Skip to content

Enhance ResearcherAgent to handle Microsoft Learn MCP server unavaila… #27

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
JesseLiberty merged 1 commit into from
Sep 6, 2026
Merged

Enhance ResearcherAgent to handle Microsoft Learn MCP server unavaila… #27

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
34 changes: 22 additions & 12 deletions Program.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -116,20 +116,30 @@ async Task<HttpResponseMessage> PostWithRetryAsync(string requestUri, object bod
name: "tavily_search",
description: "A search engine optimized for comprehensive, accurate, and trusted results.");

// Microsoft Learn's remote MCP server exposes docs search/fetch tools the
// Researcher can call alongside Tavily for authoritative Microsoft/Azure content.
await using McpClient microsoftLearnMcp = await McpClient.CreateAsync(
new HttpClientTransport(new HttpClientTransportOptions
{
Endpoint = new Uri("https://learn.microsoft.com/api/mcp"),
Name = "microsoft-learn",
}));
IList<McpClientTool> microsoftLearnTools = await microsoftLearnMcp.ListToolsAsync();

List<AIFunction> researcherTools = [tavilyTool, .. microsoftLearnTools];

// Creating a callable object
using ILoggerFactory loggerFactory = LoggerFactory.Create(builder => builder.AddConsole());
ILogger startupLogger = loggerFactory.CreateLogger("BlogWriter.Startup");

// Microsoft Learn's remote MCP server exposes docs search/fetch tools the
// Researcher can call alongside Tavily for authoritative Microsoft/Azure content.
// If the remote endpoint is unreachable/slow/erroring at startup, don't let it
// take down the whole app — fall back to Tavily-only tools.
List<AIFunction> researcherTools = [tavilyTool];
try
{
McpClient microsoftLearnMcp = await McpClient.CreateAsync(
new HttpClientTransport(new HttpClientTransportOptions
{
Endpoint = new Uri("https://learn.microsoft.com/api/mcp"),
Name = "microsoft-learn",
}));
IList<McpClientTool> microsoftLearnTools = await microsoftLearnMcp.ListToolsAsync();
researcherTools.AddRange(microsoftLearnTools);
}
Comment on lines +127 to +138
catch (Exception ex)
{
startupLogger.LogWarning(ex, "Microsoft Learn MCP server unavailable; continuing with Tavily-only research tools.");
}
Comment on lines +139 to +142

var bloggerAgent = new BloggerAgent(llm, chatOptions, loggerFactory.CreateLogger<BloggerAgent>());
var researcherAgent = new ResearcherAgent(llm, chatOptions, researcherTools, loggerFactory.CreateLogger<ResearcherAgent>());
Expand Down
5 changes: 2 additions & 3 deletions ResearcherAgent.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -58,9 +58,8 @@ public ResearcherAgent(IChatClient llm, ChatOptions chatOptions, IEnumerable<AIF
.Use(async (agent, context, next, cancellationToken) =>
{
_logger.LogInformation(
"Researcher invoking tool '{Tool}' with arguments {Arguments}",
context.Function.Name,
context.Arguments);
"Researcher invoking tool '{Tool}'...",
context.Function.Name);

return await next(context, cancellationToken);
})
Expand Down