What is Remote Mcp Ssojet

remote-mcp-ssojet is a Model Context Protocol (MCP) server powered by SSOJet, providing developers with programmatic access to enterprise Single Sign-On (SSO) capabilities. It allows applications to authenticate users and manage authorization through various identity providers without the need for complex custom SSO integrations.

Use cases

Use cases for remote-mcp-ssojet include enabling SSO for enterprise applications, integrating user authentication in web services, and providing secure access to sensitive tools and data for authenticated users.

How to use

To use remote-mcp-ssojet, developers need to set up an SSOJet application, configure the necessary environment variables, and ensure that the server is properly set up to handle authentication requests. Users must sign in via SSOJet to access secure tools provided by the server.

Key features

Key features of remote-mcp-ssojet include seamless integration with multiple identity providers, simplified user authentication and authorization management, and the ability to utilize secure tools like the ‘add’ tool after successful authentication.

Where to use

remote-mcp-ssojet can be used in various fields where secure user authentication is required, such as web applications, enterprise software, and any system that needs to manage user access through SSO.

Model Context Protocol (MCP) Server (SSOJet)

This is a Model Context Protocol (MCP) server powered by SSOJet for authentication. Users must first sign in with SSOJet. Once authenticated, they can access and use secure tools such as the add tool exposed by this server.

Configuration

SSOJet Setup

1. Go to your SSOJet dashboard.
2. Create a new Single page web application.
3. Set the callback URL for local development:

http://localhost:8788/callback

4. Note the following details from your app:

   • Client ID
   • Client Secret
   • Issuer URL (e.g. https://<your-tenant>.auth.ssojet.com/v1/)

These will be used to configure your server.

Set up a KV Namespace

This project uses a Cloudflare KV namespace to store token metadata:

wrangler kv:namespace create "OAUTH_KV"

Then, add the KV binding to your wrangler.jsonc.

Environment Variables

The following environment variables must be configured to run the server:

Development

Create a .dev.vars file in the root of your project:

SSOJET_CLIENT_ID=<your_ssojet_client_id>
SSOJET_CLIENT_SECRET=<your_ssojet_client_secret>
SSOJET_ISSUER=https://<your-tenant>.auth.ssojet.com/v1/
SSOJET_SCOPE="openid profile email"
NODE_ENV=development

Then run the MCP server locally:

npm run dev

Tool Available

The server currently provides a single tool:

Once the user signs in via SSOJet, this tool becomes accessible through compatible MCP clients such as the Workers AI LLM Playground.

Testing with MCP Inspector

You can test your server locally with MCP Inspector:

1. Set the Transport to sse

2. Set the URL to:

   http://localhost:8788/sse
   

3. A popup will appear for SSOJet authentication

4. Once logged in, you’ll see the available tools

Deploying to Cloudflare

Before deploying, set the necessary secrets in your Cloudflare environment:

wrangler secret put SSOJET_CLIENT_ID
wrangler secret put SSOJET_CLIENT_SECRET
wrangler secret put SSOJET_ISSUER
wrangler secret put SSOJET_SCOPE

Deploy with:

npm run deploy

Then, in the SSOJet dashboard, add your deployed callback URL:

https://mcp-ssojet-oidc.<your-subdomain>.workers.dev/callback

To use the deployed server with MCP Inspector or the LLM Playground, use this endpoint:

https://mcp-ssojet-oidc.<your-subdomain>.workers.dev/sse

Troubleshooting

Cloudflare Worker Logs

You can inspect logs and errors using Cloudflare’s observability dashboard:

🔗 Cloudflare Workers Logs

SSOJet Logs

Visit your SSOJet dashboard and check the Logs section to diagnose authentication issues.

Common Issues

• ❌ Invalid credentials: Double-check that secrets match your SSOJet application.
• ❌ Missing callback URL: Ensure all callback URLs are added in your SSOJet dashboard.
• ❌ Tool not showing: Make sure you’re authenticated and using the correct endpoint.
• ❌ Local connection failed: Ensure the MCP server is running on http://localhost:8788.