MongoDB Blog

Announcements, updates, news, and more

Production-Ready Agents Need A Production-Ready Data Platform

There’s a common theme to the conversations I’ve been having with AI teams lately: change. Constant, head-spinning change. Teams across industries are evaluating and re-evaluating model providers, agent frameworks, and harnesses on a continuous basis. At MongoDB, we believe that your choice of technology partner—specifically, your data platform—should simplify how you build with AI. It should deliver performance at scale, enable you to build and run anywhere, and it should allow you to choose your own providers and frameworks. This is exactly what MongoDB offers, and it’s why more than 67,000 customers rely on us for their most important applications. The organizations seeing the most AI success are the ones whose technology stacks are set up for the current pace of change. For example, DevRev’s AgentOS platform is powered by MongoDB Atlas. AgentOS handles billions of requests each month, for everything from AI-assisted insights and analytics to internal communications and development. Relying on MongoDB Atlas has helped DevRev get innovations to market faster, and enables the company to scale seamlessly as it grows. MongoDB is ideal for agentic AI in two key ways. First, an agent is only as smart as its context—which requires blending short-term memory, long-term knowledge, and enterprise data. Because this information is highly dynamic and unstructured, JSON is the ideal format. It provides the schema flexibility inherently needed by the data and allows attaching metadata like IDs and confidence scores. MongoDB stores JSON natively and provides the scale and consistency required to run thousands of concurrent agents. Second, it’s designed for how agents work. As memory accumulates, agents must pinpoint the precise context needed for a request. MongoDB solves this by providing state-of-the-art information retrieval capabilities (search, vector search, hybrid search, embeddings) directly where the operational data already lives, eliminating the need to constantly sync data across separate systems. Customers get high-precision semantic retrieval without the operational headache of managing multiple fragmented products. A good example of how MongoDB powers agents is ElevenLabs. The company relies on MongoDB Atlas to power the long-term memory and knowledge base for its autonomous agents. By leveraging Atlas Search and Vector Search, ElevenLabs enables their agents to retain complex context and deliver highly personalized interactions in real-time. Adobe, meanwhile, chose MongoDB as the long-term memory and reasoning layer for Journey Agent, its composite multimodal AI agent that unifies Adobe's marketing suite and orchestrates end-to-end customer journeys. Adobe leverages MongoDB Atlas Search and Atlas Vector Search together to power the sub-100 millisecond hybrid search the agent needs to act in real time. Defining an open standard for agent memory Last month, MongoDB partner LangChain announced the launch of Context Hub in LangSmith, a place to store, version, and collaborate on the files that define how agents behave, like AGENT.md and agent skills. But context engineering goes beyond that. Agents also rely on memory: short-term context captured in states, sessions, and interaction history, and long-term memory that persists across sessions. Figure 1. Agent memory with MongoDB. Production-Ready Agents blog image 1 media Today, there is no broadly adopted open standard for defining and managing portable agent memory across agent frameworks. Now, MongoDB—alongside LangChain and ecosystem partners—is working on an open reference architecture and contributing toward greater interoperability in this space. This work will help define what has been missing from the AI ecosystem: shared interfaces, metadata conventions, versioning patterns, and retrieval semantics for the data that differentiate agentic experiences and shape agent behavior. The aim is to enable organizations to switch model providers or try a new framework on a Tuesday—and not lose Wednesday rewriting memory plumbing. Ultimately, we want to make agent memory and context easier (and faster) to manage. For customer-facing agents to make real-time decisions, such as responding to a support request or making a policy change, they need contextual information instantly. Not info from a data warehouse that might be 30 minutes old. The context layer needs to be real-time, a required capability we’ve been delivering for tens of thousands of customers going on almost two decades. MongoDB’s performant, flexible platform = agentic success The next generation of agents will increasingly be long-horizon systems, running for hours or more. As they take on more complex tasks, context will become even more critical, and agent memory will be central to making them effective. This will create a demand for diverse, high-performance memory systems, and MongoDB is positioned to provide the flexibility and scalability agents require. With the recent release MongoDB 8.3, our core database has evolved to better support the speed and demands of AI workloads. MongoDB also delivers the retrieval accuracy necessary for agent outputs to be trusted (a non-negotiable for customer-facing applications) while optimizing tokens and cost in production. Every AI team is currently making a bet about what the future of the agentic stack will look like. The ones betting on a flexible, production-ready data platform like MongoDB—that enables teams to innovate now while ensuring structure and resilience for the future—will be able to pivot quickly. The ones betting on rigid schema designs, or on a smattering of specific models and frameworks, might end up redoing their plumbing instead of shipping products. Figure 2. Advantages of MongoDB's flexible schema for AI workloads. Production Ready Agents Blog - Image 2 media MongoDB is built for AI: JSON is the lingua franca of AI. The information agents need is highly dynamic and can be structured, semi-structured, and unstructured. MongoDB provides the schema flexibility inherently needed by the data and allows attaching metadata for richer, more precise context. Dynamic, adaptive schemas that evolve in place as fast as thought without breaking what runs on top. The MongoDB document model isn’t adapted for AI; it’s the natural shape of AI data. MongoDB offers one data platform: Every data requirement for production AI is natively integrated. Search, vector search, embeddings, hybrid retrieval, time series, and streaming run on the same OLTP foundation 67,000+ customers trust with mission-critical applications—with one API, one security model, one operational footprint.

