Uber details its MCP Gateway: a unified layer for hundreds of AI agent teams
bibryam · x · 2026-10-11
Uber's engineering blog explains its MCP Gateway, a centralized orchestration and routing microservice behind all MCP interactions across the company.
Why it exists: ad-hoc per-team MCP integrations created fragmented tooling, hard-to-discover tools, and tight coupling; scaling to hundreds of teams would multiply operational complexity and security risk.
Key design points:
- Reuse existing APIs instead of rebuilding, abstracting HTTP, gRPC, and TChannel
- Cut context and token costs via Code Mode and other optimizations
- Enforce security and access control centrally
- Automate tool discovery across services
The authors advise: unless you're Uber, don't build your own gateway—mature MCP gateways already exist.
More from coding & agent
- GPT Researcher crosses 30k GitHub stars, built and maintained almost entirely by community — EdenEmarco177 · 2026-10-11
- shadcn: AI hasn't sped up abstraction design yet, it just helps me fail faster — shadcn · 2026-10-11
- Free 7-week production Agentic RAG course hits 9.7k stars on GitHub — mdancho84 · 2026-10-11
- Arize AI shows how agents can self-learn from production traces to fix their own bugs — AI Engineer · 2026-10-11
- Power User Runs AI Coding Agent 24/7, Burns Through Weekly Limit in Two Days — gandamu_ml · 2026-10-11
- Hallucinated model name sat in codebase for months, caught 6 days before a deprecated model shutdown — Trout_dev · 2026-10-11