Configure
Set up the model provider, your front end, servers for other agents and tools, endpoint security, and the production settings.
- Model providers
Connect OpenAI, Azure OpenAI, Ollama and other local models, or your own AIAgent, and choose models that support tool calling.
- Blazor Server
Configure MentorAgent in a Blazor Web App with Server interactivity: services, the options that matter, the widget and authentication.
- Blazor WebAssembly and Auto
Keep the widget on the server, or run it in a WebAssembly or Auto client with Novior.MentorAgent.Blazor, backed by Novior.MentorAgent.Server.
- .NET MAUI
Host MentorAgent in a .NET MAUI Blazor Hybrid app, pass the signed-in user for role checks, and keep the model key on a server.
- Any front end
Use MentorAgent from React, Angular, Vue, a mobile app or any HTTP client: SignalR or Server-Sent Events, confirmation over HTTP, and how to stop an answer.
- MCP server
Expose your actions to MCP clients such as Claude Desktop or VS Code: authentication, CORS, and the actions that the server does not list.
- A2A server
Let other agents call your agent over the Agent-to-Agent (A2A) protocol: the agent card, authentication, and the actions that need confirmation.
- Secure the endpoints
Protect the SignalR hub, Server-Sent Events, /mcp and /a2a endpoints with authentication and CORS before you expose them.
- Production checklist
Settings to review before you go to production: governance defaults, safety check, rate limits, cost and routing, history, observability, and outgoing data.