~48 tools that give an MCP client full agent build parity — create/update/probe agents, edit ag

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

The BetterBugs MCP (Model Context Protocol) enables you to load BetterBugs bug reports (via report links) directly to your preferred AI Agents and developer environments with MCP Client capabilities (such as Cursor, VS C

The tools your AI needs to make your games. Turn prompts into production-ready game assets — animated characters with their weapons attached, seamless textures, terrain, VFX, HUDs — and playable game kits Unity, Godot, U
コメント