ElBruno Model Context Protocol
Semantic routing for MCP tools - .NET library that indexes MCP tool definitions and returns the most relevant tools via vector search
What is ElBruno Model Context Protocol?
ElBruno Model Context Protocol is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to semantic routing for mcp tools - .net library that indexes mcp tool definitions and returns the most relevant tools via vector search
Semantic routing for MCP tools - .NET library that indexes MCP tool definitions and returns the most relevant tools via vector search
This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Semantic routing for MCP tools - .NET library that indexes M
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx elbruno-modelcontextprotocolConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use ElBruno Model Context Protocol
ElBruno.ModelContextProtocol is a .NET library that adds semantic routing to MCP tool registries. It indexes tool definitions using local ONNX embeddings and optionally a local LLM, then returns only the most relevant tools for a given prompt — reducing LLM token usage by 70-85% by avoiding sending the full tool list on every request.
Prerequisites
- .NET 8 SDK or later installed (`dotnet --version`)
- NuGet access to install the ElBruno.ModelContextProtocol.MCPToolRouter package
- Optional: Azure OpenAI credentials for samples that use cloud LLM distillation
- Approximately 90 MB disk space for the local ONNX embedding model (auto-downloaded)
- Optional: ~1 GB disk space for the local LLM used in hybrid search mode (auto-downloaded)
Add the NuGet package to your project
Install the MCPToolRouter package into your .NET project.
dotnet add package ElBruno.ModelContextProtocol.MCPToolRouterConfigure Azure OpenAI secrets (optional)
If you plan to use cloud LLM distillation in the samples, configure Azure OpenAI credentials via dotnet user-secrets.
dotnet user-secrets set "AzureOpenAI:Endpoint" "https://your-resource.openai.azure.com/" --id elbruno-mcp-samples
dotnet user-secrets set "AzureOpenAI:ApiKey" "your-api-key" --id elbruno-mcp-samples
dotnet user-secrets set "AzureOpenAI:DeploymentName" "gpt-4o-mini" --id elbruno-mcp-samplesUse embeddings-only routing (fast mode)
In your MCP server code, call SearchAsync to filter tools using local embeddings. No LLM call is made — this typically takes 1-5 ms.
var results = await ToolRouter.SearchAsync(
"What is the temperature outside?", tools, topK: 3);Use hybrid LLM+embeddings routing (accurate mode)
For complex multi-intent prompts, use SearchUsingLLMAsync to first distill the prompt with a local LLM, then apply embedding search.
var results = await ToolRouter.SearchUsingLLMAsync(
"I need to email Alice and check the weather", tools, topK: 5);Use a reusable tool index for long-running servers
Create a ToolIndex once at startup and reuse it across requests for best performance in an MCP server context.
await using var index = await ToolIndex.CreateAsync(tools);
var results = await index.SearchAsync(prompt, topK: 3);ElBruno Model Context Protocol Examples
Client configuration
Example appsettings.json for an MCP server using the ElBruno tool router with optional tuning parameters.
{
"MCPToolRouter": {
"QueryCacheSize": 100,
"MaxPromptLength": 500,
"DistillationMaxOutputTokens": 384,
"DistillationTemperature": 0.1,
"EmbeddingModelCacheDirectory": "./.models"
}
}Prompts to try
Questions that benefit from semantic tool routing in an MCP server context.
- "Which tools are most relevant for checking the current weather in my city?"
- "I want to send an email and book a calendar event — which tools do I need?"
- "Route this complex request to the right set of tools: analyze a file and post results to Slack."
- "Show me the top 3 tools for querying a database."Troubleshooting ElBruno Model Context Protocol
ONNX model fails to download on first run
Ensure your machine has internet access during the first run. The ~90 MB embedding model is downloaded automatically and cached in the directory set by EmbeddingModelCacheDirectory. Check disk space and proxy settings.
Azure OpenAI authentication fails in samples
Verify the user-secrets values are set with the correct --id flag matching the project. Run `dotnet user-secrets list --id elbruno-mcp-samples` to confirm the values are stored.
SearchAsync returns irrelevant tools
Tune the EmbeddingTextTemplate config option to customize how tool definitions are embedded. Including the tool description and parameter names in the template usually improves relevance significantly.
Frequently Asked Questions about ElBruno Model Context Protocol
What is ElBruno Model Context Protocol?
ElBruno Model Context Protocol is a Model Context Protocol (MCP) server that semantic routing for mcp tools - .net library that indexes mcp tool definitions and returns the most relevant tools via vector search It connects AI assistants to external tools and data sources through a standardized interface.
How do I install ElBruno Model Context Protocol?
Follow the installation instructions on the ElBruno Model Context Protocol GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with ElBruno Model Context Protocol?
ElBruno Model Context Protocol works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is ElBruno Model Context Protocol free to use?
Yes, ElBruno Model Context Protocol is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
ElBruno Model Context Protocol Alternatives — Similar Developer Tools Servers
Looking for alternatives to ElBruno Model Context Protocol? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.
Ecc
★ 188.2kThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Javaguide
★ 155.8kJava 面试 & 后端通用面试指南,覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Gemini CLI
★ 104.5kA secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command in
Awesome MCP Servers
★ 87.3k⭐ Curated list of Model Context Protocol (MCP) servers - tools that extend Claude Desktop, Cursor, Windsurf, and other MCP clients with custom capabilities.
MCP Servers
★ 86.0kModel Context Protocol Servers
CC Switch
★ 77.5kA cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io
Browse More Developer Tools MCP Servers
Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up ElBruno Model Context Protocol in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use ElBruno Model Context Protocol?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.