Nexus
MCP gateway that gives any LLM secure access to enterprise tools through one universal protocol
The Problem
Every AI tool integration is a custom job. Connect an LLM to Salesforce — custom code. Connect it to Jira — different custom code. Connect it to an internal database — yet another integration. Multiply this by every model, every tool, every team, and you get an integration matrix that grows quadratically.
The Model Context Protocol (MCP) solves this by standardizing how LLMs connect to external tools. But MCP alone is a protocol — someone still needs to build the gateway, handle authentication, manage rate limiting, and ensure enterprise-grade security.
The Architecture
Nexus is an MCP gateway that sits between any LLM and any enterprise tool. One gateway. Universal protocol. Zero per-tool custom integrations.
FastAPI-based server that implements the MCP specification. Receives tool requests from any MCP-compatible client, routes them to the appropriate backend service, and returns structured responses. The gateway handles protocol negotiation, request validation, and response formatting.
Enterprise tools require authentication — API keys, OAuth tokens, service accounts. Nexus manages credentials securely, injecting them at request time without exposing them to the LLM. Credentials are stored encrypted in PostgreSQL with automatic rotation support.
Redis-backed rate limiting prevents any single LLM session from overwhelming backend services. Intelligent caching of tool responses reduces redundant API calls — when 10 agents ask for the same Jira ticket in 30 seconds, only one request hits the Jira API.
New tools are registered through a declarative YAML configuration. Define the tool's name, description, input schema (Pydantic models), authentication method, and backend endpoint. Nexus generates the MCP-compatible tool definition automatically. Adding a new enterprise tool takes minutes, not days.
Technical Decisions
Async-first with automatic OpenAPI schema generation. MCP tool definitions map directly to FastAPI's Pydantic-based request/response models. The framework's dependency injection system cleanly handles per-request authentication context.
Nexus needs to run in diverse enterprise environments — cloud, on-prem, hybrid. Docker provides the consistent runtime environment. Each tool backend can run as a sidecar container with its own dependency isolation.
Horizontal scalability. When Nexus runs behind a load balancer with multiple gateway instances, rate limits must be shared across all instances. Redis provides the distributed state layer.