🧠Advanced MCP Server Setup with
About
Advanced MCP Server Setup with uv, llama-index, ollama, and Cursor IDE
Explore
- Uses uv for fast, reproducible Python dependency management
- Integrates LlamaIndex with HuggingFace embeddings and Ollama LLMs
- Runs a local LLM backend via Ollama at localhost:11434
- Configurable MCP server inside Cursor IDE
- Environment variables stored in a .env file
- Optional ipykernel for notebook usage
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
🧠Advanced MCP Server Setup withCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
---
- [x] Python 3.10+ installed
- [x] uv (by Astral) installed globally (pip install uv)
- [x] Ollama installed and running locally
- [x] Cursor IDE installed
---
uv venv
.venv\Scripts\activate # On Windows
Create a .env file in the root of your project and add your API key:
LINKUP_API_KEY=your_api_key_here
---
Run these commands one by one inside your virtual environment:
After installation, check your uv-managed pyproject.toml for something like this:
[tool.uv.dependencies]
mcp = { extras = ["cli"] }
httpx = ""
linkup-sdk = ""
llama-index = ""
llama-index-embeddings-huggingface = ""
llama-index-llms-ollama = ""
ipykernel = ""
---
Replace the paths with your actual machine paths. You can get the full path to uv by running:
where uv # Windows
Now add this to your Cursor IDE settings:
{
"mcpServers": {
"weather": {
"command": "C:\\Users\\SIDHYA\\AppData\\Roaming\\Python\\Python311\\Scripts\\uv.exe", // Replace with your actual uv path
"args": [
"--directory",
"C:\\Users\\SIDHYA\\Development\\Ai\\mcp-server",
"run",
"server.py"
]
}
}
}
---
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"\ud83e\udde0 advanced mcp server setup with": {
"ollama-mcp-integration": {
"command": "uv",
"args": [
"init",
"mcp-server"
]
}
}
}
}McpServers
{
"ollama-mcp-integration": {
"command": "uv",
"args": [
"init",
"mcp-server"
]
}
}---
✅ Prerequisites
- [x] Python 3.10+ installed
- [x] uv (by Astral) installed globally (pip install uv)
- [x] Ollama installed and running locally
- [x] Cursor IDE installed
---
🛠Step 1: Project Setup
1.1 Create a New Project Directory
uv init mcp-server
cd mcp-server
1.2 Create and Activate Virtual Environment
```bash
uv venv
.venv\Scripts\activate # On Windows
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