June 11, 2026
Artificial Intelligence

AI Is Changing What Customers Need From a Database. MongoDB 8.3 Is Built for It

Today, we announced at .local London that MongoDB 8.3 is built for the speed AI demands—and our customers can't afford to wait. The data layer has to move at AI speed The old contract between databases and the applications on top of them was simple: databases improve slowly, and architectures evolve around them. AI has changed that contract. The workloads our customers are shipping today—agents retrieving at sub-100ms, retry storms hitting in milliseconds, multi-region deployments that can't trade compliance for latency—were edge cases 18 months ago. Now they're the baseline. MongoDB 8.3, generally available today, is our fourth significant release in 19 months. These releases compound. Customers running on 8.0 have seen 36% faster reads and 59% higher throughput for updates. 8.3 adds another 35% to write throughput, 45% to reads, and 15% to ACID transactions over 8.0 — without changing a line of application code. Enterprises like Adobe, running the most demanding AI in production, have made the requirements clear: sub-100ms retrieval, sub-second context updates, zero downtime. That's what MongoDB Atlas is built for. That's the commitment: when the data platform keeps pace, our customers can focus on shipping. MongoDB.local London Core Blog 2026 - Image 1 media Run anywhere. Stay secure. Where you run your agents isn't just an infrastructure decision anymore. Now, it's a critical compliance and security decision as well. While most platforms force a trade-off between global reach and necessary control, with 130 regions across AWS, Google Cloud, and Microsoft Azure, Atlas doesn’t force you to compromise. Atlas even enables clusters spanning multiple providers simultaneously. Avalara and Iron Mountain both took the cloud-agnostic path, modernizing on Atlas so they could meet their customers wherever they ran. The deployment shape changes. The data layer underneath doesn't. What's shifted in the last year is the pressure on both ends. Customers want retrieval and embedding capabilities closer to their users, in more places, on more clouds. They also want more authority over the residency of their data. Those two demands used to be in tension. They don't have to be. Cross-region connectivity for AWS PrivateLink, generally available today, is the clearest example. Traffic between Atlas clusters in different AWS regions stays on the AWS private backbone, with no public internet exposure. Security and compliance teams get the guarantees they need. Engineering teams design around fewer edge cases. Nobody has to make a trade-off. Built to keep pace Every capability in this post addresses friction that technical leaders have been engineering around for years. They solve different problems, but share one objective: to eliminate the infrastructure trade-offs that slow down production of AI. The AI workloads our customers will run 18 months from now will look different from those today. That's not a risk. That's the point. Four significant releases in 19 months isn't a marketing number. It's a signal about how seriously we take the current pace of change, and our commitment to staying ahead of it for our 65,200+ customers. Getting agents to retrieve the right information, accurately and at speed, is where embeddings and memory come in. Pablo Stern covers that in his blog, The Bottleneck in Enterprise AI Isn't the Model. It's the Data.

