Building the Live Context Graph for Agents, 28 Weekly Releases Later | Materialize

Sign In Get Started

Table of Contents<br>Build and iterate on your context graph<br>Allow agents to discover & query data products, using our MCP Server for Agents<br>Performance for agent-scale workloads<br>Iterate on the context graph, using replacement materialized views<br>Moving towards a headless developer experience<br>Make coding agents productive with our developer MCP server and agent skills<br>Faster development for software engineers and coding agents with mz-deploy<br>Don't ignore the humans: new UIs in the console<br>Up to 75% faster DDL<br>Connect to all your sources and sinks<br>Deliver to your warehouse with the Iceberg sink<br>Copy static data from object storage<br>Handle upstream schema changes with source versioning<br>Performance improvements<br>Enterprise readiness<br>SSO and OIDC support on Self-Managed<br>HA database support on Self-Managed<br>One weekly release at a time

Table of Contents

Agents need a tight feedback loop: observe data as context, act, and observe again to figure out if the actions were successful.<br>Imagine a logistics agent which has to:<br>reroute a late shipment<br>then read inventory and ETAs to confirm the reroute landed<br>finally, alert customers about the change<br>Traditional solutions weren't designed for agentic feedback loops like this. OLTP databases can't keep up with the volume of complex queries, and warehouses can't maintain the data freshness required.<br>This era needs a new category of infrastructure; infrastructure that can keep data fresh, and consistent, so that agents have the feedback loop they need.<br>I'm biased, of course, but I believe Materialize is the right tool for the job.<br>If you've followed us from the early days, you know the core idea: maintain views incrementally, so the result is already computed, and is served in milliseconds. Incremental view maintenance lets you easily build a live context graph for your agents: an interconnected set of data products, which represent key business objects such as Customers, Orders, or Shipments.

We've worked closely with customers like Bilt Rewards and Crane Worldwide Logistics to enable this pattern. 28 weekly Materialize releases later, we've made it easier to connect agents to your context graph, operate without a human in the loop, connect to all your data sources, and run with enterprise grade security.<br>If you want to start building right away, check out our guide to get started now. But if you want to learn about what's new, read on!<br>Build and iterate on your context graph

As mentioned in the introduction, we think of the context graph as an interconnected set of data products. In Materialize, data products are simply materialized views, or indexed views, which are kept up to date as data changes. Maintaining these data products is just step one though; you need to expose them to your agents and iterate on them.<br>Allow agents to discover & query data products, using our MCP Server for Agents

The Materialize MCP Server for agents allows your agents to discover and query data products. You can create an ontology of these data products, and expose the ontology to an agent so that it understands the relationships between your data. Once your agent understands the data, it can query & join.<br>A benefit of Materialize's model is that you can create a bespoke data product for each agent if you want to. Using bespoke data products is optional, but it makes data governance simple using our RBAC model; just grant your agent SELECT privileges on exactly the data it should see. To accomplish this with a data warehouse, you'd need to create "just another pipeline" and introduce more lag. On Materialize it's just a few lines of SQL. And you can trust that your agent's bespoke data product will remain correct and fresh.

The MCP server for Agents is available today, and endpoints are included with every Materialize environment.<br>Performance for agent-scale workloads

Agents query far more aggressively than humans or dashboards do. So we've significantly increased maximum queries per second, connections per second. We've improved tail latency; in our tests we saw 50% reductions in p99 latency.

We've also shipped optimizations that substantially reduce CPU usage for views with temporal filters, making these viable for agent scale workloads. While specific results are workload dependent, in our tests, we saw CPU usage drop substantially.

Iterate on the context graph, using replacement materialized views

Materialize allows you to build cascading data products, for instance, a materialized view which reads from another materialized view. Since all the materialized views are maintained incrementally, this topology is very cheap to maintain. But as you can imagine, with a cascade of downstream dependencies, iterating on a data product can be hard. With replacement materialized views, we're making it much easier.<br>Imagine you're a logistics firm, with a data topology like this. And imagine...