Search & Research

Serper

Search the web, news and images through Serper.dev for research and enrichment.

Explore 4 capabilities ↓

What you can build

Research a topic and synthesize an answer with sources
Monitor news and results for a keyword on a schedule
Scrape pages to enrich a lead or competitor profile
Find images and source links for content workflows

Access and credentials

Read-only web search and page scraping via the Serper.dev API key. No write or destructive actions.

This plugin uses an API token. Store credentials in OrgSDK and select them for the project that needs access.

Example action

Research a topic with source links

Use this call in a saved OrgSDK action after enabling the plugin and connecting a credential.

return await serper.search({
  "q": "local-first business automation",
  "gl": "au",
  "num": 5
});

Use with OrgSDK

OrgSDK gives external AI clients persistent projects and controlled execution. Plugins add optional tools to those projects. Each run uses pinned plugin versions, and project configuration determines which credentials they can use.

Set up OrgSDK locally ↗

The plugin’s toolkit

Capabilities

4 functions from this published version. Read calls retrieve or process information; write actions can change data in the connected service.

Find a function

4 of 4 functions

`serper.search`

Read call

Search Google via Serper.dev. Returns organic results, knowledge graph, answer box, people-also-ask, and related searches.

Parameters and return value

Parameter	Type	Details
`q`	`string`	The search query.
`gl`Optional	`string`	Country code for results (e.g. "us", "au", "uk"). Default: "us".
`hl`Optional	`string`	Language code (e.g. "en", "es").
`page`Optional	`number`	Result page number (1-based). Default: 1.
`num`Optional	`number`	Number of results per page. Default: 10.
`timeRange`Optional	`TimeRange`	Time range filter. One of: "past_hour", "past_24h", "past_week", "past_month", "past_year".
`location`Optional	`string`	Location string (e.g. "Austin,Texas,United States").
`device`Optional	`"desktop" \| "mobile"`	Device type for results. Default: desktop.
`autocorrect`Optional	`boolean`	Whether to apply autocorrect. Default: true.

Returns Promise<SearchResult>

`serper.newsSearch`

Read call

Search Google News via Serper.dev. Returns news articles matching the query.

Parameters and return value

Parameter	Type	Details
`q`	`string`	The search query.
`gl`Optional	`string`	Country code for results (e.g. "us", "au", "uk"). Default: "us".
`hl`Optional	`string`	Language code (e.g. "en", "es").
`page`Optional	`number`	Result page number (1-based). Default: 1.
`num`Optional	`number`	Number of results per page. Default: 10.
`location`Optional	`string`	Location string (e.g. "Austin,Texas,United States").
`device`Optional	`"desktop" \| "mobile"`	Device type for results. Default: desktop.
`autocorrect`Optional	`boolean`	Whether to apply autocorrect. Default: true.

Returns Promise<SearchResult>

`serper.imageSearch`

Read call

Search Google Images via Serper.dev. Returns image results with thumbnails and source links.

Parameters and return value

Parameter	Type	Details
`q`	`string`	The search query.
`gl`Optional	`string`	Country code for results (e.g. "us", "au", "uk"). Default: "us".
`hl`Optional	`string`	Language code (e.g. "en", "es").
`page`Optional	`number`	Result page number (1-based). Default: 1.
`num`Optional	`number`	Number of results per page. Default: 10.
`timeRange`Optional	`TimeRange`	Time range filter. One of: "past_hour", "past_24h", "past_week", "past_month", "past_year".
`location`Optional	`string`	Location string (e.g. "Austin,Texas,United States").
`device`Optional	`"desktop" \| "mobile"`	Device type for results. Default: desktop.
`autocorrect`Optional	`boolean`	Whether to apply autocorrect. Default: true.

Returns Promise<{ query: string; images: ImageResult[] }>

`serper.scrapeUrl`

Read call

Scrape the full text content and metadata of a web page via the Serper.dev scrape endpoint (scrape.serper.dev). Returns the page's visible text plus Open Graph / Twitter / title / description metadata.

Parameters and return value

Parameter	Type	Details
`url`	`string`	The fully-qualified URL of the page to scrape.

Returns Promise<ScrapeResult>