May 7, 2026
Home

New Research Reveals Overcoming Legacy Tech Issues Key to AI Success

This guest post comes from IDC’s Dr. William Lee, Senior Research Director, Service Provider and Core Infrastructure Research. MongoDB commissioned IDC to explore the connection between legacy infrastructure, data challenges, and AI across Asia Pacific, and today we’re happy to share that work. For more, see the full MongoDB-sponsored IDC InfoBrief, Modernizing Legacy: Winning in the Age of AI, Doc #AP242555-IB, April 2026. AI ambition is everywhere across Asia/Pacific. But ambition alone does not determine success. Organizations are discovering that AI outcomes are directly tied to the quality, accessibility, and modernity of their underlying technology stack and associated data technology foundations. Organizations that have managed to stay abreast of technical and data management changes across the application and infrastructure stacks, by embedding modernization into their organizational DNA, are experiencing 3x more digital revenue growth than those that are bound up in technical and data debt. To better understand this connection, IDC surveyed 1,400 organizations across eight Asia/Pacific markets. The findings reveal that modernization is no longer a side initiative. It is the core of a sustainable AI strategy. The AI readiness divide: Leaders versus mainstream IDC’s latest Asia/Pacific Modernization Survey, sponsored by MongoDB, identifies two distinct groups: The Mainstream Cohort: organizations still burdened by technical debt, siloed data, and skills gaps The Leaders Cohort: organizations that have embedded modernization into their strategy and experience the business results to match This divide is not theoretical. It is measurable in business performance. Organizations in the Leaders Cohort generate nearly three times more digital revenue than their peers. The difference is not simply higher AI spending. Leaders modernize core infrastructure, align executive support with transformation goals, and invest in skills development alongside technology. They treat AI readiness as an enterprise capability—not a standalone initiative. APAC IDC Blog Image 1 media The rigidity trap: Technical debt and AI failure risk A significant portion of Asia/Pacific organizations remain constrained by legacy architectures. According to IDC’s research, 43% report that their existing architecture is a major obstacle, making it difficult to build new applications without extensive modernization. This rigidity creates what IDC refers to as data debt—siloed, redundant, outdated, and poor-quality data that undermines AI performance and increases operational cost, and is in addition to the growing levels of technical debt that are being accumulated by organizations due to the slow modernization of older applications. When AI systems are trained on fragmented or inconsistent data: Outcomes become unreliable Bias risks increase Operational costs rise Business trust erodes IDC predicts that CIOs who fail to launch data debt remediation initiatives will face 50% higher AI failure rates and rising costs by 2027. Yet one-third of all enterprises continue to rely on legacy relational databases. Many such databases have been implemented in support of a wide array of business applications where business leaders expect they can use AI. Yet the legacy RDBMS-type databases are not capable of delivering on the dynamic, rapidly evolving, high-volume real-time demands that AI requires. Organizations that are unable to move to AI-ready application stacks are being left behind by those that have already made the switch. The gap between AI investment and infrastructure readiness is widening. APAC IDC Blog Image 2 media Legacy drag: The real business impact The consequences of technical debt are already visible. 