“The AI tools teams reach for keep changing, so our approach is to make sure MongoDB is present in all of them, whether a team is working in Claude or Codex, or running an agent in production. More of that building is now done by agents, and neither the agent nor the developer has to stop and set up a connection, so applications come together faster,” said Pablo Stern-Plaza, chief product officer, AI and Emerging Products, MongoDB.
With the new connectors, MongoDB is available natively across the tools where software is built. Ask questions of data in plain language in ChatGPT, Claude, and Grok. Query, inspect, and update data in MongoDB as work happens, with coding agents like Claude Code, Codex, Grok Build and Devin. And builders can also see live MongoDB data while generating an app in an IDE like Cursor.
Introducing the MongoDB Atlas Managed MCP Server
Running an agent in production means connecting it to real operational data and agent memory, and until now, teams had to build and maintain that connection themselves. “Developers want their AI tools to connect with the context and systems they already rely on,” said Vibhor Chhabra, product lead for ChatGPT Ecosystem at OpenAI. “MongoDB’s plugin in ChatGPT makes it easier to access and work with live application data, helping developers move faster while staying grounded in the context of their applications.”
“MongoDB also announced new capabilities that bring its benchmark-leading Voyage AI retrieval models into the operational database, including Automated Embeddings in MongoDB Atlas powered by Voyage AI, the Atlas Embedding and Reranking API, and voyage-code-4.
Get started with these new capabilities today for free.
