Skip to main content

Uber MCP Gateway – Somasundara & Tehrani

Speakers: Meghana Somasundara (Agentic AI Lead) and Rush Tehrani (Head of Engineering, Agentic AI Platform), Uber

Uber Scale Metrics

MetricValue
Engineers5,000+
Engineers using AI weekly90%+
Internal services10,000+
Internal agents1,500+
Executions per week60,000+

"This is no longer a pilot program at Uber. It's the new standard for how we work."

MCP Gateway & Registry

Built a control plane for all MCP interactions:

Gateway Orchestrator: Crawls 10,000+ service IDLs, generates MCP tool definitions with LLM, stores in object storage.

Gateway Service: Serves MCP servers, allows service owners to update definitions, diff, security scan, and commit.

Security: Authorization service integration, PII redaction (automatic), periodic code scanning, full observability and audit trails. Third-party MCPs get extra data scanning and sandboxed environments.

Three Consumption Surfaces

SurfaceTypeKey Features
Uber Agent BuilderNo-codeThousands active monthly, workflow automation
Uber Agent SDKCode-firstGrocery assistant, care coordination, customer support
Coding AgentsDeveloper toolsClaude Code, Cursor, Minions — 1,800 code changes/week, 95% of engineers

Agent Configuration Patterns

  • Agent Builder: Mention MCP server in instructions, pick tools, parameter overlays
  • Agent SDK: YAML config with MCP name, tool selection, parameter overrides
  • Coding Agents: AIFX CLI — mcp add command for remote/local servers

Roadmap

  1. Tool Search — Discover tools automatically, load on demand
  2. Skills — Recipes for using MCPs, shareable across teams
  3. Evaluations — Evaluate skill invocation, output quality, A/B testing

Key Quotes

"With thousands of MCPs, chaos was coming quickly. MCP and registries were going to make AI usable at numbers."

"Coding agents are producing about 1,800 code changes a week right now, used by 95% of our engineers."