95% of organizations report project delays 90% have experienced failed modernization initiatives 89% acknowledge technical debt as a major modernization obstacle In addition, organizations cite weak security integration, limited engagement with the business users, and outdated workflows as compounding challenges. Modernization failures are rarely just technical. They are organizational and structural. What sets leaders apart The Leaders Cohort does not operate in a constraint-free environment. Instead, they respond differently. IDC defines Leaders as organizations—across both digital-native and traditional industries—that have broken free from legacy rigidity and embedded modernization into ongoing operations. Their distinguishing characteristics include: Continuous, multi-pronged approaches to addressing legacy systems Alignment between executive leadership, funding, and AI outcomes Investment in modernization as a long-term capability, not a one-off project Strong focus on AI and modern application development skills The result is not just better IT performance. Leaders grow digital revenue faster and are positioned to extract value from AI initiatives earlier and more consistently than their peers. Cloud-centric data management: A strategic enabler Modern data platforms are central to this shift. In IDC’s research, 38% of Asia/Pacific organizations identify cloud-centric data management platforms as their top modernization investment priority for 2026. The motivation is clear: support hybrid architectures and AI workloads without introducing additional complexity. While AI enablement is a universal requirement, Leaders distinguish themselves by prioritizing: Security and compliance Flexibility across structured and unstructured data Scalable architectures aligned to modern AI toolchains This capability is increasingly critical. Much of today’s AI-relevant data—including content, sensor outputs, and customer interactions—resides in unstructured formats that traditional architectures struggle to integrate effectively. Handling both structured and unstructured data seamlessly has become a competitive differentiator. Modernization as a continuous strategy IDC’s perspective is clear: modernization is no longer a technology refresh cycle. It is a strategic operating model. Successful organizations approach modernization across three dimensions: People Leaders invest deliberately in AI and modern application development skills. They recognize resistance to change as a strategic risk and actively manage it. Process They adopt cloud-native approaches rather than repeating short-term “lift-and-shift” migrations that simply relocate technical debt. They use structured prioritization frameworks to embed modernization into business-as-usual operations. Technology They modernize to data platforms that support scalability, diverse data types, rapid feature development, and alignment with contemporary AI ecosystems. The ROI equation: Risk of action versus risk of inaction Modernization is often perceived as expensive and risky. However, IDC’s analysis suggests that the risk of inaction is frequently underestimated, and this study affirms that those who invest effectively, and continuously, into their application modernization program are experiencing both better ROI and higher digital revenues! Organizations that modernize report: Significant reductions in reporting time Double-digit productivity improvements Meaningful cost savings Hundreds of thousands of dollars in quantified cost reductions While full application rewrites and database modernization demand greater upfront investment than lift-and-shift migrations, they can deliver up to three times the long-term benefit. For CIOs and business leaders, the decision should not be framed as modernization cost versus status quo stability. It is modernization investment versus escalating AI failure risk. The Path forward: Legacy systems are not permanent Overcoming legacy is often perceived to be as significant a risk as taking on new technologies. IDC notes that many CIOs across the region focus on risk avoidance as a priority. In contrast, business leaders are seeking innovative solutions that drive new business opportunities, and so CIOs must balance their risk aversion concerns with the business demands. IDC’s research shows that legacy migrations that are under-funded pose significantly higher risk, and deliver lower returns, than those that are sufficiently funded from the outset. Organizations that proactively address technical debt, modernize systems, and align leadership and funding around AI-enabled outcomes will increasingly separate themselves from the pack. Those that delay will face structural disadvantages: Growing technical debt Escalating modernization costs Underperforming AI systems Slower digital revenue growth IDC’s research shows that the next wave of AI advantage in Asia/Pacific will not be determined solely by model sophistication. It will be determined by architectural foundations. Ultimately, without modernization, there can be no sustainable AI strategy.

