Skip to main content
Ultra is built as a layered proxy with clear separation between transport, processing, routing, and storage. It runs locally on each user’s machine as a single binary — MCP clients launch it as a subprocess, and all processing happens on-device. There are no cloud components in the data path.

​
System Architecture

​
Layers

​
Transport Layer

Handles MCP protocol communication. Ultra supports all MCP transport types:
  • stdio — Standard I/O for local clients (Claude Desktop, Cursor, Codex)
  • HTTP/SSE — Server-sent events over HTTP
  • Streamable HTTP — Modern HTTP streaming
The client-facing side typically uses stdio (since MCP clients launch Ultra as a subprocess), while upstream connections use whatever transport the server requires.

​
Pipeline

The interceptor chain processes every request and response, handling tracing, logging, auditing, and metrics.

​
Aggregator

The aggregator manages connections to upstream MCP servers and presents them as a single unified interface to the client.

​
Storage

Observability data is stored locally on the gateway by default, with optional sync to Ultra Hub for cloud deployments.