Aviz Network Copilot SDK Documentation

NCP SDK User Guide

Comprehensive Guide to Network Copilot SDK for AI Agent Development

The NCP SDK enables developers to create sophisticated AI agents and deploy them on the NCP platform. This guide covers everything from basic setup to advanced features like background agents, memory systems, and MCP integrations.

Getting Started
Prerequisites
Installation
Quick Verification
Core Concepts
Tools
Agents
Project Structure
Advanced Features
MCP Integration
Data Connectors
Dependency Management
Python Dependencies
System Dependencies
SDK Workflow
Project Initialization
Development
Validation
Packaging
Deployment

Getting Started

Prerequisites

Python Version

Python 3.8 or higher is required
Python 3.9+ recommended for better type support

Platform-Specific Setup

macOS


# Install Python via Homebrew (recommended)

brew install [email protected]

# Or use pyenv for version management

brew install pyenv
pyenv install 3.11.0
pyenv global 3.11.0

Linux (Ubuntu/Debian)


# Update package list

sudo apt update

# Install Python and pip

sudo apt install python3.11 python3.11-pip python3.11-venv

# Verify installation

python3.11 --version

Windows

Download Python from python.org
Run installer and check “Add Python to PATH”
Open Command Prompt or PowerShell to verify:


python --version
pip --version

Virtual Environment


# Already included with Python 3.3+
python -m venv --help

Installation

Step 1: Create Virtual Environment

Using venv:


# Create virtual environment
python -m venv .venv
# Activate virtual environment
# On macOS/Linux:
source .venv/bin/activate
# On Windows:
.venv\Scripts\activate
# Verify activation (should show .venv in prompt)
which python

Step 2: Install NCP SDK


# Install from PyPI

pip install ncp-sdk

Step 3: Verify Installation


# Check if NCP CLI is available

ncp --help

# Check Python import

python -c "from ncp import Agent, tool; print('NCP SDK installed successfully!')"

Quick Verification

Create a simple test to ensure everything works:


# test_ncp.py
from ncp import Agent, tool

@tool
def hello_world(name: str = "World") -> str:
    """Say hello to someone."""
    return f"Hello, {name}!"

# This should work without errors

agent = Agent(
    name="TestAgent",
    description="A simple test agent",
    instructions="You are a test agent. Be helpful.",
    tools=[hello_world]
    )

print("✅ NCP SDK is working correctly!")

Run the test:


python test_ncp.py

Core Concepts

Tools

Tools are the building blocks that give your agents capabilities. They’re Python functions decorated with @tool that agents can call to perform actions.

Basic Tool Creation


from ncp import tool
@tool
def ping_device(ip_address: str, timeout: int = 5) -> dict:
    [...]

Async Tools


import asyncio
import aiohttp

@tool
async def backup_device_config(device_ip: str, backup_type: str = "running") -> dict:
    [...]

Tool Documentation Best Practices


@tool
def search_documents(
    query: str,
    max_results: int = 10,
    include_metadata: bool = True
) -> List[dict]:
    [...]

Agents

Agents are AI entities that use tools to accomplish tasks. They combine language models with your custom tools to create powerful automation.

Basic Agent Configuration


from ncp import Agent

agent = Agent(
    name="NetworkMonitorBot",
    description="AI assistant for network monitoring and diagnostics",
    instructions="""
    [...]
    """,
    tools=[ping_device, get_interface_status, backup_device_config]
)

LLMConfig Parameters


from ncp import LLMConfig

config = LLMConfig(
    model="llama-3.3-70b",
    [...],
)

Project Structure

Standard project layout:


my-agent-project/
├── ncp.toml
├── requirements.txt
├── apt-requirements.txt
├── agents/
│   └── main_agent.py
├── tools/
└── **init**.py

Advanced Features

MCP Integration

Model Context Protocol (MCP) enables agents to connect to external services and data sources.

Example MCP setup:


from ncp import Agent, MCPConfig

filesystem_server = MCPConfig(
transport_type="stdio",
command="mcp-server-filesystem /path/to/files"
)

Add multiple MCP servers:


agent = Agent(
    name="MultiServiceAgent",
    [...]
    mcp_servers=[...]
    )

Data Connectors

Data connectors allow agents to access external data sources configured in the NCP platform.


from ncp import Agent, tool

@tool
def analyze_logs(query: str) -> dict:
    [...]
    agent = Agent(
    name="LogAnalyzer",
    [...]
    connectors=["splunk-prod"]
)

Dependency Management

Python Dependencies

Example requirements.txt:


pandas>=1.5.0
numpy>=1.21.0
requests>=2.28.0

Version Pinning


requests==2.28.2
pandas==1.5.3

System Dependencies

Example apt-requirements.txt:


curl
wget
git

SDK Workflow

Project Initialization


ncp init my-agent-project
cd my-agent-project

Development Best Practices

Start Simple
Test Locally
Use Type Hints
Document Everything
Handle Errors

Packaging


ncp package .

Deployment


ncp authenticate
ncp deploy my-agent-project.ncp

#Interactive Playground mode:
ncp playground