Roger Barreto
15df1152fc
* Add sample for per-run refreshable MCP authentication headers Adds a Foundry RAPI sample that attaches per-run, refreshable authentication headers to MCP requests using existing primitives: a DelegatingHandler on the MCP transport's HttpClient plus an AsyncLocal run scope. The same agent runs under two contexts, each minting a fresh token, proving the header is per run rather than bound at agent or connection creation time. The handler attaches the bearer only over HTTPS to the MCP server's own origin, logs the non-secret label only, disables cookies, and checks certificate revocation. The README covers security considerations and production notes. Fixes #1631 * Address PR review: harden redirect handling, nest-safe scope, README env vars Disable AllowAutoRedirect on the shared handler so a redirect cannot carry the bearer past the origin check. Save and restore the prior run scope instead of clearing to null so the helper is safe under nesting. Note the Foundry env vars in the samples folder README row and update the sample README security notes.
Getting started
The getting started samples demonstrate the fundamental concepts and functionality of the agent framework.
Samples
| Sample | Description |
|---|---|
| Agents | Step-by-step instructions for getting started with agents |
| Foundry | Foundry agent samples using FoundryAgent and AIProjectClient.AsAIAgent(...) |
| Agent Providers | Getting started with creating agents using various providers |
| Agents With Retrieval Augmented Generation (RAG) | Adding Retrieval Augmented Generation (RAG) capabilities to your agents |
| Agents With Memory | Adding memory capabilities to your agents |
| Agents With CodeAct (Hyperlight) | Enabling sandboxed code execution (CodeAct) for your agents via Hyperlight |
| Agent Open Telemetry | Getting started with OpenTelemetry for agents |
| OpenAI | Using OpenAI exchange types with agents |
| Anthropic | Getting started with agents using Anthropic Claude |
| Model Context Protocol | Getting started with Model Context Protocol |
| Agent Skills | Getting started with Agent Skills |
| Agent Harness with built-in tools | Demonstrating how to build an Agent Harness with built-in planning, todo, and mode management tooling |
| Declarative Agents | Loading and executing AI agents from YAML configuration files |
| AG-UI | Getting started with AG-UI (Agent UI Protocol) servers and clients |
| Dev UI | Interactive web interface for testing and debugging AI agents during development |
| A2A Agents | Working with Agent-to-Agent (A2A) specific features |