With styles, you can now customize how Claude responds.
Select from the new preset options: Concise, Explanatory, or Formal. pic.twitter.com/2QFqo6AnC1
— Anthropic (@AnthropicAI) November 26, 2024
Anthropic, the company behind the AI model Claude, has introduced a new open-source tool that enhances AI capabilities, allowing the Claude Desktop to browse the internet and manage files on your computer. This innovation is achieved through the implementation of the Model Context Protocol (MCP), a universal protocol that enables large language models (LLMs) to interact with data from various platforms seamlessly. MCP allows Claude to access not only local files but also platforms like GitHub, Slack channels, and multiple search engines.
It's only been a day since Anthropic dropped Model Context Protocol (MCP) with Claude, like universal plug for AI.
Now AI connects to tools and data insanely easier.
And people can't stop getting creative with it to do your work.
10 wild examples:
— Min Choi (@minchoi) November 26, 2024
This means that the need for numerous custom integrations is eliminated; instead, developers can update the Claude configuration file to grant access to different data sources. Alex Albert, Head of Claude Relations, emphasized that MCP is designed to address a core challenge in LLM applications: connecting them to diverse data sources. Traditionally, developers had to write custom code for each integration, but MCP offers a standardized protocol for sharing resources, tools, and prompts.
MCP can interact with both local and internet resources.
Today @Anthropic is releasing MCP, a framework that allows Claude to run servers, giving it superpowers and effectively turning the Claude app into an API.
We created some server that I think you'll love!
FileSystem: Claude can create, read, and edit files and folders locally. pic.twitter.com/2XnRVFltR4
— Pietro Schirano (@skirano) November 25, 2024
For example, users can create a local database for Christmas presents, give Claude access to it, and use Claude’s internet browsing capabilities to find the best deals online automatically.
Model Context Protocol milestones
Introducing the Model Context Protocol (MCP)
An open standard we've been working on at Anthropic that solves a core challenge with LLM apps – connecting them to your data.
No more building custom integrations for every data source. MCP provides one protocol to connect them all: pic.twitter.com/kYsivQyPDq
— Alex Albert (@alexalbert__) November 25, 2024
To put MCP to the test, Claude was given access to various resources, including a Brave web server, a GitHub account, and local files. The AI managed to research and select a name for a Word Game website, create the necessary code for the web app, write a GitHub readme file, and set up a GitHub repository—all without any errors. This demonstrates how MCP could revolutionize user interactions with AI by automating complex tasks and reducing the need for manual coding.
While MCP is still in its early development stage and somewhat clunky to set up, it offers a promising glimpse into the future of human-computer interaction. Once integrated into applications like Claude, it is expected to become more user-friendly and widely adopted. Ultimately, MCP symbolizes a significant step forward in making AI more accessible and intuitive, enabling users to create customized solutions efficiently.
Ryan Morrison, AI Editor, brings over two decades of experience in tech journalism. He has a deep understanding of artificial intelligence and technology, complemented by his studies in astronomy and physics. When not writing, Ryan indulges in storytelling, guitar strumming, and indie game development.
