mcpauth
Drop-in OAuth 2.1 + Dynamic Client Registration for MCP servers, providing authentication middleware and token verification.
README
mcpauth
Drop-in OAuth 2.1 + Dynamic Client Registration (RFC 7591) for MCP servers, backed by mcpauth.
Wraps the official @modelcontextprotocol/sdk's requireBearerAuth middleware so unauthenticated or invalid requests get rejected with a spec-correct 401 before they ever reach your MCP server's handlers.
Install
npm install getmcpauth
Usage
import express from "express";
import { mcpAuth } from "getmcpauth";
const app = express();
app.use(
"/mcp",
mcpAuth({ registrationSecret: process.env.MCPAUTH_SECRET })
);
// Unauthenticated or invalid requests never reach this handler.
app.post("/mcp", handleMcpRequest);
Get a registrationSecret by creating a project at getmcpauth.dev/dashboard — it's your MCP server's credential for both Dynamic Client Registration and token verification.
MCP clients (Claude, ChatGPT, custom agent frameworks) then discover your auth setup automatically via /.well-known/oauth-authorization-server — no manual client configuration needed.
Next.js (or any Fetch-API framework)
// app/api/mcp/route.ts
import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
import { createMcpAuthHandler } from "getmcpauth";
const handler = createMcpAuthHandler({
registrationSecret: process.env.MCPAUTH_SECRET!,
buildServer: () => {
const server = new McpServer({ name: "my-server", version: "1.0.0" });
server.registerTool(/* ... */);
return server;
},
});
export { handler as GET, handler as POST, handler as DELETE };
API
mcpAuth(options)— Express middleware. Successful token verifications are cached in-process (default 30s) so a chatty agent conversation doesn't trigger a network round trip on every tool call.createMcpAuthHandler(options)— the Next.js/Fetch-API equivalent above, returning a(request: Request) => Promise<Response>handler. Same caching behavior asmcpAuth().McpAuthTokenVerifier— implements the official SDK'sOAuthTokenVerifierinterface directly, for lower-level use.mintToken(options)— for MCP servers embedded in a product that already has its own users: your backend, which already knows who its logged-in user is, mints a token server-to-server without routing that user through mcpauth's own login.protectedResourceMetadata(options)/mcpAuthResourceMetadataHandler(options)— RFC 9728 resource-metadata helpers.
Full docs: getmcpauth.dev/docs
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.