MCP | Blog | PropelAuth

MCP Posts

Articles and insights about MCP from the PropelAuth team.

Authentication and Authorization for Internal MCP Servers

Picture this: You’ve just built a brilliant Model Context Protocol (MCP) server. It’s the ultimate internal powerhouse, seamlessly bridging your organization’s LLMs with your most sensitive private repositories, production databases, and internal APIs. It feels like magic.

MCP Organization Scopes in PropelAuth

As MCP (Model Context Protocol) becomes the standard way users connect AI assistants like Claude and ChatGPT to SaaS products, one question is becoming crucial to define organization scopes effectively within PropelAuth.

Building Custom UIs with Shadcn and PropelAuth’s Integration MCP Server

With our recent release of the PropelAuth Integration MCP server, we wanted to put it plus our shadcn component registry to the test by building some custom user interfaces.

PropelAuth Integration MCP Server

We keep track of a lot of metrics at PropelAuth, but one of the most important metrics is time to integrate. How long does it take from when someone starts using our services to when they can effectively implement MCP?

Deep dive into OAuth 2.1 and MCP using Cloudflare Workers

Model Context Protocol (MCP) servers are a convenient way to allow AI applications (Claude, Gemini, ChatGPT, etc.) to connect to your product. We'll explore how OAuth 2.1 fits into the framework of an effective MCP setup.

Production-ready MCP server using Cloudflare Workers

Model Context Protocol (MCP) servers are a convenient way to allow AI applications (Claude, Gemini, ChatGPT, etc.) to connect to your product. In this article, we discuss best practices for deploying production-ready MCP servers.

Guide to understanding MCP with examples

Model Context Protocol (MCP) is a standard for connecting AI applications (ChatGPT, Claude, Gemini, OpenCode) to external systems (Google, GitHub, YouTube, etc.). Here we provide examples to aid understanding.

MCP Authentication with FastMCP

MCP servers are just a clean way to give an AI client (like Claude Desktop, Claude Code, ChatGPT, etc) a set of functions it can call. This can really streamline the process of integrating AI solutions into existing workflows.

Why does DCR matter for MCP?

Model Context Protocol (MCP) is a standard for connecting AI applications (Claude, ChatGPT, Gemini) to external applications (Linear, Google Calendar, etc.). Understanding Dynamic Client Registration (DCR) is crucial to leveraging the full potential of MCP.

What is Dynamic Client Registration?

Dynamic Client Registration (DCR) is an extension of OAuth that allows OAuth clients to be created programmatically. It wasn’t a very popular extension initially, but its importance has grown as more services look for dynamic integrations.