Artificial Intelligence
Building AI-powered Apps with MongoDB
Introducing the Embedding and Reranking API on MongoDB Atlas
The next frontier for AI isn’t simply more capable models. It’s better context. As LLMs become embedded in every process and product, their accuracy and trust depend on grounding generation in the right data. Search and retrieval are foundational to this shift, powering everything from AI chatbots and assistants to fully autonomous agents. But building AI retrieval today means stitching together databases, vector search, and retrieval model providers—each introducing operational complexity.
Enterprise-Level, Scalable AI with Morphik and MongoDB
As AI continues to revolutionize how large enterprises operate, the most crucial startups are those capable of turning massive amounts of unstructured information into actionable intelligence. Morphik, one of the fastest-growing AI knowledge platforms for enterprises, uses MongoDB to deliver secure, high-performance, multitenant systems that power real-world automation at scale.
Revolutionize Asset Maintenance with MongoDB and MaintainX
We’re excited to announce that MongoDB and MaintainX are joining forces to help manufacturers achieve excellence in maintenance operations. This joint solution enables a digital thread from raw production data to maintenance execution.
Building Next-gen AI agents: The MongoDB Atlas-Microsoft Foundry Integration
Generative AI is rapidly evolving from experimenting with models to relying on intelligent, autonomous multi-agent workflows that can reason, act, and adapt in real time. Together, Microsoft and MongoDB are defining the future of AI by providing companies everywhere a robust, secure, scalable foundation for building innovative, next-generation AI agents.
Unlocking Financial Services Document Intelligence with Agentic AI and MongoDB
Driven by rising customer expectations and the demand for greater efficiency, accuracy, and agility, the financial services industry is undergoing a profound transformation. Gone are the days of painstaking manual document reviews, and welcome instead to the era of agentic AI, where intelligent systems and a robust data foundation redefine how financial data is processed and understood. Powered by MongoDB’s flexible, scalable platform, organizations can seamlessly manage multimodal data to unlock insights, automate workflows, and stay ahead in this evolving landscape.
Announcing the MongoDB Plugin for Firebase Genkit
We’re thrilled to introduce the MongoDB Plugin for Genkit, designed to accelerate your AI-powered applications with advanced search and database tooling—all within the Genkit ecosystem. Whether you're building chatbots, intelligent assistants, or recommendation engines, this plugin brings together MongoDB’s cutting-edge search capabilities and Genkit’s AI workflows, enabling seamless vector, full-text, and hybrid search with zero hassle.
Smarter AI Search, Powered by MongoDB Atlas and Pureinsights
We’re excited to announce that the integration of MongoDB Atlas with the Pureinsights Discovery Platform is now generally available—bringing to life a reimagined search experience powered by keyword, vector, and gen AI. What if your search box didn’t just find results, but instead understood intent? That’s exactly what this integration delivers! Beyond search: From matching to meaning Developers rely on MongoDB’s expansive knowledge ecosystem to find answers fast. But even with a rich library of technical blogs, forum threads, and documentation, traditional keyword search often falls short—especially when queries are nuanced, multilingual, or context-driven. That’s where the MongoDB-Pureinsights solution shines. Built on MongoDB Atlas and orchestrated by the Pureinsights Discovery platform, this intelligent search experience starts with the fundamentals: fast, accurate keyword results, powered by MongoDB Atlas Search . But as queries grow more ambiguous—say, “tutorials for AI”—the platform steps up. MongoDB Atlas Vector Search with Voyage AI , available as an embedding and reranking option (now part of MongoDB), goes beyond literal keywords to interpret intent—helping applications deliver smarter, more relevant results. The outcome: smarter, semantically aware responses that feel intuitive and accurate—because they are. What’s more, with generative answers enabled, the platform synthesizes information across MongoDB’s ecosystem (blog content, forums, and technical docs) to deliver clear, contextual answers using state-of-the-art language models. But it's not just pointing you to the right page. Instead, the platform is providing the right answer, with citations, ready to use. It’s like embedding a domain-trained AI assistant directly into your search bar. “As organizations look to move beyond traditional keyword search, they need solutions that combine speed, relevance, and contextual understanding,” said Haim Ribbi, Vice President, Global CSI, VAR & Tech Partner at MongoDB. “MongoDB Atlas provides the foundation for smarter discovery, and this collaboration with Pureinsights shows how easily teams can deliver gen AI-powered search experiences using their existing content.” Built for users everywhere But intelligence alone doesn’t make it transformational. What sets this experience apart is its adaptability. Whether you’re a developer troubleshooting in Berlin or a product owner building in São Paulo, the platform tailors responses to your preferences. Prefer concise summaries or deep technical dives? Want to translate answers in real time? Need responses that reflect your role and context? You’re in control. From tone and length to language and specificity, this is a search that truly understands you—literally and figuratively. Built on MongoDB. Elevated by Voyage AI. Delivered by Pureinsights. At the core of this solution is MongoDB Atlas, which unifies fast, scalable data access to structured content through Atlas Search and Atlas Vector Search. Looking ahead, by integrating with Voyage AI’s industry-leading embedding models, MongoDB Atlas aims to make semantic search and retrieval-augmented generation (RAG) applications even more accurate and reliable. While currently in private preview, this enhancement signals a promising future for developers building intelligent, AI-powered experiences. Pureinsights handles the orchestration layer. Their Discovery Platform ingests and enriches content, blends keyword, vector, and generative search into a seamless UI, and integrates with large language models like GPT-4. The platform supports multilingual capabilities, easy deployment, and enterprise-grade scalability out of the box. While generative answers are powered by integrated large language models (LLMs) and may vary by deployment, the solution is enterprise-ready, cloud-native, and built to scale. Bringing intelligent discovery to your own data Watch the demo video to see AI-powered search in action across 4,000+ pages of MongoDB content—from community forums and blog posts to technical documentation. While the demo features MongoDB’s content, the solution is built to adapt. You can bring the same AI-powered experience to your internal knowledge base, customer support portal, or developer hub—no need to build from scratch. Visit our partner page to learn more about MongoDB and Pureinsights and how we’re helping enterprises build smarter, AI-powered search experiences. Apply for a free gen AI demo using your enterprise content.
