Tag: mcp
-
Make it easy to use AI with your apps to retain customers
Adobe hasn’t done well in the “AI era.” Perhaps the answer is this: people are happy to use Adobe, and if let them use it through AI too, they’ll keep using AI. In my experience, once you integrate with AI tools (through skills, MCP servers, or just having an API that agents can use), those…
-
New spec maks MCP more enterprise-y, scalable, and otherwise performant
The biggest change in today’s update is an overhaul of how MCP processes request metadata. Previously, AI applications sent metadata via a relatively complex workflow called a handshake. The new MCP release removes the workflow, which has several benefits. One is that it makes it easier to scale MCP applications in response to traffic spikes.…
-
people work better with HTML, not markdown
I like the idea of having your AI thingies creating one off HTML pages as output. For example, monitoring and management agents. Most services now have an MCP server that will give API access to observability, logs, etc. What if instead of emitting JSON, they (also) emitted an HTML page? 🔗 Using Claude Code: The…
-
Now you can react faster than ever to security problems
This is an excerpt from our Tanzu Catsup last week. In that episode we talked all about how this AI stuff is changing – for the better – how you can handle security problems at the app layer. It’s Monday morning. Your boss walks up, says “scrap the backlog, we’ve got a list of CVEs…
-
Spaghetti DBMS, MCP for Knowledge Workers, The Harness Is the Harness – Related to your interests, Wednesday
Also: 55% of jobs reshaped, power over GPUs, a thousand DIY weekend platforms, and mood-tracking the robot MCP Servers for, and of, knowledge workers This is an excerpt from last week’s Tanzu Catsup. David and I have been talking a lot about the AI harness. We of course sprinkle in talk about how you would…
-
Write your AI stuff in the languages you know and that are running your organization
From my recent article on The New Stack: The choice of where and how to start your AI journey is a business decision, not a technology one. By grounding your AI efforts in the operational muscle you’ve already built with Java and Spring, you minimize friction and risk. Everyone just keeps doing what they’re doing,…
-
Making LLMs think harder
What exactly does “thinking” mean? “Thinking harder”? Robin says: prospecting new analogies; sending your inquiry out away from the gravitational attractors of protocol and cliché; turning the workpiece around to inspect it from new angles; and especially bringing more senses into the mix.” And, also that it is silent. We even have a phrase that…
-
You need a proxy for enterprise AI Google Cloud suggests using a centralized proxy to mediate all communication between clients and remote MCP servers. This proxy enforces access control, audit logging, secret policies, and secure transport, helping reduce the attack surface by having one enforced point rather than many decentralized servers. In addition, Google emphasizes…
-
Getting MCP auth into Spring AI
As the kids say: 👀 ”This repository provides Authorization support for Spring AI integrations with the Model Context Protocol (MCP). It covers both MCP Clients, MCP Servers, and Spring Authorization Server.” 🔗 spring-ai-community/mcp-security: Spring Security Configuration for MCP
-
Looks like great additions for MCP. Spring AI 1.1.0-M1 Available Now
-
How to Secure MCP Servers –
-
How Elicitation in MCP Brings Human-in-the-Loop to AI Tools –
-
GoogleCloudPlatform/apigee-samples – Use Apigee as MCP middleware.
-
VMware Tanzu enhances support for generative AI and agents with Tanzu AI Solutions – “As customers move from AI experimentation to implementation, they stand to benefit from closer integrations between technology components as they redefine “Ops” frameworks within their businesses. VMware Tanzu AI Solutions are designed to do just that, with specific enhancements like AI…
-
A think tool
Giving AI an inner-voice with Model Context Protocol I separated out a “think tool” from my agentic D&D project this week. The think tool is stupidly simple: all it does it echo back whatever the AI sends it. The original write-up from Anthropic makes it seems a little more mystical, but it doesn’t take long…
-
MCP Best Practices – Including unit tests!
-
MCP Is the New Control Point in AI—Are CIOs Ready for the Lock-In Battle? – They get the date of the spec’s release wrong (it was November 2024), and it has that Futurum cable TV news vibe, but good points are made, e.g.: “Will MCP remain truly portable, or will each vendor implement its own…
-
MCP Is RSS for AI: More Use Cases for Model Context Protocol – I like this: “I’m inclined to think of MCP as RSS for AI.” // Once prompts are used as intended – to be user initiated activity in the UI, we’ll see if things evolve. Think of an MCP prompt as adding a…
You must be logged in to post a comment.