AI assistants are becoming our digital coworkers. They’re doing tasks for us that we used to do ourselves.
Much of their value will come from their ability to use computers, browsers, and APIs to do things outside of their environment, by using MCP (Model Context Protocol) servers.
AI assistants rely on MCP servers to let them:
- Open, edit, and save files
- Log notes in your CRM
- Read or send emails
- Enter and retrieve data
- Create to do tasks for you in your project management application
- … and so much more
MCP is the bridge that lets AI actually do things, not just chat.
Here are some resources for learning more:
- Podcast from Daniel Whitenack, Chris Benson, Practical AI Podcast
https://practicalai.fm/312 - Blog Post from Yoko Li, Andreessen Horowitz
https://a16z.com/a-deep-dive-into-mcp-and-the-future-of-ai-tooling/ - Courses from Andrew Ng, DeepLearning.AI, Anthropic
https://learn.deeplearning.ai/courses/building-toward-computer-use-with-anthropic/lesson/mshe8/tool-use https://learn.deeplearning.ai/courses/mcp-build-rich-context-ai-apps-with-anthropic/lesson/fkbhh/introduction
Resources for Startup Operators 