Building with the MÁS stack
Here a TypeScript agent is configured to use the Grafana MCP server (written in Golang). Files are synced from Google Drive into the agent's vector store for RAG. And you can talk to the agent using the Slack app provided out-of-the-box.
➡️ Next, authorize GDrive and Slack access for your MÁS stack and deploy it. The DeepStructure platform builds and runs your agent app and MCP servers, colocated together in secure managed infrastructure. MCP servers can target any of the node.js, Python, and Golang runtimes we currently support — like a cross-language "npm" for MCP.
➡️ Now the agent and its MCP server are up and running in DeepStructure Cloud. Communicate with your new agent through a variety of interfaces:
Out-of-the-box Slack app that you add to your workspace
HTTP requests from your existing services
Email, Telegram, GitHub, Notion, and other human interfaces you can add on
OpenAI Assistants API, via the DeepStructure endpoint:
➡️ From here, the DeepStructure platform enables you to start extending your app in a variety of ways:
Augment your agents with your own tools implemented as resilient, scalable TypeScript workflows
React to events in other data stores, such as S3
Monitor and observe all runs and data flows among components of your agents and tools
Build evals around the labeled datasets that DeepStructure automatically creates for your agent inputs and outputs
Self-host in your own VPC for enterprise data governance
Ship better AI features, faster.
Take control of cost, quality, & latency.
AI infrastructure as a simple API
Bring fresh data to your LLMs, search that data and generate answers, and make calls out to other necessary tools — all managed on DeepStructure Cloud.
Familiar Assistants API yet with the optionality to use different model providers, and to customize and replace components to suit your specific needs.
Connectors to the outside world
Declaratively connect your data sources and human interfaces with our prebuilt connectors.

Closing the Developer-User loop
Use our built-in feedback system to collect usage data starting from day one.
The more usage data you collect, the better you can optimize your AI features.

TypeScript workflows with batteries included
Workflow platform that your engineering team wishes they had time to build.
We give you a Postgres, blob store, and application management out of the box.