neonserver

grtxx/neonserver

★ 0 stars Python 🤖 AI/LLM Updated today

Async AI chat server with MCP tool integration, persona system and streaming responses. Built with FastAPI, LangChain and Gemini.

View on GitHub → Try with Claude — $10 free →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "neonserver": {
      "command": "uvx",
      "args": [
        "neonserver"
      ]
    }
  }
}

Or install with pip: pip install neonserver

README Excerpt

A lightweight async chat server that connects a Gemini-powered AI assistant to one or more MCP (Model Context Protocol) tool servers. Built with FastAPI and LangChain, it exposes a WebSocket-based API and a minimal web frontend. Neonserver acts as the backend of a company-internal AI assistant ("NEON"). It:

Tools (20)

GETPOSTapproverequestcredentialsdatedonegidmem_contentsmem_idmessageotpsettingssidstatustitletokentoolcallupdateduserguidutf8mb4

Topics

chatbotgeminilangchainllmrag

neonserver

Quick Install

README Excerpt

Tools (20)

Topics

Related AI/LLM Servers