Files
agent-framework/dotnet/samples/02-agents/Agents/Agent_Step07_AsMcpTool/Program.cs
T
c79f886dc3 .NET: Align Foundry sample environment variables and credentials. (#6422)
* dotnet: refresh Foundry sample guidance

Carry forward the still-relevant sample guidance and Foundry-specific documentation fixes from the old stacked sample migration work, adapted to the current repo layout and policy.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* dotnet: rename Foundry sample env vars

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* dotnet: remove persistent provider sample

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* dotnet: drop SAMPLE_GUIDELINES.md from this PR

Defer the guidelines doc and its cross-link to a follow-on PR to avoid broken-link failures in CI.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* dotnet: add DefaultAzureCredential warning to remaining samples

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* dotnet: address PR review feedback

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-06-11 17:26:00 +00:00

46 lines
2.0 KiB
C#

// Copyright (c) Microsoft. All rights reserved.
// This sample shows how to expose an AI agent as an MCP tool.
using Azure.AI.Projects;
using Azure.AI.Projects.Agents;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Extensions.DependencyInjection;
using Microsoft.Extensions.Hosting;
using ModelContextProtocol.Server;
var endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
var deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-5.4-mini";
// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
var aiProjectClient = new AIProjectClient(new Uri(endpoint), new DefaultAzureCredential());
// Create a server side agent and expose it as an AIAgent.
ProjectsAgentVersion agentVersion = await aiProjectClient.AgentAdministrationClient.CreateAgentVersionAsync(
"Joker",
new ProjectsAgentVersionCreationOptions(
new DeclarativeAgentDefinition(model: deploymentName)
{
Instructions = "You are good at telling jokes, and you always start each joke with 'Aye aye, captain!'.",
})
{
Description = "An agent that tells jokes.",
});
AIAgent agent = aiProjectClient.AsAIAgent(agentVersion);
// Convert the agent to an AIFunction and then to an MCP tool.
// The agent name and description will be used as the mcp tool name and description.
McpServerTool tool = McpServerTool.Create(agent.AsAIFunction());
// Register the MCP server with StdIO transport and expose the tool via the server.
HostApplicationBuilder builder = Host.CreateEmptyApplicationBuilder(settings: null);
builder.Services
.AddMcpServer()
.WithStdioServerTransport()
.WithTools([tool]);
await builder.Build().RunAsync();