Uber Builds MCP Gateway to Govern Access to 800+ Servers and 5,000+ AI Agent Tools

Uber has built an MCP Gateway that standardizes how AI agents discover and invoke internal services, supporting more than 800 MCP servers and 5,000 tools, the company detailed in a blog post. The architecture splits an MCP Registry control plane, which holds tool definitions, schemas, ownership and enablement settings, from a Proxy Gateway that translates MCP requests into HTTP, gRPC or TChannel calls; Uber's AutoCrawler scans Protocol Buffers and Thrift schemas to generate MCP-compatible schemas, and new tools stay disabled until owning teams review and enable them. Uber also introduced Omni MCP for incremental tool discovery and Response Projection for requesting specific response fields, as loading thousands of tool definitions into an agent's context becomes inefficient.

Uber has built an MCP Gateway to standardize how AI agents discover and invoke internal services https://www.uber.com/us/en/blog/designing-mcp-gateway/ , addressing fragmented integrations, duplicated infrastructure, and inconsistent security practices as agent adoption expands across the company. The platform supports more than 800 MCP servers and 5,000 tools, providing a common layer for discovery, protocol translation, authorization, and execution. Uber engineers describe this approach as a microservice architecture that exposes existing APIs as MCP tools without requiring changes to the underlying services. The architecture separates the MCP Registry, which acts as the control plane, from the Proxy Gateway, which handles runtime execution. The registry maintains tool definitions, schemas, ownership, and enablement settings, while the proxy translates MCP requests into HTTP, gRPC, or TChannel calls and converts responses back into MCP-compatible results. Uber MCP Gateway with APIs as tools Source: Uber Blog Post https://www.uber.com/us/en/blog/designing-mcp-gateway/ The architecture has drawn comparisons with established API gateway patterns. Ajay Sharma https://www.linkedin.com/in/ajay-sharma-76502729/ , Principal Software Engineer at Microsoft CoreAI, wrote in a LinkedIn post https://lnkd.in/p/gGxqQDvM , Azure API Gateways has been doing this for a while now. It's a recipe for order to the chaos that LLMs come with. Kelly Goetsch https://www.linkedin.com/in/kellygoetsch/ , President at Pipe17, similarly observed in a LinkedIn post https://lnkd.in/p/givtt8Ue that Uber's new MCP gateway looks identical to gateways we've built over the decades for APIs and later GraphQL. Tamir Dresher https://www.linkedin.com/in/tamirdresher/ highlighted in a LinkedIn post https://lnkd.in/p/g9v3c-Sr the continuing relevance of established distributed systems concerns, including security, discovery, observability, and governance. Uber’s AutoCrawler automates tool discovery using Cadence https://cadenceworkflow.io/?uclick id=b57d0f9c-3082-4857-9e2d-3229b3558a0d . It scans internal interface definition language IDL registries and extracts API definitions from Protocol Buffers and Thrift schemas. It then generates MCP-compatible schemas and uses a large language model to produce tool descriptions. Newly discovered tools remain disabled until their owning teams review and explicitly enable them. Configuration changes propagate to the data plane without requiring service restarts or redeployments. Auto Crawler Flow Source: Uber Blog Post https://www.uber.com/us/en/blog/designing-mcp-gateway/ The gateway enforces authorization at both server and tool levels through Uber’s internal access control system. It also supports redaction of personally identifiable information PII and other sensitive data in tool responses. For third-party integrations, including Jira and Google, a separate service exchanges internal user tokens for the corresponding third-party authentication tokens. As the tool catalog grows, loading definitions for thousands of tools into an agent’s context becomes inefficient. Uber developed Omni MCP to support incremental discovery, allowing agents to search for servers, discover relevant tools, retrieve individual schemas, and invoke selected tools as needed. Response Projection lets agents request specific response fields instead of receiving complete payloads. Uber’s aifx command-line interface https://github.com/AI-First-Exchange also enables coding agents to discover and invoke tools, writing results to files for selective inspection.