The Future of AI Software Development is Agentic
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. Figure 1. Overview of the MongoDB MCP Server. 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. Figure 2. Example workflow with n8n and MongoDB powering an AI agent. 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. Start building your applications with the MongoDB MCP Server today by following the Get Started guide . Visit the AI Learning Hub to learn more about building AI applications with MongoDB.
Supercharge Self-Managed Apps With Search and Vector Search Capabilities
MongoDB is excited to announce the public preview of search and vector search capabilities for use with MongoDB Community Edition and MongoDB Enterprise Server. These new capabilities empower developers to prototype, iterate, and build sophisticated, AI-powered applications directly in self-managed environments with robust search functionality. This post is also available in: Deutsch , Français , Español , Português , Italiano , 한국어 , 简体中文 . Versatility is one of the reasons why developers love MongoDB. MongoDB can run anywhere. 1 This includes local setups where many developers kickstart their MongoDB journey, to the largest enterprise data centers when it is time to scale, and MongoDB’s fully managed cloud service, MongoDB Atlas . Regardless of where development takes place, MongoDB effortlessly integrates with any developer's workflow. MongoDB Community Edition is the free, source-available version of MongoDB that millions of developers use to learn, test, and grow their skills. MongoDB Enterprise Server is the commercial version of MongoDB’s core database. It offers additional enterprise-grade features for companies that prefer to self-manage their deployments on-premises or in public, private, or hybrid cloud environments. With native search and vector search capabilities now available for use with Community Edition and Enterprise Server, MongoDB aims to deliver a simpler and consistent experience for building great applications wherever they are deployed. What is search and vector search? Similar to the offerings in MongoDB Atlas, MongoDB Community Edition and MongoDB Enterprise Server now support two distinct yet complementary search capabilities: Full-text search is an embedded capability that delivers a seamless, scalable experience for building relevance-based app features. Vector search enables developers to build intelligent applications powered by semantic search and generative AI using native, full-featured vector database capabilities. There are no functional limitations on the core search aggregation stages in this public preview. Therefore, $search , $searchMeta , and $vectorSearch are all supported with functional parity to what is available in Atlas, excluding features in a preview state. For more information, check out the search and vector search documentation pages. Solving developer challenges with integrated search Historically, integrating advanced search features into self-managed applications often required bolting on external search engines or vector databases to MongoDB. This approach created friction at every stage for developers and organizations, leading to: Architectural complexity: Managing and synchronizing data across multiple, disparate systems added layers of complexity, demanded additional skills, and complicated development workflows. Operational overhead: Handling separate provisioning, security, upgrades, and monitoring for each system placed a heavy load on DevOps teams. Decreased developer productivity: Developers are forced to learn and use different query APIs and languages for both the database and the search engine. This resulted in frequent context switching, steeper learning curves, and slower release cycles. Consistency challenges: Aligning the primary database with separate search or vector indexes risked producing out-of-sync results. Despite promotions of transactional guarantees and data consistency, these indexes were only eventually consistent. This led to incomplete results in rapidly changing environments. With search and vector search now integrated into MongoDB Community Edition and MongoDB Enterprise Server, these trade–offs disappear. Developers can now create powerful search capabilities using MongoDB's familiar query framework, removing the synchronization burden and the need to manage multiple single-purpose systems. This release simplifies data architecture, reduces operational overhead, and accelerates application development. With these capabilities, developers can harness sophisticated out-of-the-box capabilities to build a variety of powerful applications. Potential use cases include: table, th, td { border: 1px solid black; border-collapse: collapse; } th, td { padding: 5px; } Use Case Description Keyword/Full-text search Autocomplete and fuzzy search Create real-time suggestions and correct spelling errors as users type, improving the search experience Search faceting Apply quick filtering options in applications like e-commerce, so users can narrow down search results based on categories, price ranges, and more Internal search tools Build search tools for internal use or for applications with sensitive data that require on-premises deployment Vector search AI-powered semantic search Implement semantic search and recommendation systems to provide more relevant results than traditional keyword matching Retrieval-augmented generation (RAG) Use search to retrieve factual data from a knowledge