April 14, 2026
Artificial Intelligence

Introducing MongoDB Agent Skills and Plugins for Coding Agents

Software engineering is evolving into agentic engineering. According to the Stack Overflow Developer Survey 2025, 84% of respondents use or plan to use AI tools in their development, up from 76% the previous year. At this rate, the tooling needs to keep pace. Last year, we introduced the MongoDB MCP Server to give agents the connectivity they need to interact with MongoDB, helping them generate context-aware code. But connectivity was only the start. Agents are generalists by design, and they don't inherently know the best practices and design patterns that real-world production systems demand. Today, we're addressing this by introducing official MongoDB Agent Skills: structured instructions, best practices, and resources that agents can discover and apply to generate more reliable code across the full development lifecycle, from schema design and performance optimization to implementing advanced capabilities like AI retrieval. To bring this directly into the tools you use, we're also launching plugins for Claude Code, Cursor, Gemini CLI, and VS Code, combining the MongoDB MCP Server and Agent Skills in a single, ready-to-use package. Turning coding agents into MongoDB experts Coding agents are great at producing working code, but they still make common mistakes in production systems, often defaulting to relational thinking that doesn't translate well to MongoDB, such as: Over-normalizing schemas, ignoring MongoDB's document-oriented strengths. Underusing compound indexes, causing performance bottlenecks at scale. Misusing indexes and search indexes, overlooking the consistency trade-off for high-performance full-text search. Because these pitfalls mirror common human errors, they are naturally reflected in agent outputs. MongoDB Agent Skills address this by providing expert guidance to agents, like schema design heuristics, indexing strategies, query patterns, and operational safeguards, enabling agents to ship more reliable, more consistent code faster. Agent Skills were introduced by Anthropic as an open standard and have since been adopted by the leading AI development tools, including Claude Code, Cursor, Codex, and more. This initial release covers the full application development lifecycle on MongoDB, from connection management and schema design to guidance on implementing advanced capabilities. We will continue to update and expand our skills library based on user needs. Figure 1. MongoDB Agent Skills. Scaling agentic engineering with MongoDB As organizations embrace agentic software engineering, existing processes and workflows must be reimagined. The MongoDB MCP Server and MongoDB Agent Skills are built for this shift and work best together, giving builders and agents the tools to move fast without sacrificing guardrails or control. The MongoDB MCP Server serves as the connectivity layer for your MongoDB deployments. It manages authentication and defines exactly what agents can access and do. Combined with MongoDB’s native authorization, it ensures agents operate with only the permissions they need, while giving teams governance through configurable controls like disabling specific tools. Agent Skills ensure agents follow best practices from the start, reducing architectural risk, accelerating implementation, and raising the baseline quality of every agent-generated code. While some skills can be used independently, others work in conjunction with the MongoDB MCP Server for workflows that require it. To simplify setup, the MCP Server and skills are now packaged together as plugins and extensions for Claude Code, Cursor, Gemini CLI, and VS Code, bringing these capabilities directly into your preferred tools. Figure 2. MongoDB for Claude plugin in action. We also encourage you to build your own skills as your agentic workflows mature. Whether enforcing internal naming conventions, custom data modeling patterns, or team-specific workflows, skills give you a practical way to codify institutional knowledge and ensure every agent and every developer works from the same playbook. How to get started Whether you’re using Claude Code, Cursor, Gemini CLI, or other AI development tools, you can install the MongoDB MCP Server and Agent Skills in seconds. For example, in Claude Code, install the plugin that bundles both: Code Snippet /plugin marketplace add mongodb/agent-skills /plugin install mongodb@mongodb-plugins For Cursor, Gemini CLI, and VS Code extensions, refer to their respective documentation. You can also install the skills for most coding agents using the Vercel Skills CLI (requires Node.js): Code Snippet npx skills add mongodb/agent-skills If you prefer, you can manually clone the GitHub repository and copy the skills into the appropriate folder for your agent. Similarly, to install the MongoDB MCP Server, use the following command: Code Snippet npx mongodb-mcp-server@latest setup Agentic engineering is changing how teams work, and it is changing fast. Agents need the context and guidance to meet the standards of real-world production applications. With the official MongoDB Agent Skills and plugins, builders can move faster with confidence, and organizations can adopt coding agents knowing that MongoDB best practices are embedded directly into every workflow. Next Steps Ship faster, more reliable apps on MongoDB with Agent Skills. Install for Claude Code, Cursor, Gemini CLI and VS Code!

