AI Agent Knowledge Library

Architect

Architecture, communication, orchestration, and context design for robust AI agent systems.

31 Published resources

Explore: Agent Architectures Context Architecture Protocols & Interoperability Workflow & Orchestration

Editor’s pick

Start with this guide

A host discovers multiple MCP servers, applies policy-aware routing, and executes calls through isolated client connections.

Architecture Guide Intermediate

Multi-Server MCP Architecture: Routing, Isolation, and Control

An architecture guide for coordinating multiple MCP servers without creating tool collisions, permission sprawl, or shared failure domains.

Knowledge library

Latest resources

31 published articles

A user-selected workspace passes through path validation before an MCP server receives access to scoped files.

Explainer Intermediate

MCP Roots and Filesystem Boundaries Explained

A security-focused guide to MCP roots, file URI validation, workspace boundaries, user consent, symlinks, and modern alternatives.

An MCP server requests model generation, the client applies policy and approval, and an approved result returns to the server.

Deep Dive Intermediate

MCP Sampling Explained: Model Calls Requested by Servers

A practical explanation of MCP sampling, including message flow, model preferences, tool use, approvals, security, and current design status.

An MCP capability signal enables a utility request that returns a bounded, privacy-aware interface result.

Reference Intermediate

MCP Logging and Completion Utilities

A practical reference to MCP logging notifications and completion suggestions, including current status, security, and implementation boundaries.

An MCP operation pauses for clearly explained user input or consent, then resumes safely with validated information.

Deep Dive Intermediate

MCP Elicitation: Requesting User Input Safely

A practical guide to requesting missing user input during MCP operations without confusing conversation, consent, or credentials.

Diagram showing many AI hosts connecting through a reusable MCP layer to business systems.

Article

Why MCP Exists: The Integration Problem It Solves

Understand why AI integrations become difficult at scale and how MCP creates a reusable boundary between AI applications and external systems.

Diagram showing an AI application hosting three MCP clients, each connected to a server for orders, policy resources, or ticket actions.

Article

What Is MCP? A Practical Guide for AI Agent Builders

A practical, beginner-friendly guide to the Model Context Protocol: its host-client-server architecture, tools and resources, request flow, trade-offs, and security boundaries.

Diagram showing model function calling producing a proposal, the host applying control, and MCP connecting to an external provider.

Article

MCP vs Function Calling: What Actually Changes?

A practical comparison of MCP and model function calling, including their boundaries, request flow, portability, security, and combined architecture.

Layer diagram showing an AI host using MCP to reach a server that calls an existing backend API.

Article

MCP vs APIs: What Changes and When to Use Each

Learn how MCP relates to REST APIs and SDKs, what each layer owns, and why most production MCP servers still call existing APIs.

Diagram showing a user request moving through an AI host and MCP to produce a verified tool result.

Article

How MCP Works: From User Request to Tool Result

Trace an MCP interaction from server discovery through model tool selection, host authorization, execution, and the final answer.