DevOps
A caching and compression layer that sits between agents and MCP servers, intercepting redundant context requests before they hit the wire. Uses TTL-based cache invalidation, Brotli compression, and semantic caching. Can achieve up to 95%+ token reduction and significantly lower LLM bills.
Host { # Host Application
n1: circle label="User sends prompt"
n2: rectangle label="Agent requests context"
n3: rectangle label="Receive context"
n4: rectangle label="Agent responds to user"
n1.handle(right) -> n2.handle(left)
n2.handle(bottom) -> Proxy.n5.handle(top) [label="Context request"]
n3.handle(right) -> n4.handle(left)
}
Proxy { # Context Proxy
n5: rectangle label="Receive context request"
n6: rectangle label="Check cache with TTL"
n7: diamond label="Cache hit?"
n8: rectangle label="Return cached context"
n9: rectangle label="Fetch fresh from MCP server"
n10: rectangle label="Compress and cache response"
n5.handle(right) -> n6.handle(left)
n6.handle(right) -> n7.handle(left)
n7.handle(right) -> n8.handle(left) [label="Hit"]
n7.handle(bottom) -> n9.handle(top) [label="Miss"]
n8.handle(top) -> Host.n3.handle(bottom) [label="Cached context"]
n9.handle(bottom) -> MCPServer.n11.handle(top) [label="Fetch request"]
n10.handle(top) -> Host.n3.handle(left) [label="Fresh context"]
}
MCPServer { # MCP Server
n11: rectangle label="Fetch full context"
n12: rectangle label="Return fresh data"
n11.handle(right) -> n12.handle(left)
n12.handle(top) -> Proxy.n10.handle(bottom) [label="Fresh data"]
}
DevOps
A routing pattern that puts a semantic router in front of MCP tools so the LLM only sees the subset it needs. Uses vector embeddings and cosine similarity to match user intent to tools dynamically. Achieves up to 96% reduction in input tokens when dealing with large tool catalogs.
DevOps
The simplest MCP pattern — direct connection between host application and MCP server over stdio or HTTP. No extra hops, lowest latency, easiest debugging. Perfect for MVPs, hackathons, and single-team setups where security governance is not yet a concern.
DevOps
An API gateway pattern that sits between agents and MCP servers to handle authentication, rate limits, and auditing. The gateway enforces OAuth 2.0, SAML, SSO, tool-level rate limiting, and team-based quotas. Essential for multi-team or multi-tenant MCP deployments.
DevOps
A multi-agent mesh pattern where agents communicate through a shared context broker backed by MCP. Enables coordinated tool access and state synchronization across multiple specialized agents (planner, coder, reviewer, operator). Supports both orchestrated and choreographed interaction patterns.
DevOps
A resilience pattern that wraps MCP calls with health-aware gates using three states: Closed (normal), Open (failures detected, fast-fail), and Half-Open (testing recovery). Prevents cascading failures when tools become unresponsive. Essential for production-grade reliability.
Architecture
A single-agent AI architecture where one agent handles everything: parsing requests, reasoning, calling tools via MCP, and generating responses. This is the default architecture for prototypes and simple automations—easy to debug but hits context-window limits quickly and is hard to parallelize. Ideal for MVPs and solo builders shipping fast.