The problem
An agent asked to find offers needs search results for a particular product and market. A general answer from memory cannot establish which sellers appear in today’s results. A regular search-page fetch may also leave the agent with an incomplete page instead of comparable product records.
How NativePort helps
NativePort connects your agent to SerpApi’s Google Shopping search. The agent supplies the product description and receives structured offers. It can then shortlist relevant results and show the links behind its comparison.
Technical implementation
Use Python 3 with requests installed (python -m pip install requests). Set NATIVEPORT_API_KEY in your environment to your NativePort key. Run the snippets on your server, where your key stays private.
Set SHOPPING_QUERY to a specific product query, such as a model name and capacity. This example requests one results page for the US market in English using the Google Shopping engine.
import json
import os
import requests
BASE = "https://api.nativeport.ai"
HEADERS = {"Authorization": f"Bearer {os.environ['NATIVEPORT_API_KEY']}"}
response = requests.get(
BASE + "/serpapi",
headers=HEADERS,
params={"engine": "google_shopping", "q": os.environ["SHOPPING_QUERY"],
"gl": "us", "hl": "en"},
timeout=120,
)
response.raise_for_status()
result = response.json()
if result.get("error"):
raise RuntimeError(result["error"])
offers = result.get("shopping_results", [])
print(json.dumps(offers, indent=2, ensure_ascii=False))An empty list means no offers were returned in that field. The first results page is a shortlist, not a complete inventory of the market. Check the model, condition, delivery charges, and destination before comparing prices. Your agent can use the retail product guide to inspect a seller’s product page separately; that additional lookup is outside this example.
Tool costs
| Tool used in the example | Price per call |
|---|---|
| SerpApi — Google Shopping search | $0.026375 / call |
Prices in USD. Usage-based tools have no fixed per-call price. View pricing.
Let your agent build it
You don’t need to write this code yourself. Copy this page’s link and paste it into your agent. Ask it to follow the guide and implement the feature for you.
Keep exploring
Collect Amazon customer reviews
Give your agent review text and ratings from a product page to identify recurring customer feedback.
View guide
Collect public Instagram profiles and posts
Turn public Instagram pages into records your agent can compare and summarize.
View guide
Collect public TikTok video data
Retrieve public video records for an agent to organize, compare, or monitor.
View guide
Explore all use cases
Find the next tool your agent needs, from web access to voice and document processing.
All use cases