Tools And Protocols
23 个课时
01 The Tool Interface — Why Agents Need Structured I/O
CODE 1 OUTPUTS
✓ → 02 Function Calling Deep Dive — OpenAI, Anthropic, Gemini CODE 1 OUTPUTS
✓ → 03 Parallel Tool Calls and Streaming with Tools CODE 1 OUTPUTS
✓ → 04 Structured Output — JSON Schema, Pydantic, Zod, Constrained Decoding CODE 1 OUTPUTS
✓ → 05 Tool Schema Design — Naming, Descriptions, Parameter Constraints CODE 1 OUTPUTS
✓ → 06 MCP Fundamentals — Primitives, Lifecycle, JSON-RPC Base CODE 1 OUTPUTS
✓ → 07 Building an MCP Server — Python + TypeScript SDKs CODE 1 OUTPUTS
✓ → 08 Building an MCP Client — Discovery, Invocation, Session Management CODE 1 OUTPUTS
✓ → 09 MCP Transports — stdio vs Streamable HTTP vs SSE Migration CODE 1 OUTPUTS
✓ → 10 MCP Resources and Prompts — Context Exposure Beyond Tools CODE 1 OUTPUTS
✓ → 11 MCP Sampling — Server-Requested LLM Completions and Agent Loops CODE 1 OUTPUTS
✓ → 12 Roots and Elicitation — Scoping and Mid-Flight User Input CODE 1 OUTPUTS
✓ → 13 Async Tasks (SEP-1686) — Call-Now, Fetch-Later for Long-Running Work CODE 1 OUTPUTS
✓ → 14 MCP Apps — Interactive UI Resources via `ui://` CODE 1 OUTPUTS
✓ → 15 MCP Security I — Tool Poisoning, Rug Pulls, Cross-Server Shadowing CODE 1 OUTPUTS
✓ → 16 MCP Security II — OAuth 2.1, Resource Indicators, Incremental Scopes CODE 1 OUTPUTS
✓ → 17 MCP Gateways and Registries — Enterprise Control Planes CODE 1 OUTPUTS
✓ → 18 MCP Auth in Production — DCR, JWKS Rotation, Audience-Pinned Tokens on iii Primitives CODE 1 OUTPUTS
✓ → 19 A2A — Agent-to-Agent Protocol CODE 1 OUTPUTS
✓ → 20 OpenTelemetry GenAI — Tracing Tool Calls End-to-End CODE 1 OUTPUTS
✓ → 21 LLM Routing Layer — LiteLLM, OpenRouter, Portkey CODE 1 OUTPUTS
✓ → 22 Skills and Agent SDKs — Anthropic Skills, AGENTS.md, OpenAI Apps SDK CODE 1 OUTPUTS
✓ → 23 Capstone — Build a Complete Tool Ecosystem CODE 1 OUTPUTS
✓ →