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.
Orchestrator { # Orchestrator Agent
n1: circle label="Complex task received"
n2: rectangle label="Decompose into subtasks"
n3: rectangle label="Assign subtask to Agent B"
n4: rectangle label="Receive subtask result"
n5: rectangle label="Request shared context"
n6: rectangle label="Compile final response"
n1.handle(right) -> n2.handle(left)
n2.handle(right) -> n3.handle(left)
n3.handle(bottom) -> Worker.n7.handle(top) [label="Subtask assignment"]
n4.handle(right) -> n5.handle(left)
n5.handle(bottom) -> Broker.n11.handle(top) [label="Context request"]
n6.handle(left) -> n2.handle(bottom) [label="Next iteration"]
}
Worker { # Worker Agent
n7: rectangle label="Receive subtask"
n8: rectangle label="Fetch shared context"
n9: rectangle label="Call MCP tool"
n10: rectangle label="Return result to orchestrator"
n7.handle(right) -> n8.handle(left)
n8.handle(bottom) -> Broker.n11.handle(left) [label="Context request"]
n8.handle(right) -> n9.handle(left)
n9.handle(bottom) -> MCPServer.n13.handle(top) [label="MCP tool call"]
n10.handle(top) -> Orchestrator.n4.handle(bottom) [label="Subtask result"]
}
Broker { # Shared Context Broker
n11: rectangle label="Resolve context request"
n12: rectangle label="Return shared state"
n11.handle(right) -> n12.handle(left)
n12.handle(top) -> Orchestrator.n6.handle(bottom) [label="Context to orchestrator"]
n12.handle(left) -> Worker.n9.handle(top) [label="Context to worker"]
}
MCPServer { # MCP Server
n13: rectangle label="Execute tool"
n14: rectangle label="Return tool output"
n13.handle(right) -> n14.handle(left)
n14.handle(top) -> Worker.n10.handle(bottom) [label="Tool output"]
}
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 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
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.
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.
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.