| Component | Build Status | NuGet Package |
|---|---|---|
| nanoFramework.WebServer |  | |
| nanoFramework.WebServer.FileSystem |  | |
| nanoFramework.WebServer.Mcp |  | |
| nanoFramework.WebServer.Skills |  |
This library provides a lightweight, multi-threaded HTTP/HTTPS WebServer for .NET nanoFramework with comprehensive Model Context Protocol (MCP) support and AI Agent Skills Discovery (A2A-compatible) for AI agent integration.
- Multi-threaded request handling
- Static file serving with FileSystem support
- RESTful API support with parameter handling
- Route-based controllers with attribute decoration
- Authentication support (Basic, API Key)
- HTTPS/SSL support with certificates
- Model Context Protocol (MCP) for AI agent integration
- AI Agent Skills Discovery with A2A-compatible Agent Card
- Automatic tool discovery and JSON-RPC 2.0 compliance
Using the Web Server is very straight forward and supports event based calls.
// You need to be connected to a Wi-Fi or ethernet connection with a proper IP Address// Optionally you can pass a parameter with the IP address for the server to bind tousing(WebServerserver=newWebServer(80,HttpProtocol.Http)){server.CommandReceived+=ServerCommandReceived;server.Start();Thread.Sleep(Timeout.Infinite);}privatestaticvoidServerCommandReceived(objectsource,WebServerEventArgse){if(e.Context.Request.RawUrl.ToLower()=="/hello"){WebServer.OutputAsStream(e.Context.Response,"Hello from nanoFramework!");}else{WebServer.OutputHttpCode(e.Context.Response,HttpStatusCode.NotFound);}}Controllers are supported including with parametarized routes like 'api/led/{id}/dosomething/{order}'.
using(WebServerserver=newWebServer(80,HttpProtocol.Http,newType[]{typeof(MyController)})){server.Start();Thread.Sleep(Timeout.Infinite);}publicclassMyController{[Route("api/hello")][Method("GET")]publicvoidHello(WebServerEventArgse){WebServer.OutputAsStream(e.Context.Response,"Hello from Controller!");}[Route("api/led/{id}")][Method("GET")]publicvoidLedState(WebServerEventArgse){stringledId=e.GetRouteParameter("id");WebServer.OutputAsStream(e.Context.Response,$"You selected Led {ledId}!");}}Enable AI agents to interact with your embedded devices through standardized tools and JSON-RPC 2.0 protocol.
publicclassIoTTools{[McpServerTool("read_sensor","Reads temperature from sensor")]publicstaticstringReadTemperature(){// Your sensor reading codereturn"23.5°C";}[McpServerTool("control_led","Controls device LED","Output the status of the LED")]publicstaticstringControlLed(LedCommandcommand){// Your LED control codereturn$"LED set to {command.State}";}}publicclassLedCommand{publicstringState{[Description("LED state: on, off, or blink")]get;set;}}You can define reusable, high-level prompts for AI agents using the McpServerPrompt attribute. Prompts encapsulate multi-step instructions or workflows that can be invoked by agents.
Here's a simple example:
usingnanoFramework.WebServer.Mcp;publicclassMcpPrompts{[McpServerPrompt("echo_sanity_check","Echo test prompt")]publicstaticPromptMessage[]EchoSanityCheck(){returnnewPromptMessage[]{newPromptMessage("Call Echo with the string 'Hello MCP world!' and return the response.")};}}Prompts can be discovered and invoked by AI agents in the same way as tools. You can also define prompts with parameters using the McpPromptParameter attribute.
publicstaticvoidMain(){// Connect to WiFi firstvarconnected=WifiNetworkHelper.ConnectDhcp(Ssid,Password,requiresDateTime:true);// Discover and register MCP toolsMcpToolRegistry.DiscoverTools(newType[]{typeof(IoTTools)});// Discover and register MCP promptsMcpPromptRegistry.DiscoverPrompts(newType[]{typeof(McpPrompts)});// Start WebServer with MCP supportusing(varserver=newWebServer(80,HttpProtocol.Http,newType[]{typeof(McpServerController)})){// Optional customizationMcpServerController.ServerName="MyIoTDevice";McpServerController.Instructions="IoT device with sensor and LED control capabilities.";server.Start();Thread.Sleep(Timeout.Infinite);}}Once running, AI agents can discover and invoke your tools:
// Tool discoveryPOST /mcp
{
"jsonrpc": "2.0",
"method": "tools/list",
"id": 1
}
// Tool invocationPOST /mcp
{
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"name": "control_led",
"arguments": {"State": "on"}
},
"id": 2
}Expose device capabilities as discoverable skills for AI agents using the A2A (Agent2Agent) protocol conventions.
