All 62 articles, sorted alphabetically
MCP authorization architecture
Deep-dive on MCP's authorization spec: protected-resource metadata discovery, dynamic client registration, PKCE consent flows…
Read article →MCP Authentication Models
How MCP servers authenticate clients (and vice versa).
Read article →MCP request cancellation architecture
Deep-dive on Model Context Protocol cancellation: the notifications/cancelled message, request-id tracking and abort primitives, threading cancellatio…
Read article →MCP capability negotiation architecture
Deep-dive on MCP capability negotiation: the initialize handshake where client and server exchange protocol versions and capabilities, the intersectio…
Read article →MCP Client Architecture in Depth
A 2500-word walkthrough of MCP client architecture: session per server, capability merge, tool namespace, resource aggregator, approval UI, health, au…
Read article →MCP Client Patterns
Discovery, multiplexing, capability matching.
Read article →MCP Client and Server
The division of responsibilities between MCP client (LLM app) and server (integration provider), and how they cooperate.
Read article →MCP completion -- argument autocompletion for tools and prompts
Deep-dive on the MCP completion capability: the argument-filling need, the server offering autocompletion suggestions, context-awareness, completion f…
Read article →MCP elicitation
Deep-dive on MCP elicitation: server requests for structured user input, schema-validated responses, client mediation and the trust boundary, user con…
Read article →MCP error handling architecture
Deep-dive on Model Context Protocol error handling: the JSON-RPC code space, why tool failures ride inside successful results with isError, cancellati…
Read article →MCP gateway architecture
Deep-dive on MCP gateways: merged policy-filtered catalogs, namespace mapping, OAuth token exchange per backend, session and notification fan-out, tra…
Read article →MCP logging architecture
Deep-dive on MCP logging: logging/setLevel, notifications/message, level enum, sinks, structured payload, throttle, PII scrub.
Read article →Multi-tenant MCP server architecture
Deep-dive on multi-tenancy for MCP servers: why isolation must live in the authenticated session rather than tool arguments, how identity flows from t…
Read article →MCP Notifications: Fire-and-Forget Messaging in the Model Context Protocol
How MCP uses id-less JSON-RPC notifications for list-changed events, progress, resource updates, and cancellation — and the idempotent, backpressure-a…
Read article →MCP OAuth Authorization
How MCP servers authorize tool callers.
Read article →Model Context Protocol Overview
What Anthropic's MCP is, why standardizing agent-tool integration matters, and how it enables a plug-and-play ecosystem.
Read article →MCP pagination architecture
Deep-dive on Model Context Protocol pagination: cursor-based paging for resources/tools/prompts lists, opaque nextCursor tokens, keyset vs offset resu…
Read article →MCP progress architecture
Deep-dive on MCP progress notifications: progress tokens, notifications/progress, cancellation, throttling, timeouts, UX.
Read article →MCP Prompt Templates
Server-defined reusable prompts that LLM clients can discover and parametrize.
Read article →MCP Prompts
How MCP servers can provide prompt templates that clients use to compose LLM requests.
Read article →MCP prompts architecture
Deep-dive on MCP prompts: templates, argument schema, auto-complete, client UI, versioning, localization, governance.
Read article →MCP Protocol Details
The technical protocol of MCP: JSON-RPC over stdio or SSE, message shapes, request/response flow.
Read article →MCP rate limiting architecture
Deep-dive on rate limiting an MCP tool server: how a per-client, per-tool token bucket admits or rejects each call — weighting expensive tools more, a…
Read article →MCP server registry -- discovering and managing servers
Deep-dive on MCP server registries: the manual-config scaling problem, the registry catalog, capability-based discovery, server metadata, publishing, …
Read article →Remote MCP Servers in 2026
Hosted MCP and the marketplace dynamics.
Read article →MCP Resource Subscriptions
How clients subscribe to resource updates and receive change notifications.
Read article →MCP resource subscriptions architecture
Deep-dive on MCP resource subscriptions: capability negotiation, resources/subscribe, the resources/updated notification, server-side subscription reg…
Read article →MCP Resources
How MCP servers expose data (files, DB rows, API responses) to LLMs via the resources primitive.
Read article →MCP resources architecture
Deep-dive on MCP resources: URI templates, list + read, subscribe + change notifications, access control, caching, and audit.
Read article →MCP roots architecture
Deep-dive on MCP roots: client declares roots, roots/list, path validation, multi-root, change notify, user consent, audit.
Read article →MCP sampling architecture
Deep-dive on MCP sampling: sampling/createMessage, host arbitration, model preferences, context inclusion, trust boundary, audit.
Read article →MCP Security
How to secure MCP deployments: sandbox untrusted servers, user consent for tool calls, and trust boundary management.
Read article →MCP Security Model
Auth, capabilities, and what a compromised server can do.
Read article →MCP Server Architecture in Depth
A 2500-word walkthrough of MCP server architecture: client, transport, capability negotiation, resources/tools/prompts, backend systems, and safety.
Read article →MCP Server Design Patterns
Tool surface, error semantics, observability.
Read article →MCP sessions -- stateful connections between client and server
Deep-dive on MCP sessions: the stateful client-server connection, initialization (handshake, version), capability negotiation (extensibility and compa…
Read article →MCP SSE Transport
How the SSE transport works, its dual-channel design, and why it's being replaced by Streamable HTTP.
Read article →MCP stdio Transport
How stdio transport works: parent spawns child, messages over stdin/stdout, and when it's the right choice.
Read article →MCP structured tool output architecture
Deep-dive on structured tool output in the Model Context Protocol: instead of flattening a tool's result into prose the calle…
Read article →MCP Server Testing Patterns
Unit and integration testing for MCP servers.
Read article →MCP tool annotations architecture
Deep-dive on MCP tool annotations: readOnlyHint, destructiveHint, idempotentHint, openWorldHint, and title; how clients turn them into auto-run/confir…
Read article →MCP Tools
How MCP servers expose callable functions (tools) with schemas, and how LLMs invoke them.
Read article →MCP Tools Architecture in Depth
A 2500-word walkthrough of MCP tools: tools/list, schemas, tools/call, structured results, safety metadata, elicitation, sampling, streaming.
Read article →MCP Transports
The transport options in MCP: stdio for local, SSE for remote, and Streamable HTTP for modern deployment.
Read article →MCP transport architecture
Deep-dive on MCP transports: stdio, HTTP+SSE, streamable HTTP, JSON-RPC framing, handshake, capability negotiation, and resumable sessions.
Read article →MCP Transport Layer Deep-Dive: stdio vs. SSE for Remote Resources
Read article →MCP Transport
When each transport fits.
Read article →MCP streaming transport architecture
Deep-dive on MCP streaming transport: SSE frames, chunked deltas, progress events, backpressure, cancel, reconnect.
Read article →MCP versioning architecture
Deep-dive on Model Context Protocol versioning: how the initialize handshake negotiates a shared protocol version, how capability flags let features e…
Read article →MCP Versioning Strategy
Capability evolution without breaking clients.
Read article →MCP vs OpenAI Function Calling
Two protocols for the same idea — when to use each.
Read article →