Show HN: Toolnexus for .NET – MCP and agent skills as tools for any LLM

Toolnexus 0.1.2, a C#/.NET library that unifies MCP servers, agent skills, custom functions, and HTTP endpoints into a single tool set for any LLM, has been released. The library enables building agents in a few lines of code with features like streaming, retries, and memory, and is a port of the same library available in JavaScript, Python, Go, and Java.

Toolnexus 0.1.2 dotnet add package Toolnexus --version 0.1.2 NuGet\Install-Package Toolnexus -Version 0.1.2 Install-Package https://docs.microsoft.com/nuget/reference/ps-reference/ps-ref-install-package . <PackageReference Include="Toolnexus" Version="0.1.2" / PackageReference https://docs.microsoft.com/nuget/consume-packages/package-references-in-project-files , copy this XML node into the project file to reference the package. <PackageVersion Include="Toolnexus" Version="0.1.2" / Directory.Packages.props <PackageReference Include="Toolnexus" / Project file Central Package Management CPM https://learn.microsoft.com/en-us/nuget/consume-packages/central-package-management , copy this XML node into the solution Directory.Packages.props file to version the package. paket add Toolnexus --version 0.1.2 maintainers https://fsprojects.github.io/Paket/contact.html for support. r "nuget: Toolnexus, 0.1.2" :package Toolnexus@0.1.2 addin nuget:?package=Toolnexus&version=0.1.2 Install as a Cake Addin tool nuget:?package=Toolnexus&version=0.1.2 Install as a Cake Tool maintainers https://cakebuild.net/support/nuget for support. toolnexus Build an agent in a few lines. Point at an mcp.json and a skills/ folder, call RunAsync , and you have a working agent — MCP servers, agent skills, your own functions, and HTTP endpoints unified as one tool set, driving any LLM. Right-sized.Not a framework no builders, no config to wade through , not a toy that falls over the moment you need streaming or a retry. Everything a real agent needs — the loop, hooks, streaming, retries, memory — and nothing it doesn't. The C /.NET port of toolnexus https://github.com/muthuishere/toolnexus — the same library, byte-identical, also in JavaScript, Python, Go, and Java . Built on the official ModelContextProtocol SDK. Targets .NET 10. Install dotnet add package Toolnexus An agent in 3 steps using Toolnexus; // 1. tools from an mcp.json + a skills/ folder await using var tk = await Toolkit.CreateAsync new Toolkit.Options .WithMcpConfig "./mcp.json" .WithSkillsDir "./skills" ; // 2. point at any OpenAI- or Anthropic-style endpoint var agent = LlmClient.Create new LlmClient.Options { BaseUrl = "https://openrouter.ai/api/v1", Style = "openai", // or "anthropic" Model = "openai/gpt-4o-mini", ApiKey = Environment.GetEnvironmentVariable "OPENROUTER API KEY" , } ; // 3. run — skills injected into the system prompt, tools called for you, looped to an answer var res = await agent.RunAsync "Refund order 1234 for the customer.", tk ; Console.WriteLine res.Text ; The loop runs call → execute tools → feed back → repeat, with hooks, streaming, retries/backoff, and conversation memory available. res carries Text , ToolCalls , usage, turns, and model. Add your own tools using Toolnexus; // a method → a tool attribute-based public sealed class MathTools { ToolMethod "add", "Add two numbers" public string Add Param "a" double a, Param "b" double b = a + b .ToString ; } tk.Register Tools.FromObject new MathTools .ToArray ; // a REST endpoint → a tool tk.Register HttpTool.Of new HttpTool.Options { Name = "create ticket", Description = "Create a ticket", Method = "POST", Url = "https://api.example.com/tickets", Headers = new Dictionary<string, string { "Authorization" = "Bearer ${API TOKEN}" }, // ${ENV} expands, never logged InputSchema = new Dictionary<string, object? { "type" = "object", "properties" = new Dictionary<string, object? { "title" = new Dictionary<string, object? { "type" = "string" } }, "required" = new List<object? { "title" }, }, } ; You can also pass ExtraTools / AnnotatedObjects straight into Toolkit.Options . Bring your own loop js var tools = tk.ToOpenAI ; // or tk.ToAnthropic / tk.ToGemini var system = tk.SkillsPrompt ; // skills catalog for your system prompt // when the model returns a tool call name, arguments : var res = await tk.ExecuteAsync name, args ; // - ToolResult Output, IsError, Metadata The four sources | Source | How | |---|---| MCP servers | an mcp.json mcpServers / servers / mcp ; local stdio + remote streamable-HTTP, Headers for auth | Agent skills | a folder of <name /SKILL.md ; a skill tool loads each on demand + a system-prompt catalog | Native tools | ToolMethod / Param on a class Tools.FromObject , or NativeTool.Of ... | HTTP / REST | HttpTool.Of ... — an endpoint becomes a tool, ${ENV} headers | All four appear as one uniform ITool in tk.Tools . API | Member | Description | |---|---| Toolkit.CreateAsync opts | async factory → Toolkit await using | LlmClient.Create opts | the unified host loop RunAsync / StreamAsync | tk.Tools | the uniform tools | tk.ExecuteAsync name, args, ctx? | run a tool → ToolResult | tk.SkillsPrompt | system-prompt skill catalog | tk.ToOpenAI / ToAnthropic / ToGemini | provider tool schemas | tk.Register params ITool | add native/http/custom tools | More Full docs, the other four language ports, the shared behavior spec, and runnable examples: https://github.com/muthuishere/toolnexus https://github.com/muthuishere/toolnexus MIT licensed. Product | Versions Compatible and additional computed target framework versions. | |---|---| | .NET | net10.0 is compatible. net10.0-android was computed. net10.0-browser was computed. net10.0-ios was computed. net10.0-maccatalyst was computed. net10.0-macos was computed. net10.0-tvos was computed. net10.0-windows was computed. | Learn more about Target Frameworks https://docs.microsoft.com/dotnet/standard/frameworks and .NET Standard https://docs.microsoft.com/dotnet/standard/net-standard .- net10.0 - ModelContextProtocol /packages/ModelContextProtocol/ = 1.4.0 - NuGet packages This package is not used by any NuGet packages. GitHub repositories This package is not used by any popular GitHub repositories.