February 2026 Summaries

PropelAuth offers hosted authentication pages such as Login UI, Signup UI, and organization management pages, which can be customized through their dashboard or Terraform. While these default interfaces are useful, some customizations require direct code modifications, prompting the introduction of the shadcn/ui component library. This library allows developers to create and fully customize frontend components, such as custom login screens, by accessing and editing the code directly. For instance, developers can enhance user experience by integrating visual elements like a Three.js ocean background. The platform also provides components for two-factor authentication, password recovery, and single sign-on processes, all of which can be integrated seamlessly into applications. Additionally, the PropelAuth Integration MCP server offers guidance for AI coding agents to utilize these components effectively, facilitating the creation of personalized authentication experiences.

PropelAuth emphasizes the importance of reducing the time it takes for users to integrate its services into their products, continuously refining processes to achieve this goal. Enhancements include developing custom client libraries for popular frameworks like React, FastAPI, and Next.js, creating an onboarding CLI for automated integration steps, and personalizing documentation through framework pickers. The latest advancement is the PropelAuth Integration MCP Server, designed to streamline and expedite the integration process using AI agents. This server ensures AI agents have optimal context, facilitating rapid integration in various projects. Users are encouraged to explore the documentation for incorporating this tool and to provide feedback on its effectiveness.

PropelAuth provides comprehensive audit logs that help organizations track and analyze important events within their authentication systems, enhancing security and facilitating issue resolution. These logs are divided into Project, User, and Organization categories, each offering specific filters such as event type, date, and the user or employee responsible for the action. This functionality allows teams to pinpoint changes in configurations, user activities, and organizational settings, thereby addressing inquiries and debugging issues efficiently. Advanced features available on the Growth+ plan include Impersonation and User Facing Audit Logs, which provide additional visibility into employee actions and allow audit information to be shared with end users. PropelAuth also supports exporting audit logs to platforms like Datadog and Amazon S3, ensuring that organizations can maintain detailed records of critical events and enhance their operational transparency.

When building a B2B product, a critical architectural decision involves defining how to separate customers, often referred to as "organizations" or "tenants," which establishes clear user group boundaries. PropelAuth offers flexible organizational structures similar to platforms like GitHub and Slack, where users can belong to multiple organizations with role-based access control and customizable policies. However, for scenarios requiring stronger user isolation, such as distinct identity management for enterprise customers or maintaining separate accounts for different organizational contexts, isolated organizations provide complete separation by ensuring users can only exist within one organization. This model is particularly beneficial for enterprises needing strict data boundaries and simplified Single Sign-On (SSO) processes. Despite these varying needs, both standard and isolated organizations can coexist within the same project, allowing companies to adapt their isolation levels according to customer requirements and seamlessly transition between organizational models through PropelAuth's dashboard or API.

Setting up a Model Context Protocol (MCP) server provides a streamlined method for AI applications like Claude, Gemini, and ChatGPT to interact with various products through function calls. This blog post describes the process of building an MCP server using a Cloudflare Worker, focusing on creating a basic server with a calculator tool capable of performing arithmetic operations. Key steps include configuring the server with necessary dependencies, setting up authentication and authorization using OAuth 2.1 via PropelAuth, and ensuring security by validating client credentials and consented scopes. The server is tested with Claude Desktop, demonstrating the workflow of requesting and processing tool calls. This setup not only facilitates basic operations like calculations but can be extended to more complex real-world applications, such as querying SEO data or managing calendar events, by integrating with existing APIs.

Setting up a Model Context Protocol (MCP) server allows AI applications like Claude, Gemini, and ChatGPT to interact with your product, and this blog post outlines the process of developing a basic MCP server using a Cloudflare Worker. The guide walks through creating a simple calculator tool within the server, which handles basic math operations, and details the integration of necessary dependencies such as @modelcontextprotocol/sdk, Cloudflare's Agent library, and the validation library zod. Once the server is functional, the post addresses authentication and authorization by introducing PropelAuth as an MCP authorization server, enabling OAuth 2.1 compliance, and detailing how to validate AI client requests. Additionally, it emphasizes the importance of secure connections and proper scope management to ensure only authorized users can perform certain actions. The blog also discusses the full workflow of an authenticated interaction between an AI client and the MCP server, offering real-world use cases where such a setup could be beneficial, such as querying SEO data with Ahrefs or managing calendar operations with Google Calendar MCP servers.

Model Context Protocol (MCP) is a standardized protocol that facilitates the integration of AI applications, such as ChatGPT and Claude, with external systems like CRM tools or other services, enabling users to perform complex operations through AI clients by exposing functions called "tools." This standard allows AI to interact with your product's APIs and conduct tasks on behalf of users, like querying CRM data or integrating with services such as Crunchbase or Gmail for enhanced workflows. MCP servers can operate locally or remotely, with local servers interacting directly with the user's machine and remote servers often requiring authentication via OAuth 2.1 to ensure secure operations. The protocol's design allows multiple AI clients to understand and interact with an MCP server, promoting interoperability and enabling seamless, multi-system operations. PropelAuth offers a service to handle authentication complexities, allowing developers to focus on implementing core functionalities like search or update actions without dealing with the intricacies of login, consent, and token management.

An MCP server is a structured way to provide AI clients with callable functions, such as fetching weather data or managing a calendar, by creating a secure and authenticated environment. Initially built as an unauthenticated server using FastMCP in Python, it establishes a local endpoint that AI clients can connect to through a tunnel service like ngrok. The server is tested with AI clients like Claude Desktop, demonstrating its utility in responding to queries. To enhance security, authentication and authorization are added using PropelAuth, which involves OAuth 2.1 access tokens and scope consent, allowing users to securely access personal information within AI applications. This setup ensures that tools can be used as native capabilities within AI clients while maintaining user security and permission control, thus making the solution scalable from simple demos to enterprise-level implementations.