OpenAI officially announces MCP support!
Sam Altman announced that OpenAI will support the MCP standard, tweeting
"people love MCP and we are excited to add support across our products.
available today in the agents SDK and support for chatgpt desktop app + responses api coming soon!"
One of the bigger resistance points from developers was, what if OpenAI comes up with a competing protocol and bifurcate the development community. I guess we have our answer, time to build!
- Sam Altman's tweet OpenAI official MCP support
- OpenAI Documentation MCP in python agents SDK
Official MCP Java SDK released by VMWare Tanzu
Java SDK developed by Spring AI at VMware Tanzu is now the official Java SDK for MCP. This joins the official existing Kotlin SDK in the growing list of supported languages. The Spring AI team will maintain the SDK as an integral part of the Model Context Protocol organization.
- Java SDK Github
Anthropic officially announces the Model Context Protocol (MCP)
Anthropic introduces MCP as a “universal, open standard” for connecting AI systems to where data lives.
They release the MCP specification and SDKs (in Python and TypeScript) along with initial reference MCP servers for popular tools like Google Drive, Slack, GitHub, Git, Postgres, and web browsing (Puppeteer)
This launch immediately enables developers to run local MCP servers or integrate MCP into AI apps (Claude 2’s desktop app is updated to support MCP out-of-the-box). Anthropic’s announcement emphasizes that MCP will help “replace fragmented integrations with a single protocol,” allowing AI assistants to access relevant data more easily.
- Anthropic Blog official announcement
- Github Official MCP spec Github