Installation: Seamless Integration, Precision Perfected

Elevate your setup with Installation—expertly designed for seamless integration, saving time and ensuring flawless results. Trusted by professionals for precision every time." )

Visit Repository

✨ Developer Tools

4.0(38 reviews)

57 saves

26 comments

Ranked in the top 3% of all AI tools in its category

About Installation

What is Installation: Seamless Integration, Precision Perfected?

Imagine setting up a chatbot framework that just works—no guesswork, no missing dependencies. This guide walks you through installing LibreChat with its MCP server and Ollama integration. Think of it like building a LEGO set where every piece snaps into place. The magic? Configuring MongoDB, setting up Ollama models, and linking tools to fetch IP addresses—all in under 15 minutes (if you’re not as slow as me).

How to Use Installation: Seamless Integration, Precision Perfected?

Bootstrap the IP Server: Navigate to IpServer and run npm install && npm run build && npm start. This is your foundational server—think of it as the engine room of your chatbot fleet.
Spin up MongoDB: Launch a local instance on mongodb://127.0.0.1:27017. I prefer using MongoDB Compass here for visual confirmation, but the CLI works too.
Deploy LibreChat: Clone the repo via git clone, configure the .env, and execute npm run frontend && npm run backend. The frontend build always takes me longer—don’t panic if it feels slow.
Configure the YAML: Add MCP server settings and Ollama endpoints. My go-to models here are Mistral and Gemma for their balance between speed and accuracy.
Launch Ollama: Serve it on port 11434 with a chosen model. I recommend starting with Qwen2.5 to test the waters.
Test the Agent: Query IP addresses via the LibreChat UI. If it returns your actual IPv6, you’ve hit the jackpot.

Installation Features

Key Features of Installation: Seamless Integration, Precision Perfected

Streamlined MCP Configuration: Define server timeouts (like the 60s default) and model mappings without YAML syntax headaches.
Tool Autoloading: Adding IP lookup tools via the UI instead of manual coding—this alone saves 30 minutes of my time.
Ollama’s Lightweight Magic: Run quantized models (those q4_K_M suffixes) without melting your laptop’s fans.
Environment Flexibility: The host.docker.internal switch makes this setup work in containers too—handy for my Docker-obsessed coworkers.

Use Cases of Installation: Seamless Integration, Precision Perfected

This setup shines in scenarios where you need:

A chatbot that fetches real-time network metadata (like debugging internal systems)
Lightweight LLM inference without GPU clusters (perfect for Raspberry Pi projects)
A playground to test Ollama’s model lineup before production
End-to-end demos showing how chatbots interface with backend services

Installation FAQ

FAQ from Installation: Seamless Integration, Precision Perfected

Why use SSE instead of WebSocket?: SSE is easier to configure behind corporate proxies—trust me, I’ve cried over WebSockets in firewalled networks.
Can I add more tools later?: 100% yes! The tool registry is designed for expansion. I once added a weather API tool in 5 minutes using the same method.
Ollama model list isn’t showing up…: Check the name field in your YAML starts with ‘ollama’ (case-insensitive). A lowercase typo here once cost me an hour.
Is port 3080 customizable?: Modify the PORT env variable in .env. I use 3005 to avoid collisions with my Next.js projects.
Help! My IP tools return localhost addresses: Ensure your backend server has proper network permissions. On Macs, check System Settings > Privacy > Accessibility.

Content

Installation

cd IpServer && npm install && npm run build && npm run start
install a local mongodb server and serve it on mongodb://127.0.0.1:27017
cd LibreChat && git clone [email protected]:danny-avila/LibreChat.git && mv .env.example .env && npm install && npm run frontend && npm run backend
add following configuration to your librechat.yaml file:

mcpServers:
  ipServer:
    # type: sse # type can optionally be omitted
    url: http://localhost:3000/sse
    timeout: 60000 # 1 minute timeout for this server, this is the default timeout for MCP servers.

endpoints:
  custom:
    - name: "Ollama"
      apiKey: "ollama"
      # use 'host.docker.internal' instead of localhost if running LibreChat in a docker container
      baseURL: "http://localhost:11434/v1/chat/completions"
      models:
        default:
          [
            "qwen2.5:3b-instruct-q4_K_M",
            "mistral:7b-instruct-q4_K_M",
            "gemma:7b-instruct-q4_K_M",
          ]
        # fetching list of models is supported but the `name` field must start
        # with `ollama` (case-insensitive), as it does in this example.
        fetch: true
      titleConvo: true
      titleModel: "current_model"
      summarize: false
      summaryModel: "current_model"
      forcePrompt: false
      modelDisplayLabel: "Ollama"

download and run ollama, download a model from https://ollama.ai/models/ and serve ollama on http://localhost:11434/

Usage

Visit http://localhost:3080/ to see the LibreChat UI.
Create a new agent with the name "Ollama" and select the ollama as the model provider and select a model
Click on the Add Tools button below and add the get-external-ip, get-local-ip-v6, get-external-ip-v6, get-local-ip tools
Ask agent what's my local ip address? / what's my external ip address? / what's my external ipv6 address? / what's my internal ipv6 address?
Agent should invoke your tools and return the results.