Uber details its MCP Gateway, the unified platform all its AI agents use to reach backends
AxSaucedo · x · 2026-10-09
Uber engineers published a deep dive on their MCP Gateway, now the single platform all company AI agents traverse to reach backend systems.
- Ad-hoc per-team MCP integrations proved agents dramatically more capable with live business context, but created fragmentation: tools hard to discover, unreliable to operate, tightly coupled to specific services
- As hundreds of teams adopted agentic workflows, Uber needed a centralized, scalable layer
The Gateway design goals:
- Orchestration and routing layer between agents and backends
- Abstracts protocol differences (HTTP, gRPC, TChannel)
- Enforces consistent security and observability guarantees
- Makes MCP tools easy to create, discover and reuse across the company
A reference architecture for enterprises scaling MCP and agents.
More from coding & agent
- vLLM on K8s: GPU Faults Can Render a Node Unusable — Inference Is Stateful — tianyin_xu · 2026-10-09
- Addy Osmani: Agents Erode Engineers' Joy of Knowing — If You Only Pick, Never Conjure — addyosmani · 2026-10-09
- Relevance and instruction following: the third automated AI quality check — goyalshaliniuk · 2026-10-09
- 7 Quality Checks to Automate Before Your AI App Ships to Production — goyalshaliniuk · 2026-10-09
- Dev calls for a truly intelligent model selector in Codex/ChatGPT after GPT-5's router flops — flowersslop · 2026-10-09
- Claude Code's Web Search Queries Get Increasingly Unhinged as Projects Progress — jwt0625 · 2026-10-09