Anthropic is proposing a new standard for connecting AI assistants to the systems where data resides.
Called the Model Context Protocol, or MCP for short, Anthropic says the standard, which it open sourced today, could help AI models produce better, more relevant responses to queries.
MCP lets models — any models, not just Anthropic’s — draw data from sources like business tools and software to complete tasks, as well as from content repositories and app development environments.
“As AI assistants gain mainstream adoption, the industry has invested heavily in model capabilities, achieving rapid advances in reasoning and quality,” Anthropic wrote in a blog post. “Yet even the most sophisticated models are constrained by their isolation from data — trapped behind information silos and legacy systems. Every new data source requires its own custom implementation, making truly connected systems difficult to scale.”
MCP ostensibly solves this problem through a protocol that enables developers to build two-way connections between data sources and AI-powered applications (e.g., chatbots). Developers can expose data through “MCP servers” and build “MCP clients” — for instance, apps and workflows — that connect to those servers on command.
Anthropic says that companies, including Block and Apollo, have already integrated MCP into their systems, while dev tooling firms, including Replit, Codeium, and Sourcegraph, are adding MCP support to their platforms.
“Instead of maintaining separate connectors for each data source, developers can now build against a standard protocol,” Anthropic wrote. “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.”
Developers can start building with MCP connectors now, and subscribers to Anthropic’s Claude Enterprise plan can connect the company’s Claude chatbot to their internal systems via MCP servers. Anthropic has shared prebuilt MCP servers for enterprise systems like Google Drive, Slack, and GitHub, and says that it’ll soon provide toolkits for deploying production MCP servers that can serve entire organizations.
“We’re committed to building MCP as a collaborative, open-source project and ecosystem,” Anthropic wrote. “We invite [developers] to build the future of context-aware AI together.”
MCP sounds like a good idea in theory. But it’s far from clear that it’ll gain much traction, particularly among rivals like OpenAI, which would surely prefer that customers and ecosystem partners use their data-connecting approaches and specifications.
In fact, OpenAI recently brought a data-connecting feature to ChatGPT, its AI-powered chatbot platform, that lets ChatGPT read code in dev-focused coding apps — similar to the use cases MCP drives. OpenAI has said that it plans to bring the capability, called Work with Apps, to other types of apps in the future, but it’s pursuing implementations with close partners rather than open sourcing the underlying tech.
It also remains to be seen whether MCP is as beneficial and performant as Anthropic claims it to be. The company says, for example, that MCP can enable an AI bot to “better retrieve relevant information to further understand the context around a coding task,” but the company offers no benchmarks to back up this assertion.
