Uber Cuts AI Costs with 1,000 MCP Servers and Zero Schema Bloat

Uber unified over 1,000 MCP server interactions through a single gateway and reduced tool schema overhead from 50–70k tokens to nearly zero. Since April 2026, total AI costs have remained flat even as active AI tool users grew 7x and agent requests grew 9.4x.

• Cost of 1,000 requests cut by ~34%, sessions by 52% from peak
• Schemas for 100+ tools added 50–70k tokens to each request
• Three approaches: CLI calls, tool search, and code-mode with batch execution
• About 25 ready-made code-mode skills created for popular tools