Imagine asking both a stranger and a friend for a restaurant recommendation. The stranger might point you to the highest rated places on Yelp, but your friend will know that you love hole-in-wall-spots, enjoy spicy food, and prefer quiet restaurants where you can hold a conversation.
This difference—between generic information and personally tailored advice—illustrates a weakness of many AI assistants today. While these AI models are incredibly knowledgeable, their guidance is only as valuable as the context the user offers. Interacting with them is usually more like talking to a stranger than a friend.
Today, I want to share a project that bridges this gap, showing how we can make AI interactions more valuable by connecting them to our personal tools and data.
Building Bridges: The Model Context Protocol
The Model Context Protocol (MCP), recently published by Anthropic, creates an open standard for building bridges between AI models and other applications, giving assistants the power to access and interact with relevant information in other apps.
To explore the practical impact of this new standard, I built a connection between the Claude Desktop app and my favorite task manager, Things. Now, when I chat with Claude it knows what's on my todo list in Things, and it can modify that information just like I can when I use the app.
This integration opens up entirely new ways to interact with a task manager, especially when combined with other MCP integrations (such as calendar access). Instead of working through menus and lists, you can have natural conversations about your work.
Your Todo List Learns to Talk Back
For example, let’s ask Claude to help me plan out my day for tomorrow. I already have a workout penciled in for the afternoon, and I’m talking to Claude inside a Project that gives it some general information about how I like to work, such as preferring to do “deep” work in the morning.
Me: Block out time on my calendar tomorrow for focused work on my most pressing task
Claude: I'll help you schedule focused work time for tomorrow (January 10th). First, let me check your calendar and tasks to see what's already scheduled and what your most pressing work is.
Claude: [Uses MCP integrations to see what’s on my todo list and calendar.]
Claude: I notice you have a task with a deadline tomorrow ("Finalize post" in the "Write: Things MCP Server Post" project) and another high-priority task to prototype the diet assistant project. Since you prefer intellectual work in the morning and already have a workout scheduled for 4:00-5:00 PM, I suggest blocking out focused time in the morning. Here's my proposed plan:
Block out 9:00 AM - 12:00 PM for focused work, with the description mentioning both the post finalization (priority due to deadline) and the diet assistant prototype This gives you the morning for deep work while you're fresh, and still leaves the afternoon for other tasks around your workout
Would you like me to create this calendar block? I can adjust the timing if you prefer a different schedule. Also, I notice tomorrow is a dog walking day - would you like me to schedule the lunch break walk as well?
Claude identified the tasks that are “due” tomorrow, decided that they should be scheduled for the morning, and also realized that my calendar was missing my midday walk with Charlie 🐶.
What else can we do with this? We could ask Claude to create a task to pack for the vacation on my calendar next month, and expect it to learn the destination from the calendar entry and create an appropriate packing list. Or ask Claude to analyze our tasks and visualize them in the classic Eisenhower matrix, giving us a quick overview of how we’re allocating our time. It feels like having a hybrid coach/assistant on call.
Context Everywhere
This approach relates to something I've been exploring with Flavorful, an AI powered application to help home cooks be more creative and improvisational. There's a world of difference between asking an AI "give me a recipe for grilled cheese" and "give me a recipe that uses ingredients I have on hand, matches these dietary preferences, and builds on these techniques I've been practicing."
The same principle applies across domains – context transforms generic AI capabilities into personally relevant assistance. The possibilities extend far beyond task management and cooking. Consider:
- Having intelligent conversations about your fitness plan with access to your health stats, schedule, and meal plan
- Getting personalized financial advice based on your income, spending patterns, and life events
- Planning your garden using insights from your photos, plant history, local weather patterns, and sensor data
The key to realizing many of these possibilities lies in maintaining an open ecosystem for AI integration. The MCP specificaiton is publicly available, and a growing directory of MCP servers enables connections to various applications. This openness invites combinations that neither AI nor traditional tools could offer alone.
From Strangers to Acquaintances
Advancing AI isn't just about waiting for smarter models — it's also about finding ways to make existing AI more personally meaningful. My Things integration started with a simple thought: "What if an AI assistant could understand how I organize my work?" Maybe you're looking at your favorite tools right now and imagining similar possibilities. We're moving from AI assistants that act like helpful strangers to acquaintances familiar with our personal context.
I'm continuing to develop both the Things-MCP integration and Flavorful, exploring how AI can enhance rather than replace human capabilities. If you're working on similar projects or have ideas to share, I'd love to hear from you at hello@haldick.com.