Anthropic发布了名为Model Context Protocol (MCP)的开源工具，旨在将AI助手与各种数据源连接起来，从而提高AI性能。MCP提供了一种通用连接方式，允许AI助手直接访问所需信息，以更好地回答问题或执行任务。这与OpenAI近期推出的“Work with Apps”功能类似，但MCP的目标是适用于所有AI系统和数据源。开发者可以使用MCP简化AI与数据源的集成，构建更强大的AI代理，例如连接代码编辑器、创建代码仓库等，从而推动AI朝着更智能、更具代理性的方向发展。

🤔Anthropic发布了Model Context Protocol (MCP)开源工具，旨在连接AI助手与各种数据源，例如数据库、代码库、文件系统等，从而提升AI性能。

🤝MCP提供了一种标准协议，开发者只需一次性集成MCP，即可连接到任意数据源，无需为每个数据源单独编写代码，简化了AI与数据源的集成过程。

💻一些代码软件，如Replit、Codeium和Sourcegraph，已经开始使用MCP构建AI代理，例如自动创建代码仓库、提交代码等任务，方便用户操作。

💡MCP的应用有助于构建更强大的AI代理，使AI系统能够在不同工具和数据集之间保持上下文，并提供更可持续的架构，推动AI朝着更智能、更具代理性的方向发展。

Anthropic has released a new open-source tool to connect AI assistants directly to the information they need to inform their responses or carry out tasks. The new Model Context Protocol (MCP) provides a universal connection to all sorts of data sources, which Anthropic says will improve performance.

Earlier this month, OpenAI started testing a new “Work with Apps” feature that lets the Mac version of ChatGPT directly connect to certain coding apps. Anthropic’s tool, on the other hand, aims to work across all AI systems and data sources.

As noted by Alex Albert, Anthropic’s head of Claude relations, developers currently have to create custom code for each dataset they want their AI model to draw from. With Anthropic’s MCP, Albert says developers can integrate it with their AI tool once and then “connect to data sources anywhere” thanks to a “standard protocol for sharing resources, tools, and prompts.”

Anthropic says coding software like Replit, Codeium, and Souregraph have already started using MCP to build out their AI agents, which can complete tasks on behalf of users. This tool will likely make it easier for other companies and developers to connect an AI system with multiple data sources — something that could become especially helpful as the industry leans into agentic AI.

“Instead of maintaining separate connectors for each data source, developers can now build against a standard protocol,” Anthropic’s announcement says. “As the ecosystem matures, AI systems will maintain context as they move between different tools and datasets, replacing today’s fragmented integrations with a more sustainable architecture.”