The Tool Interface
A language model produces tokens. A program takes actions. The gap between those two is the tool interface: a contract that lets the model request an action and the host execute…
Function Calling Deep Dive
The three frontier providers converged on the same tool-call loop in 2024 and then diverged on everything else. OpenAI uses `tools` and `tool_calls`. Anthropic uses `tool_use` a…
Parallel and Streaming Tool Calls
Three independent weather lookups serialized is three round trips. Run them in parallel and total time collapses to the slowest single call. Every frontier provider now emits mu…
Structured Output
"Ask the model nicely to return JSON" fails 5 to 15 percent of the time, even on frontier models. Structured outputs close that gap with constrained decoding: the model is liter…
Tool Schema Design
A correct tool fails silently when the model cannot tell when to use it. Naming, descriptions, and parameter shapes drive 10 to 20 percentage-point swings in tool-selection accu…
MCP Fundamentals
Every integration before MCP was a one-off. The Model Context Protocol, first shipped by Anthropic in November 2024 and now stewarded by the Linux Foundation's Agentic AI Founda…
Building an MCP Server
Most MCP tutorials show only stdio hello-worlds. A real server exposes tools plus resources plus prompts, handles capability negotiation, emits structured errors, and works the …
Building an MCP Client
Most MCP content ships server tutorials and waves a hand at the client. Client code is where the hard orchestration lives: process spawning, capability negotiation, tool list me…
MCP Transports
stdio works locally and nowhere else. Streamable HTTP (2025-03-26) is the remote standard. The old HTTP+SSE transport is deprecated and being removed in mid-2026. Picking the wr…
MCP Resources and Prompts
Tools get 90 percent of MCP attention. The other two server primitives solve different problems. Resources expose data for reading; prompts expose reusable templates as slash-co…
MCP Sampling
Most MCP servers are dumb executors: take arguments, run code, return content. Sampling lets a server flip direction: it asks the client's LLM to make a decision. This enables s…
MCP Roots and Elicitation
Hard-coded paths break the moment a user opens a different project. Pre-filled tool arguments break when the user under-specifies. Roots scope the server to a user-controlled se…
MCP Async Tasks
Real agent work takes minutes to hours: CI runs, deep-research synthesis, batch exports. Synchronous tool calls drop connections, time out, or block the UI. SEP-1686, merged in …
MCP Apps
Text-only tool output caps what agents can show. MCP Apps (SEP-1724, official January 26, 2026) let a tool return sandboxed interactive HTML rendered inline in Claude Desktop, C…
MCP Security I — Tool Poisoning
Tool descriptions land in the model's context verbatim. Malicious servers embed hidden instructions that users never see. Research in 2025-2026 from Invariant Labs, Unit 42, and…
MCP Security II — OAuth 2.1
Remote MCP servers need authorization, not just authentication. The 2025-11-25 spec aligns with OAuth 2.1 + PKCE + resource indicators (RFC 8707) + protected-resource metadata (…
MCP Gateways and Registries
Enterprises cannot let every dev install random MCP servers. A gateway centralizes auth, RBAC, audit, rate limiting, caching, and tool-poisoning detection, then exposes the merg…
MCP Auth in Production — Enrollment, JWKS Refresh, Audience Pinning
Lesson 16 stood up the OAuth 2.1 state machine in memory. By 2026, every MCP server you ship to a real org sits behind production auth: client enrollment that scales to an unbou…
A2A Protocol
MCP is agent-to-tool. A2A (Agent2Agent) is agent-to-agent — an open protocol for letting opaque agents built on different frameworks collaborate. Released by Google in April 202…
OpenTelemetry GenAI
An agent calls five tools, three MCP servers, and two sub-agents. You need one trace across all of it. The OpenTelemetry GenAI semantic conventions (stable attributes in v1.37 a…
LLM Routing Layer
Provider lock-in is expensive. Different tool-calling workloads suit different models. Routing gateways give one API surface, retries, failover, cost tracking, and guardrails. T…
Skills and Agent SDKs
MCP says "what tools exist." Skills say "how to do a task." The 2026 stack layers both. Anthropic's Agent Skills (open standard, December 2025) ship as SKILL.md with progressive…
Capstone — Tool Ecosystem
Phase 13 taught every piece. This capstone wires them into one production-shaped system: an MCP server with tools + resources + prompts + tasks + UI, OAuth 2.1 at the edge, an R…