usingnanoFramework.WebServer.Skills;[Skill("climate","Climate Control","HVAC management for building zones")][SkillTag("temperature")][SkillTag("hvac")][SkillExample("What is the current temperature?")]publicclassClimateSkill{[SkillAction("GetTemperature","Reads current room temperature")]publicstaticdoubleGetTemperature(){return22.5;}[SkillAction("SetTarget","Sets the target temperature")]publicstaticboolSetTarget(TargetInputinput){returntrue;}}publicclassTargetInput{publicdoubleTemperature{[Description("Target temperature in Celsius")]get;set;}}publicstaticvoidMain(){// Connect to WiFi firstvarconnected=WifiNetworkHelper.ConnectDhcp(Ssid,Password,requiresDateTime:true);// Discover and register skillsSkillRegistry.DiscoverSkills(newType[]{typeof(ClimateSkill)});// Start WebServer with Skills Discovery supportusing(varserver=newWebServer(80,HttpProtocol.Http,newType[]{typeof(SkillDiscoveryController)})){// Optional customizationSkillDiscoveryController.AgentName="SmartThermostat";SkillDiscoveryController.AgentDescription="Embedded HVAC controller with sensor capabilities";server.Start();Thread.Sleep(Timeout.Infinite);}}Once running, AI agents can discover and invoke your skills:
GET /.well-known/agent-card.json{
"name": "SmartThermostat",
"description": "Embedded HVAC controller with sensor capabilities",
"version": "1.0.0",
"skills": [
{
"id": "climate",
"name": "Climate Control",
"tags": ["temperature", "hvac"],
"actions": [
{ "name": "GetTemperature", "description": "Reads current room temperature" },
{ "name": "SetTarget", "description": "Sets the target temperature" }
]
}
]
}POST /skills/invokeContent-Type: application/json
{ "skill": "climate", "action": "GetTemperature", "arguments": {} }| Topic | Description |
|---|---|
| Controllers and Routing | Learn about route attributes, method decorations, and URL parameters |
| Authentication | Configure Basic Auth, API Key, and custom authentication |
| HTTPS and Certificates | Set up SSL/TLS encryption with certificates |
| File System Support | Serve static files from storage devices |
| Model Context Protocol (MCP) | Complete MCP guide for AI agent integration |
| AI Agent Skills Discovery | A2A-compatible skills discovery and invocation |
| REST API Development | Build RESTful APIs with request/response handling |
| Event-Driven Programming | Handle requests through events and status monitoring |
| Examples and Samples | Working examples and code samples |
- No compression support in request/response streams
- MCP implementation supports server features only (no notifications or SSE)
- No or single parameter limitation for MCP tools and Skills actions (use complex objects for multiple parameters)
- Prompt parameters, when declared, are always mandatory.
- Skills Discovery implements A2A discovery and invocation only (no task lifecycle)
Install 'nanoFramework.WebServer' for the Web Server without File System support. Install 'nanoFramework.WebServer.FileSystem' for file serving, so with devices supporting File System. Install 'nanoFramework.WebServer.Mcp' for MCP support. It does contains the full 'nanoFramework.WebServer' but does not include native file serving. You can add this feature fairly easilly by reusing the code function serving it. Install 'nanoFramework.WebServer.Skills' for A2A-compatible AI Agent Skills Discovery. Like MCP, it includes the core 'nanoFramework.WebServer' and can be used alongside MCP.
For documentation, feedback, issues and contributions, please refer to the Home repo.
Join our Discord community here.
The list of contributors to this project can be found at CONTRIBUTORS.
Licensed under the MIT license.
This project has adopted the code of conduct defined by the Contributor Covenant to clarify expected behaviour in our community. For more information see the .NET Foundation Code of Conduct.
This project is supported by the .NET Foundation.