Topic
Model Context Protocol
17 episodes
-
MCP server portals
Asteria and Draco unpack Cloudflare's MCP server portals as boundary infrastructure for enterprise MCP adoption: one Access-controlled endpoint, curated tools, managed OAuth, Code Mode, and observability, with caveats around direct server URLs, admin credentials, and sync paths.
-
GitHub ARPAHLS/skillware: A Python framework for modular, self Contained skill management for machines.
Skillware is a new open-source framework that packages AI agent capabilities into modular, installable skills using a Python-based registry. The hosts debate whether this is a genuine infrastructure win or yet another abstraction layer in search of a problem, and end up excited by the practicality of installing a skill like `finance/wallet_screening` with executable logic, governance, and tool schemas that work across models. They call out the trust model for running third-party skills, tease an install demo (`pip install "skillware[gemini]"`), and close on an enthusiastic call to arms.
-
Enterprise Managed Authorization: Zero touch OAuth for MCP
Tyler and Pippa dig into the Model Context Protocol's new Enterprise-Managed Authorization extension: what it promises, whether the technical design holds up, and who actually gains traction outside the launch coalition. They question if zero-touch OAuth truly solves enterprise adoption friction or just moves constraint into IdP policy complexity, and float a practical Build Next path that tests the claim on your own stack.
-
The Protocol That Cleaned Up Our Agent Architecture | Towards Data Science
MCP (Model Context Protocol) is an open standard for how agents discover and call tools. Instead of scattering tool definitions across multiple agent files, you run tools on a separate server that agents connect to at runtime. The protocol provides a clean interoperability boundary—any MCP-compatible client can call any MCP-compatible server without integration work. For teams with multiple overlapping agents, this eliminates schema drift, simplifies approval gates, and decouples the tool layer from the orchestration layer.
-
Opentabs Dev/opentabs
OpenTabs lets AI agents call real web APIs through your browser session—Discord, Slack, GitHub, Notion, and 100+ more—without screenshots, DOM scraping, or API keys. Cody questions the security model and plugin discovery overhead; Justy argues the authenticated-session angle solves a real friction point for AI workflows. They land on it as genuinely useful for power users and developers, but adoption hinges on plugin ecosystem maturity and trust.
-
Cloudflare Launches Code Mode MCP Server to Optimize Token Usage for AI Agents
Cloudflare's new Model Context Protocol (MCP) server powered by Code Mode reduces token usage for AI agents, making it possible to interact with complex APIs more efficiently.
-
AI's next bottleneck isn't the models — it's whether agents can think together
AI's next bottleneck is not the models, but whether agents can think together, requiring next-level infrastructure and shared cognition
-
Preparing IT for AI Agents: How MCP Shapes the Future of AI
Izzo and Boone explore MCP (Model Context Protocol) and how it's positioning IT infrastructure for AI agents, diving into the protocol's architecture, orchestration patterns, and what it means for organizations preparing their systems for autonomous AI workflows.
-
Developer’s Guide to AI Agent Protocols Google Developers Blog
Izzo and Boone explore Google's new Agent Development Kit and the emerging protocols solving AI agent integration hell - MCP for data connections, A2A for agent-to-agent communication, and UCP for commerce workflows. They build a restaurant supply chain agent live, showing how these protocols eliminate custom integration code.
-
Managed MCP servers for Google Cloud databases | Google Cloud Blog
Google Cloud launches managed MCP servers for their database portfolio, letting AI agents directly interact with PostgreSQL, Spanner, Cloud SQL, Firestore, and Bigtable through the Model Context Protocol standard. No infrastructure to deploy — just configure endpoints and agents get secure, governed access to operational data.
-
OpenAI Publishes Codex App Server Architecture for Unifying AI Agent Surfaces
InfoQ Homepage News OpenAI Publishes Codex App Server Architecture for Unifying AI Agent Surfaces Architecture & Design Orchestrating Production-Ready AI Workflows with Apache Airflow (Webinar Mar 5th) OpenAI Publishes Codex App Server Architecture for Unifying AI Agent Surfaces Feb 17, 2026 3 min read by Eran Stiller Write for InfoQ Feed your curiosity. Help 550k+ global senior developers each month stay ahead.
-
Learn RAG & MCP Fundamentals
This podcast episode delves into the importance of mastering Retrieval Augmented Generation (RAG) and Model Context Protocol (MCP) to enhance AI's capabilities in real-world applications. Hosts discuss how these technologies empower developers to create integrated systems that leverage private data effectively and enable AI to interact with various software seamlessly.
-
MCP powered RAG Over Complex Docs
In this episode, we explore the integration of MCP-powered Retrieval-Augmented Generation (RAG) over complex documents, emphasizing its real-world applications and significance. Hosts discuss how this technology transforms document processing and retrieval, providing a fresh perspective on managing complex data efficiently.
-
Google launches managed MCP servers that let AI agents simply plug into its tools | TechCrunch
Google's launch of managed MCP servers aims to simplify how AI agents interact with various tools and data, reducing the complexity developers face while integrating these systems. This innovation could lead to more effective AI solutions for businesses and other sectors, as it streamlines connections to Google's robust services.
-
Why the MCP Server Is Now a Critical Microservice
In this episode, we explore how the MCP server has become an essential microservice in modern software architecture. We discuss its implications for system scalability, reliability, and collaboration, and provide concrete examples to illustrate its real-world applications. Join us for insights into why adopting this technology could be transformative for businesses today.
-
Critical Vulnerability in MCP Server Platform Exposes 3,000+ Servers and Thousands of API Keys
Home Cyber Security Critical Vulnerability in MCP Server Platform Exposes 3,000+ Servers and Thousands of... Cyber Security Cyber Security News Vulnerability News Critical Vulnerability in MCP Server Platform Exposes 3,000+ Servers and Thousands of API Keys By Guru Baran - October 22, 2025 A critical vulnerability in Smithery.ai, a popular registry for Model Context Protocol (MCP) servers .
-
No OAuth Required: An MCP Client For AWS IAM
Dennis Traub for AWS Posted on Nov 18 • Edited on Nov 20 No OAuth Required: An MCP Client For AWS IAM # ai # agents # mcp # aws When Anthropic published the Model Context Protocol (MCP) , I immediately started experimenting with deployment options on AWS: First, I tried running MCP servers as AWS Lambda functions. A great solution in terms of simplicity and cost, but it also meant I had to manually manage session state across invocations.