MCP 服务器

Universal MCP OAuth Gateway

A deployable serverless MCP OAuth gateway and proxy that adds OAuth 2.0 authentication to Excalidraw tools or any external MCP server, enabling secure connections from clients like Google Spark and Gemini.

README

Universal MCP OAuth Gateway (with Excalidraw & Proxy Support)

A deployable, serverless Universal Model Context Protocol (MCP) OAuth Gateway & Proxy built on Next.js 14.

This project allows you to attach OAuth 2.0 authentication to Excalidraw OR ANY external MCP server so enterprise clients like Google Spark & Gemini Agents can connect seamlessly without OAuth rejection errors.

How It Works

[Google Spark Client] ──(OAuth 2.0 Auth + Discovery)──> [Universal MCP OAuth Gateway on Vercel]
                                                                  │
                                       ┌──────────────────────────┴──────────────────────────┐
                                       ▼                                                     ▼
                     [Built-in Tools: Excalidraw, SVG, Mindmaps]      [Proxy Mode: Any External Remote MCP Server]

Features

🔐 Universal OAuth 2.0 Auth Server: Implements /.well-known/oauth-authorization-server and /.well-known/openid-configuration with RFC 7591 dynamic client registration.
🌐 MCP Server & Proxy Gateway:
- Mode 1 (Built-in): Excalidraw tools (create_diagram, generate_flowchart, generate_mindmap, export_svg, view_diagram) & web utilities.
- Mode 2 (Universal Proxy): Proxies JSON-RPC 2.0 requests to any unauthenticated remote MCP server specified via UPSTREAM_MCP_URL or X-MCP-Target-URL.
🖼️ Interactive Web Viewer: Embedded viewer at /view/[id] allowing users & AI agents to inspect, copy, and download rendered Excalidraw diagrams as SVG.
⚡ 100% Vercel Native: Uses stateless JWT tokens—no database setup required.

Google Spark Connection & Deployment Instructions

Step 1: Deploy to Vercel

Push this repository to GitHub.
Import the project into Vercel.
(Optional for Proxy Mode): If you want to proxy another unauthenticated MCP server, add an Environment Variable in Vercel:
```
UPSTREAM_MCP_URL = https://your-other-mcp-server.com/api/mcp
```
Click Deploy. Vercel will assign a public domain, e.g.: https://your-mcp-gateway.vercel.app

Step 2: Connect to Google Spark / Gemini

In Google Spark, select Add Remote MCP Server.

Enter your deployed MCP Endpoint URL:

https://your-mcp-gateway.vercel.app/api/mcp

Google Spark automatically discovers the OAuth endpoints at:

https://your-mcp-gateway.vercel.app/.well-known/oauth-authorization-server

Complete the one-click authorization prompt. Google Spark can now invoke tools from Excalidraw or your proxied MCP server!

API Endpoints

Endpoint	Description
`GET /.well-known/oauth-authorization-server`	OAuth 2.0 Server Discovery Metadata (RFC 8414)
`GET /.well-known/openid-configuration`	OpenID Connect Discovery Metadata
`POST /api/auth/register`	RFC 7591 Dynamic Client Registration
`GET /api/auth/authorize`	OAuth Authorization endpoint
`POST /api/auth/token`	OAuth Token Exchange endpoint
`POST /api/mcp`	MCP HTTP JSON-RPC 2.0 Tool Execution / Proxy Endpoint
`GET /api/mcp/sse`	MCP Server-Sent Events Transport
`GET /view/[id]`	Interactive Excalidraw Canvas Viewer