Today we are making open source the Model Context Protocol (MCP), a new standard for connecting AI assistants to the systems where data resides, including content repositories, business tools, and development environments. Its goal is to help frontier models produce better and more relevant answers.
As AI assistants become more widely adopted, the industry has invested heavily in model capabilities, making rapid advances in reasoning and quality. Yet even the most sophisticated models are limited by their isolation from data, stuck behind information silos and legacy systems. Each new data source requires its own custom implementation, making it difficult to scale truly connected systems.
MCP meets this challenge. It provides a universal, open standard for connecting AI systems to data sources, replacing fragmented integrations with a single protocol. The result is a simpler, more reliable way to allow AI systems to access the data they need.
Model Context Protocol
The Model Context Protocol is an open standard that allows developers to establish secure, two-way connections between their data sources and AI-powered tools. The architecture is simple: developers can either expose their data through MCP servers or create AI applications (MCP clients) that connect to these servers.
Today, we’re introducing three major components of the Model Context Protocol to developers:
- The Model Context Protocol specification and SDK
- Support for local MCP server in the Office applications Claude
- A open source repository MCP servers
Claude 3.5 Sonnet is capable of quickly creating MCP server implementations, allowing organizations and individuals to quickly connect their most important data sets to a range of AI-driven tools. To help developers start exploring, we share prebuilt MCP servers for popular enterprise systems like Google Drive, Slack, GitHub, Git, Postgres, and Puppeteer.
Early adopters like Block and Apollo have integrated MCP into their systems, while developer tool companies like Zed, Replit, Codeium, and Sourcegraph are working with MCP to improve their platforms, enabling AI agents to better retrieve relevant information to better understand the context around a system. coding task and produce more nuanced and functional code with fewer attempts.
“At Block, open source is more than a development model: it is the foundation of our work and a commitment to creating technology that drives meaningful change and serves as a public good for all,” said Dhanji R . Prasanna, Chief Technology Officer at Block. “Open technologies like the Model Context Protocol are the bridges that connect AI to real-world applications, ensuring that innovation is accessible, transparent and rooted in collaboration. We’re excited to partner on a protocol and use it to build agentic systems. remove the burden of mechanics so people can focus on creating.
Instead of maintaining separate connectors for each data source, developers can now rely on a standard protocol. As the ecosystem matures, AI systems will maintain context as they move between different tools and data sets, replacing today’s fragmented integrations with a more sustainable architecture.
To start
Developers can start creating and testing MCP connectors today. Existing Claude for Work customers can begin testing MCP servers locally, connecting Claude to internal systems and data sets. We will soon provide development toolkits for deploying remote production MCP servers that can serve your entire Claude for Work organization.
To start building:
- Install predefined MCP servers via the Claude Bureau app
- Follow our quick start guide to build your first MCP server
- Contribute to our open source repositories connectors and implementations
An open community
We are committed to building MCP as a collaborative, open source project and ecosystem, and we look forward to your feedback. Whether you are an AI tool developer, a company looking to leverage existing data, or a pioneer exploring frontiers, we invite you to build the future of contextual AI together.