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

Knowledge library

More resources — Page 2

31 published articles

Architecture diagram showing an MCP host with dedicated clients connecting to focused local and remote servers.

Article

MCP Architecture: Hosts, Clients, Servers, Tools, and Resources

A component-by-component guide to MCP architecture, including host and client responsibilities, server primitives, transports, and trust boundaries.

A model proposes an MCP tool, the host approves it, and the server performs the action.

Explainer Beginner

MCP Tools Explained: How AI Agents Take Action

A practical guide to MCP tools, including schemas, discovery, execution, approvals, errors, and safe production design.

MCP messages travel to a local process over STDIO or to a remote service over Streamable HTTP.

Comparison Intermediate

MCP Transports: STDIO vs Streamable HTTP

Understand how MCP messages travel over STDIO and Streamable HTTP and how to choose the right transport for local and remote servers.

An MCP resource identified by URI is selected by the host and added to model context.

Explainer Beginner

MCP Resources Explained: Giving Agents the Right Context

Understand MCP resources, resource URIs, templates, discovery, reading, subscriptions, and safe context selection.

An MCP client declares version metadata, discovers server capabilities, and sends compatible requests.

Deep Dive Intermediate

MCP Lifecycle and Capability Negotiation

A current guide to MCP version compatibility, capability discovery, request metadata, feature use, and the transition from older handshakes.

A user selects an MCP prompt template that produces structured messages for an AI application.

Explainer Beginner

MCP Prompts Explained: Reusable Workflows for AI Applications

A practical guide to MCP prompts, including discovery, arguments, message content, user control, safety, and design patterns.

MCP security trust boundaries from user through application policy and client authorization to the MCP server and backend business system.

Explainer Intermediate

MCP Security and Permissions

A practical security model for MCP trust boundaries, authorization, least privilege, approvals, external content, backend credentials, and auditability.

Explainer Intermediate

MCP Client Architecture

Understand how an MCP host manages dedicated clients, discovers server capabilities, applies policy, invokes operations, and handles failures.

Production MCP and A2A architecture with a user, coordinator agent, CRM database and search through MCP, and a specialist agent through A2A using specialist tools through MCP.

Explainer Intermediate

MCP + A2A Production Architecture

A production architecture for combining MCP capability access with A2A specialist delegation while preserving policy, identity, tracing, and failure boundaries.

Tutorial Intermediate

Building an MCP Server

A framework-neutral tutorial for designing, implementing, testing, securing, and deploying an MCP server over real backend systems.