mirror of
https://github.com/microsoft/agent-framework.git
synced 2026-06-16 21:04:09 +08:00
08abe9e704
* feat: add Agent_Step26_FoundryToolboxMcpSkills sample Add a new sample demonstrating MCP-based skills discovery from a Foundry Toolbox endpoint using AgentSkillsProviderBuilder and AIContextProviders. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * fix: address PR review comments for Step26 sample - Add Foundry-Features: Toolboxes=V1Preview header to MCP transport options, matching the Step25 pattern - Document skill://index.json prerequisite in README Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Update dotnet/samples/02-agents/AgentsWithFoundry/Agent_Step26_FoundryToolboxMcpSkills/Program.cs Co-authored-by: Roger Barreto <19890735+rogerbarreto@users.noreply.github.com> --------- Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Co-authored-by: Roger Barreto <19890735+rogerbarreto@users.noreply.github.com>
08abe9e704
ยท
2026-05-28 12:41:33 +00:00
History
Getting started with Foundry Agents
These samples demonstrate how to use Microsoft Foundry with Agent Framework.
Quick start
The simplest way to create a Foundry agent is using the FoundryAgent type directly:
FoundryAgent agent = new(
new Uri(endpoint),
new AzureCliCredential(),
model: "gpt-5.4-mini",
instructions: "You are good at telling jokes.",
name: "JokerAgent");
Console.WriteLine(await agent.RunAsync("Tell me a joke about a pirate."));
Or using the AIProjectClient.AsAIAgent(...) extensions:
AIProjectClient aiProjectClient = new(new Uri(endpoint), new DefaultAzureCredential());
FoundryAgent agent = aiProjectClient.AsAIAgent(
model: deploymentName,
instructions: "You are good at telling jokes.",
name: "JokerAgent");
Prerequisites
- .NET 10 SDK or later
- Foundry project endpoint
- Azure CLI installed and authenticated
Set:
$env:AZURE_AI_PROJECT_ENDPOINT="https://your-foundry-service.services.ai.azure.com/api/projects/your-foundry-project"
$env:AZURE_AI_MODEL_DEPLOYMENT_NAME="gpt-5.4-mini"
Some samples require extra tool-specific environment variables. See each sample for details.
Samples
| Sample | Description |
|---|---|
| FoundryAgent lifecycle | Create a FoundryAgent directly with endpoint and credentials |
| Basics (Responses API) | Create and run an agent using AsAIAgent extensions |
| Multi-turn conversation | Multi-turn using sessions and response ID chaining |
| Multi-turn with server conversations | Server-side conversations visible in Foundry UI |
| Using function tools | Function tools |
| Function tools with approvals | Human-in-the-loop approval |
| Structured output | Structured output with JSON schema |
| Persisted conversations | Persisting and resuming conversations |
| Observability | OpenTelemetry observability |
| Dependency injection | DI with a hosted service |
| Using MCP client as tools | MCP client tools |
| Using images | Image multi-modality |
| Agent as function tool | Agent as a function tool for another |
| Middleware | Multiple middleware layers |
| Plugins | Plugins with dependency injection |
| Code interpreter | Code interpreter tool |
| Computer use | Computer use tool |
| File search | File search tool |
| OpenAPI tools | OpenAPI tools |
| Bing custom search | Bing Custom Search tool |
| SharePoint | SharePoint grounding tool |
| Microsoft Fabric | Microsoft Fabric tool |
| Web search | Web search tool |
| Memory search | Memory search tool |
| Local MCP | Local MCP client with HTTP transport |
| Code interpreter file download | Download container files generated by code interpreter |
| Foundry toolbox via MCP | Use a Foundry Toolbox from a non-hosted agent via its MCP endpoint |
| Foundry toolbox MCP skills | Use a Foundry Toolbox with MCP-based skills discovery (SEP-2640) via AIContextProviders |
Running the samples
cd dotnet/samples/02-agents/AgentsWithFoundry
dotnet run --project .\FoundryAgent_Step01