I'm a computer scientist who develops interactive, intelligent, and insightful visualization systems for analyzing and exploring large-scale data on the web.
https://lekschas.de · https://github.com/flekschas · https://linkedin.com/in/flekschas
Fritz Lekschas
Loading...
Another benefit is when your UI has rich ephemeral state that shouldn't live in a db. Think of dashboards or
visualization tools with crossfilters, selections, and dynamic color scales. These view models are often larger than the data model itself.
See higlass.demo.mcp-web.dev as an example
To build AI-controllable frontend apps with MCP-Web, you need to model your frontend state declaratively. Break your state into atomic and derived units, and describe it with Zod schemas. Exposing your state as tools is then straightforward. MCP-Web comes with utilities to streamline all this.
MCP-Web also lets you trigger AI queries directly from the frontend. Your app can "ask" AI questions, not just respond to AI requests. As an example, checkers.demo.mcp-web.dev is a checkers game where you play against AI. But since the app is AI-controllable, you can also let AI play against AI.
If you're curious about the philosophy and design decisions behind MCP-Web, keep on reading at mcp-web.dev/made-with-love.
This approach makes the frontend the main control surface, which has a few benefits. Primarily, it makes human-AI parity easy. Humans control state through UIs and AI controls the same state through tools. So both have the same capabilities, which also enables mixed-initiative interactions
With MCP-Web, your frontend app becomes the MCP server. AI doesn't need to parse HTML to identify possible actions. It gets typed tools to directly manipulate your frontend app's state like your UIs do.
Try it: todo.demo.mcp-web.dev is a todo app that either you or AI can fully control.
Did you ever want to control frontend apps through AI while being able to take over at any point? I built a library called MCP-Web that lets you expose state, actions, and UI as MCP tools+apps for AI while maintaining human agency.
Code: github.com/flekschas/mc...
Docs: mcp-web.dev
I'm proud to announce the latest release of 🧬 #Oxbow 🏹, with new features to make NGS data analysis more powerful, efficient, and "composable".
Learn more at: oxbow.readthedocs.io
This was a really fun project that was cooking up in our heads for years. AI coding finally made it possible to build the idea in the evenings :)
Still super thankful for the embedding reading club that @nvictus.bsky.social organized with folks from Mirny Lab back in 2020 or 2021!
Expose frontend state and actions as MCP tools for AI agents
mcp-web.dev
Fritz Lekschas
Fritz Lekschas
Fritz Lekschas
Fritz Lekschas
Fritz Lekschas
Fritz Lekschas
Fritz Lekschas
Fritz Lekschas
Nezar Abdennur
High-dimensional data is hard to understand. But is it truly cursed?
To help you build better intuition for high-dimensional datasets, @lekschas.de and I developed dtour, a visualization tool for smoothly navigating through data projections.
