Today in New York, our flagship MongoDB.local event is bringing together thousands of developers and tech leaders to discuss the future of building with MongoDB. Among the many exciting innovations and product announcements shared during the event, one theme has stood out: empowering developers to reliably build with AI and create AI solutions at scale on MongoDB. This post will explore how these advancements are set to accelerate developer productivity in the AI era.

Ship faster with the MongoDB MCP Server

Software development is rapidly evolving with AI tools powered by large language models (LLMs). From AI-driven editors like VS Code with GitHub Copilot and Windsurf, to terminal-based coding agents like Claude Code, these tools are transforming how developers work. While these tools bring tremendous productivity gains already, coding agents are still limited by the context they have. Since databases hold the core of most application-related data, access to configuration details, schemas, and sample data from databases is essential for generating accurate code and optimized queries.

With Anthropic’s introduction of the Model Context Protocol (MCP) in November 2024, a new way emerged to connect AI agents with data sources and services. Database connection and interaction quickly became one of the most popular use cases for MCP in agentic coding.

Today, we’re excited to announce the general availability (GA) of the MongoDB MCP Server, giving AI assistants and agents access to the context they need to explore, manage, and generate better code with MongoDB. Building on our public preview used by thousands of developers, the GA release introduces key capabilities to strengthen production readiness:

• Enterprise-grade authentication (OIDC, LDAP, Kerberos) and proxy connectivity.
• Self-hosted remote deployment support, enabling shared deployments across teams, streamlined setup, and centralized configuration. Note that we recommend following security best practices, such as implementing authentication for remote deployments.
• Accessible as a bundle with the MongoDB for VS Code extension, it delivers a complete experience: visually explore your database with the extension or interact with the same connection through your AI assistant, all without switching context.

Meeting developers where they are with n8n and CrewAI integrations

AI is transforming how developers build with MongoDB, not just in coding workflows, but also in creating AI applications and agents. From retrieval-augmented generation (RAG) to powering agent memory, these systems demand a database that can handle diverse data types—such as unstructured text (e.g., messages, code, documents), vectors, and graphs—all while supporting comprehensive retrieval mechanisms at scale like vector and hybrid search. MongoDB delivers this in a single, unified platform: the flexible document model supports the varied data agents need to store, while advanced, natively integrated search capabilities eliminate the need for separate vector databases. With Voyage AI by MongoDB providing state-of-the-art embedding models and rerankers, developers get a complete foundation for building intelligent agents without added infrastructure complexity.

As part of our commitment to making MongoDB as easy to use as possible, we’re excited to announce new integrations with n8n and CrewAI.

n8n has emerged as one of the most popular platforms for building AI solutions, thanks to its visual interface and out-of-the-box components that make it simple and accessible to create reliable AI workflows. This integration adds official support for MongoDB Atlas Vector Search, enabling developers to build RAG and agentic RAG systems through a flexible, visual interface. It also introduces an agent chat memory node for n8n agents, allowing conversations to persist by storing message history in MongoDB.

Meanwhile, CrewAI—a fast-growing open-source framework for building and orchestrating AI agents—makes multi-agent collaboration more accessible to developers. As AI agents take on increasingly complex and productive workflows such as online research, report writing, and enterprise document analysis, multiple specialized agents need to interact and delegate tasks with each other effectively. CrewAI provides an easy and approachable way to build such multi-agent systems. Our official integration adds support for MongoDB Atlas Vector Search, empowering developers to build agents that leverage RAG at scale. Learn how to implement agentic RAG with MongoDB Atlas and CrewAI.

The future is agentic

AI is fundamentally reshaping the entire software development lifecycle, including for developers building with MongoDB. New technology like the MongoDB MCP Server is paving the way for database-aware agentic coding, representing the future of software development. At the same time, we’re committed to meeting developers where they are: integrating our capabilities into their favorite frameworks and tools so they can benefit from MongoDB’s reliability and scalability to build AI apps and agents with ease.