Linkup is a search engine that allows you to search the web for relevant results.
Linkup is a search engine that allows you to search the web for relevant results. On Nagent, Linkup is exposed as a fully-configurable ai web scraping integration that any agent can call — 4 actions, and API key authentication. No code is required to wire Linkup into your workflow — connect it once via the External Integrations panel and reuse it across every agent you build.
Agent builders use Linkup 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 Linkup 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 Linkup, with input parameters and output schema. Drop these into any step of an agent built in Helix.
LINKUP_CREATE_RESPONSEProxy endpoint for OpenAI-compatible response generation. Used when the OpenAI client's base URL is set to Linkup. Supports 'linkup-standard' for faster results and 'linkup-deep' for more comprehensive results.
Input parameters
Optional custom text format configuration.
The natural language question for which you want to retrieve context. Must be a plain string, not an object or array.
The model used to generate the response. 'linkup-standard' returns results faster; 'linkup-deep' takes longer but yields more comprehensive results.
Optional instructions to guide the response generation. Similar to a system message.
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
LINKUP_FETCH_WEBPAGEFetch and retrieve a markdown representation of a webpage from a given URL. Supports optional JavaScript rendering for single-page applications, raw HTML extraction, and image extraction from the webpage content. Use this when you need to extract clean, structured content from web pages.
Input parameters
The URL of the webpage to fetch
Whether to render JavaScript on the webpage before fetching content. Set to true for single-page applications or dynamic content
Whether to extract images from the webpage and include them in the response
Whether to include the raw HTML of the webpage in the response
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
LINKUP_GET_CREDITS_BALANCETool to retrieve the current credits balance for your Linkup account. Returns the number of credits remaining that can be used for search and fetch operations.
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
LINKUP_SEARCHSearch the web and retrieve insights using Linkup's API. This action provides three output modes: natural language answers with sources (sourcedAnswer), raw search context (searchResults), or custom structured JSON (structured). Supports filtering by date range and domains, with optional image results. Standard depth uses 1 credit, deep search uses 10 credits. Only indexes publicly available web content; private repositories and internal endpoints return no results.
Input parameters
Level of search depth. 'standard' is faster and uses 1 credit, 'deep' is more comprehensive and uses 10 credits
The natural language question for which you want to retrieve context
Filter results up to this date in ISO 8601 format (YYYY-MM-DD)
Filter results from this date onwards in ISO 8601 format (YYYY-MM-DD)
Maximum number of results to return
Type of output: 'sourcedAnswer' provides a natural language answer with citations, 'searchResults' returns raw search context, 'structured' returns custom JSON format Response fields: `sourcedAnswer` returns `answer` (str) and `sources` (list); `searchResults` returns `results` array with `name`, `url`, `content` per item; `structured` returns schema-defined JSON.
Whether to include image results in the response
Exclude these domains from search results
Only search within these domains (up to 100 domains)
Adds sources to structured responses. Only applicable when output_type is 'structured'
Embeds citations directly within the answer text. Only applicable when output_type is 'sourcedAnswer'
JSON schema defining the custom response format. Required when output_type is 'structured'
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 47 agents privately built on Nagent that already use Linkup.
Build on Nagent
Connect Linkup 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 Linkup, and click "Connect Now." You'll authenticate with an API key — Nagent handles credential storage and refresh automatically. Once connected, Linkup is available to any agent in your workspace.
No. Nagent provides no-code integration for every tool. Once Linkup is connected, you configure its 4 actions directly in the agent builder UI — no API calls, no boilerplate, no schema management.
Helix — Nagent's agentic agent builder — lets you drop Linkup 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 Linkup event fires, the agent kicks off automatically.
Every Linkup 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 Linkup ships with 4 pre-built ai web scraping actions, you can layer custom logic around them inside Helix — pre/post-processing steps, conditional branches, retries, or stitching Linkup together with other connected tools. For deeper customization, talk to our team about Nagent's Agentic AI Lab — forward-deployed engineers who build Linkup-based workflows tailored to your business.