semantic-router Model Context Protocol (MCP) Server

GitHub

A programmable Mixture-of-Models router for heterogeneous LLM inference

5,131 stars Go Go 1 file · ~2,147 tokens #ai-gateway#bert-classification#fine-tuning#golang#huggingface-candle#huggingface-transformers#kubernetes#llm

semantic-router MCP Server

MCP server for vllm-project/semantic-router

Ready-to-Use Client Configurations 
{
  "mcpServers": {
    "semantic-router": {
      "command": "npx",
      "args": [
        "-y",
        "@vllm-project/semantic-router"
      ]
    }
  }
}