March 31, 2026
Artificial Intelligence

Observability and OpenTelemetry: Introducing MongoDB Atlas Log Integration

In high-stakes enterprise environments, outages do not wait for business hours, and neither do IT/Network Operators. A latency spike hits the dashboard, and metrics signal that the database is under pressure. The cause? Indeterminate. Meanwhile, the business impact is immediate: orders fail to process, customers can’t access accounts, transactions stall, and critical records become temporarily unavailable. Every minute of uncertainty translates into lost revenue, frustrated users, and escalating pressure. Teams often fall back on a familiar—yet time-consuming—ritual: logging into their data platform, exporting large log files, extracting compressed archives, and manually searching through thousands of lines of entries to identify the issue. What should be a quick diagnosis becomes a manual context-switching investigation. By the time the problematic query, configuration issue, or audit event is identified, users have already experienced the disruption—and the business has absorbed the cost. MongoDB believes the database should be the heartbeat of a digital business. So we’re introducing a new log integration that brings MongoDB Atlas system and audit logs directly into external observability and storage platforms. This enhancement helps bridge the gap between metrics and meaning when it matters most. Flexible log delivery for modern observability workflows Now database operators, DevOps pros, and IT Operations teams alike can send MongoDB system and audit logs—including mongod, mongos, and audit logs—directly to the tools they already rely on: Datadog, Splunk, Google Cloud Storage, Azure Blob Storage, or Amazon S3. Beyond native integrations, MongoDB supports sending logs via OpenTelemetry (OTel), the open-source standard for collecting and transmitting telemetry data. This enables customers to export MongoDB logs to any observability or logging backend that supports OTel. By using a vendor-neutral, standards-based protocol, MongoDB fits seamlessly into modern observability architectures. This eliminates lock-in and preserves flexibility as tooling strategies evolve. Enabling real-time clarity Modern enterprises generate rich system logs essential for debugging and compliance. However, when these logs are siloed, operational inefficiencies grow. Manual log access introduces friction, delays resolution, and creates a visibility gap between metrics and logs. MongoDB’s new log integration transforms that experience with: Accelerated troubleshooting: Send logs in near real-time to observability platforms like Datadog, Splunk, or OpenTelemetry-compatible backends, enabling teams to quickly identify issues and reduce manual operational steps that slow incident resolution. Unified telemetry: Correlate MongoDB logs with application traces and infrastructure metrics in existing observability platforms, helping teams quickly understand how database behavior impacts overall system performance. Simplified compliance: Automatically route audit logs to secure long-term storage such as Amazon S3, helping organizations meet regulatory and audit requirements without manual log management. Figure 1. Atlas Log Integration configuration options for delivering MongoDB logs to observability and storage platforms. image Real-world use cases How does this look in practice for modern application, operations, and engineering teams? Here are a few examples. table The criticality of observability As applications scale, the database becomes the most critical layer of an organization’s technology stack. Missing or siloed visibility leads to costly downtime and fragmented decision-making. This log integration is available for dedicated M10+ clusters. An external sink can be configured in minutes: Navigate to the Project Integrations page in the MongoDB Atlas UI. Select the intended destination: Datadog, Splunk, Google Cloud, Microsoft Azure, Amazon S3, or any OTel log endpoint. Enter the required credentials and select the desired logs to send: mongod, mongos, or audit. Note: Atlas Search logs are also currently available via private preview. Figure 2. MongoDB Atlas logs integrated into an OpenTelemetry observability pipeline. image One observability strategy, built to scale For teams that need fast, MongoDB-centric visibility, MongoDB Atlas continues to offer powerful native tools like Query Insights and the Query Profiler. These capabilities are designed to surface what is happening inside a user’s clusters with minimal friction. However, as organizations scale, database insights can not live in isolation. MongoDB Atlas’s log integration extends observability systematically to the data plane. This enables MongoDB logs to flow into the observability platforms teams already use across engineering, security, IT operations, and compliance. With native integrations and an OpenTelemetry-compatible endpoint, teams can route logs wherever they are needed. This enables rapid troubleshooting, stronger auditability, and confident scaling without blind spots.

March 12, 2026
Home

Ready to get Started with MongoDB Atlas?

Start Free