base to bring accurate, context-aware data into large language model (LLM) applications AI agents Create agents that utilize tools to collect context, communicate with external systems, and execute actions Hybrid search Hybrid search Combine keyword and vector search techniques Data processing Text analysis Perform text analysis directly in the MongoDB database MongoDB offers native integrations with frameworks such as LangChain , LangGraph , and LlamaIndex . This streamlines workflows, accelerates development, and embeds RAG or agentic features directly into applications. To learn more about other AI frameworks supported by MongoDB, check out this documentation . MongoDB’s partners and champions are already experiencing the benefits from utilizing search and vector search across a wider range of environments: “We’re thrilled that MongoDB search and vector search are now accessible in the already popular MongoDB Community Edition. Now our customers can leverage MongoDB and LangChain in either deployment mode and in their preferred environment to build cutting-edge LLM applications.”—Harrison Chase, CEO, LangChain. “MongoDB has helped Clarifresh build awesome software, and I’ve always been impressed with its rock-solid foundations. With search and vector search capabilities now available in MongoDB Community Edition, we gain the confidence of accessible source code, the flexibility to deploy anywhere, and the promise of community-driven extensibility. It’s an exciting milestone that reaffirms MongoDB’s commitment to developers.”—Luke Thompson, MongoDB Champion, Clarifresh. “We’re excited about the next interaction of search experiences in MongoDB Community Edition. Our customers want the highest flexibility to be able to run their search and gen AI-enabled applications, and bringing this functionality to Community unlocks a whole new way to build and test anywhere.”—Jerry Liu, CEO, LlamaIndex. “Participating in the Private Preview of Full-text and Vector Search for MongoDB Community has been an exciting opportunity. Having $search, $searchMeta, and $vectorSearch directly in Community Edition brings the same powerful capabilities we use in Atlas—without additional systems or integrations. Even in early preview, it’s already streamlining workflows and producing faster, more relevant results.”—Michael Höller, MongoDB Champion, akazia Consulting. Accessing the public preview The public preview is available for free and is intended for testing, evaluation, and feedback purposes only. Search and Vector Search with MongoDB Community Edition. The new capabilities are compatible with MongoDB version 8.2+, and operate on a separate binary, mongot, which interacts with the standard mongodb database binary. To get started, ensure that: A MongoDB Community Server cluster is running using one of the following three methods: Download MongoDB Community Server version 8.2 from the MongoDB Downloads page . As of public preview, this feature is available for self-managed deployments on supported Linux distributions and architectures for MongoDB Community Edition version 8.2+. Download the ```mongot``` binary from the MongoDB Downloads page . Pull the container image for Community Server 8.2 from a public Docker Hub repository . Coming soon: Deploy using the MongoDB Controllers for Kubernetes Operator (Search Support for Community Server is planned for version 1.5+ ). Search and Vector Search for use with MongoDB Enterprise Server . The new capabilities are deployed as self-managed search nodes in a customer's Kubernetes environment. This will seamlessly connect to any MongoDB Enterprise Server clusters, residing inside or outside Kubernetes itself. To get started, ensure that: A MongoDB Enterprise Server cluster is running. version 8.0.10+ (for MongoDB Controllers for Kubernetes operator 1.4). version 8.2+ (for MongoDB Controllers for Kubernetes operator 1.5+). A Kubernetes environment. The MongoDB Controllers for Kubernetes Operator are installed in the Kubernetes cluster. Find installation instructions here . Comprehensive documentation for setup for MongoDB Community Edition and MongoDB Enterprise Server is also available. What's next? During the public preview, MongoDB will deliver additional updates and roadmap features based on customer feedback. After the public preview, these search and vector search capabilities are anticipated to be generally available for use with on-premise deployments. For Community Edition, these capabilities will be available at no additional cost as part of the Server Side Public License (SSPL) . For MongoDB Enterprise Server, these capabilities will be included in a new paid subscription offering that will launch in the future. Pricing and packaging details for the subscription will be available closer to launch. For developers seeking a fully managed experience in the cloud, MongoDB Atlas offers a production-ready version of these capabilities today. MongoDB would love to hear feedback! Suggest new features or vote on existing ideas at feedback.mongodb.com . The input is critical for shaping the future of this product. Users can contact their MongoDB account team to provide more comprehensive feedback. Check out MongoDB’s documentation to learn how to get started with Search and Vector Search in MongoDB Community Edition and MongoDB Enterprise Server . 1 MongoDB can be deployed as a fully managed multi-cloud service across all major public cloud providers, in private clouds, locally, on-premises and hybrid environments.