Zenserp is a real-time SERP API that extracts Google Search results in JSON format.
Zenserp is a real-time SERP API that extracts Google Search results in JSON format. On Nagent, Zenserp is exposed as a fully-configurable ai web scraping integration that any agent can call — 12 actions, and API key authentication. No code is required to wire Zenserp into your workflow — connect it once via the External Integrations panel and reuse it across every agent you build.
Agent builders use Zenserp to automate the kinds of tasks ai web scraping teams previously handled manually. Concrete examples — each one is a single agent step in Nagent — include:
Every action and trigger is paired with a structured input/output schema (visible in the sections below), so when you wire Zenserp into Helix — our agentic agent builder — the editor knows exactly what each step expects and produces. Configure once, deploy anywhere across your Nagent agents.
Every operation an agent can call against Zenserp, with input parameters and output schema. Drop these into any step of an agent built in Helix.
ZENSERP_BING_SEARCHTool to obtain Bing search results. Use when you need real-time scraping of Bing SERPs from bing.com.
Input parameters
Search query; supports Bing operators
Two-letter country code (ISO 3166), e.g. 'US'
Latitude for geolocation override, e.g. '40.7128'
Longitude for geolocation override, e.g. '-74.0060'
Market code for the request (per Bing market codes)
Number of results to return (1-50)
Zero-based offset for pagination (skip this many results)
Canonical geolocation, e.g. 'New York,New York,United States'
Must be 'bing.com' to target Bing search
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ZENSERP_GET_SHOPPING_PRODUCTTool to retrieve detailed Google Shopping product page information by product_id. Use when you need comprehensive product details including pricing, reviews, specifications, and seller information for a specific product.
Input parameters
Country code for search results (e.g., 'us', 'fr').
Web interface language code (e.g., 'en' for English, 'fr' for French).
Geolocation used in the query. Use Google's canonical names for accurate results.
The PID (product id) from Google Shopping Search. Use this to fetch detailed product page information.
URL of the search engine to query. Override the default search engine domain.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ZENSERP_GET_STATUSTool to check the remaining API requests for your API key. Use when you need to verify your Zenserp API quota.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ZENSERP_GOOGLE_REVERSE_IMAGE_SEARCHTool to perform a reverse image search on Google. Use after obtaining a public image URL to find where the image appears online.
Input parameters
Number of results to return (1-100).
Zero-based offset for pagination.
Public URL of the image to reverse search.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ZENSERP_GOOGLE_SEARCHTool to perform a standard Google search via Zenserp. Use when you need structured SERP data for a given query.
Input parameters
Search query; supports full Google search operators.
Country code for geolocation (e.g., 'us', 'fr').
Google interface language code, e.g., 'en'.
Language filter prefixed with 'lang_', e.g., 'lang_fr'.
Latitude for geolocation query.
Longitude for geolocation query.
Number of search results to return (1-100).
Type of search: 'isch' for images, 'nws' for news, 'shop' for shopping, 'lcl' for maps, 'vid' for video.
Zero-based offset for pagination (use with num for pages).
Device to emulate: 'desktop' or 'mobile'.
Raw export format: 'html' or 'csv'.
Geolocation for the query (use canonical Google names or uule tokens).
Restrict results by timeframe: e.g., 'now 1-H', 'today 12-m'.
Override search engine URL (e.g., 'google.com' for Google, 'youtube.com' for YouTube search).
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ZENSERP_GOOGLE_TRENDSTool to retrieve Google Trends data. Use when comparing keyword popularity over time.
Input parameters
Interface language code (optional), e.g., 'en'.
Category filter code (optional). Use numeric codes defined by Google Trends.
Geographic location code (optional), e.g., 'US'.
Property to compare (optional).
Keywords to compare in Google Trends. Provide as array 'keyword\[\]'.
Timeframe for trends data (optional).
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ZENSERP_LIST_BATCHESTool to list all submitted batches for your Zenserp API key. Use when you need to retrieve batch processing status or history.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ZENSERP_LIST_COUNTRIESTool to get the list of supported Google country (gl) parameters. Use when you need to know valid country codes for geolocation.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ZENSERP_LIST_LANGUAGESTool to get a list of supported Google interface language (hl) parameters. Use when you need to find valid language codes for Google search queries.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ZENSERP_LIST_LOCATIONSTool to get a list of supported geo locations for search targeting. Use when you need to know which location parameters are available for geolocation queries.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ZENSERP_LIST_SEARCH_ENGINESTool to get the list of supported search engines that can be queried via Zenserp. Use when you need to determine which search engine domains are available for searches.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ZENSERP_YANDEX_SEARCHTool to obtain Yandex search results via Zenserp API. Use when you need programmatic access to Yandex search data after constructing a query.
Input parameters
Search query string
Geographic location code (ISO 3166-1 alpha-2), e.g., 'us', 'ru'
Language code for results, e.g., 'en', 'ru'
Number of results to return (1-100)
Type of search: 'isch' for images-only search
Device type to emulate: 'desktop' or 'mobile'
Search location, e.g., 'New York, USA'
Must be 'yandex.com' to target Yandex search
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
No publicly available marketplace agent is found using this tool yet. There are 31 agents privately built on Nagent that already use Zenserp.
Build on Nagent
Connect Zenserp to any Nagent agent in minutes — no API key management, no boilerplate. Just configure and deploy.
The five questions agent builders ask before adopting a new integration.
Open the External Integrations panel inside Nagent (app.nagent.ai/externalIntegration), find Zenserp, and click "Connect Now." You'll authenticate with an API key — Nagent handles credential storage and refresh automatically. Once connected, Zenserp is available to any agent in your workspace.
No. Nagent provides no-code integration for every tool. Once Zenserp is connected, you configure its 12 actions directly in the agent builder UI — no API calls, no boilerplate, no schema management.
Helix — Nagent's agentic agent builder — lets you drop Zenserp steps into any workflow visually. Pick an action (e.g., one of those listed above), fill in the inputs (Helix knows the required vs. optional schema for each parameter), and connect it to upstream/downstream steps. Triggers run as the entry point of an agent, so when a Zenserp event fires, the agent kicks off automatically.
Every Zenserp action and trigger ships with a fully-typed schema — input parameters with name, type, required flag, and description, plus the output payload shape. The schemas are documented in the sections above. Helix uses these schemas to validate your configuration at build time and to type-check the data flowing between steps.
Yes. While Zenserp ships with 12 pre-built ai web scraping actions, you can layer custom logic around them inside Helix — pre/post-processing steps, conditional branches, retries, or stitching Zenserp together with other connected tools. For deeper customization, talk to our team about Nagent's Agentic AI Lab — forward-deployed engineers who build Zenserp-based workflows tailored to your business.