The Linkup connector lets your AI agent act in each user's Linkup account. Each user connects their own Linkup access token once, and Scalekit sends it with every call, so your agent never handles credentials. It comes with 11 tools.
- Tools
- 11
- What they doRead · write · destructive
- 9 · 2 · 09 read2 write0 destructive
- Users sign in with
- Access token
Setup
Install the SDK
Terminal window npm install @scalekit-sdk/node dotenvTerminal window pip install scalekit-sdk-python python-dotenvSet your credentials
Add your Scalekit credentials to your
.envfile. Find values in app.scalekit.com > Developers > API Credentials..env SCALEKIT_ENVIRONMENT_URL=<your-environment-url>SCALEKIT_CLIENT_ID=<your-client-id>SCALEKIT_CLIENT_SECRET=<your-client-secret>Create the Linkup connection
In AgentKit > Connections, create a Linkup connection. The name you give it is the
connection_nameyour code passes. See Configure connections.Authorize a user and make your first call
quickstart.mts import { ScalekitClient } from '@scalekit-sdk/node'import 'dotenv/config'import { createInterface } from 'node:readline/promises'const scalekit = new ScalekitClient(process.env.SCALEKIT_ENVIRONMENT_URL,process.env.SCALEKIT_CLIENT_ID,process.env.SCALEKIT_CLIENT_SECRET,)const actions = scalekit.actionsconst connector = 'linkup'const identifier = 'user_123'// Generate an authorization link for the userconst { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })console.log('Authorize Linkup:', link)const rl = createInterface({ input: process.stdin, output: process.stdout })await rl.question('Press Enter after authorizing...')rl.close()// Make your first callconst result = await actions.executeTool({connector,identifier,toolName: 'linkup_credits_balance_get',toolInput: {},})console.log(result)Terminal window npx tsx quickstart.mtsquickstart.py import osfrom scalekit import ScalekitClientfrom dotenv import load_dotenvload_dotenv()scalekit_client = ScalekitClient(env_url=os.getenv("SCALEKIT_ENVIRONMENT_URL"),client_id=os.getenv("SCALEKIT_CLIENT_ID"),client_secret=os.getenv("SCALEKIT_CLIENT_SECRET"),)actions = scalekit_client.actionsconnection_name = "linkup"identifier = "user_123"# Generate an authorization link for the userlink_response = actions.get_authorization_link(connection_name=connection_name,identifier=identifier,)print("Authorize Linkup:", link_response.link)input("Press Enter after authorizing...")# Make your first callresult = actions.execute_tool(tool_input={},tool_name="linkup_credits_balance_get",connection_name=connection_name,identifier=identifier,)print(result)Terminal window python quickstart.pyEach user opens the link once and enters their Linkup credentials there. See Authorize a user for the full flow and statuses.
Tools
Pass the exact name toexecute_toollinkup_credits_balance_getGet the remaining credit balance of your Linkup account.Read-onlyGet Credits Balance
Get the remaining credit balance of your Linkup account. Returns the balance. Use this before large batches or deep searches to check you have credits.
Inputs
This tool takes no inputs.
linkup_page_fetchFetch one public web page or PDF by URL and return its content as clean markdown, optionally with typed JSON extracted by a schema.Read-onlyFetch Web Page
Fetch one public web page or PDF by URL and return its content as clean markdown, optionally with typed JSON extracted by a schema. Returns markdown, and when requested raw content, images or the structured object. Use this when you already know the URL. Use linkup_search to find pages first.
Inputs
urlstringrequired- Full URL of the public page or PDF to fetch. Example: https://www.linkup.so/blog.
extract_imagesboolean- Also return the images found on the page. Linkup defaults to false. Example: false.
include_raw_contentboolean- Also return the raw page content and its content type. Linkup defaults to false. Example: false.
instructionsstring- Instructions that guide the structured extraction. Requires schema. Example: Extract the article title and publication date.
modestring- Fetch strategy. pro has much higher success on hard-to-retrieve pages and costs more. Linkup defaults to standard. Example: standard.one of
standardpro render_jsboolean- Render the page's JavaScript before extracting. Slower; use for single-page apps. Linkup defaults to false. Example: false.
schemastring- JSON Schema, as a string, of type object describing structured data to extract from the page. Fields with no grounded value are left out. Example: {"type":"object","properties":{"title":{"type":"string"}}}
linkup_research_getGet one research task by id, with its status and, once completed, its answer or structured output and sources.Read-onlyGet Research Task
Get one research task by id, with its status and, once completed, its answer or structured output and sources. Returns the task id, status (pending, processing, completed or failed) and output. Use this to poll a task started by linkup_research_create. Use linkup_research_list to find task ids.
Inputs
idstringrequired- Research task id returned by linkup_research_create or linkup_research_list. Example: 6f1c2a9e-3b4d-4e5f-8a7b-1c2d3e4f5a6b.
linkup_research_listList the research tasks created by your Linkup organization, with pagination.Read-onlyList Research Tasks
List the research tasks created by your Linkup organization, with pagination. Returns tasks with their id, status and timestamps. Use this to find a research task id. Use linkup_research_get for one task's output.
Inputs
pageinteger- Page number, starting at 1. Linkup defaults to 1. Example: 1.
page_sizeinteger- Results per page, 1 to 100. Linkup defaults to 10. Example: 20.
sort_bystring- Field to sort by. Example: createdAt.one of
createdAtupdatedAt sort_directionstring- Sort direction. Linkup defaults to asc. Example: desc.one of
ascdesc
linkup_rewind_fetchReturn a web page as it was at the end of a given UTC day (beta).Read-onlyFetch Past Page (Rewind)
Return a web page as it was at the end of a given UTC day (beta). Returns the stored page content for that day. Use this to see a page's past version. The URL must match the stored URL exactly. Use linkup_page_fetch for the live page.
Inputs
as_ofstringrequired- UTC day to fetch the page as of, YYYY-MM-DD. Example: 2025-09-17.
urlstringrequired- Exact URL of the page. No normalization is applied, so it must match the stored URL. Example: https://www.federalreserve.gov/newsevents/pressreleases.htm.
linkup_rewind_searchSearch the web as it was at the end of a given UTC day (beta).Read-onlySearch Past Web (Rewind)
Search the web as it was at the end of a given UTC day (beta). Returns ranked results from Linkup's stored snapshot for that day. Use this for point-in-time research or backtesting. Use linkup_search for the live web.
Inputs
as_ofstringrequired- UTC day to search as of, YYYY-MM-DD. Example: 2025-09-17.
qstringrequired- The search query. Example: Federal Reserve interest rate decision.
linkup_searchSearch the live web with Linkup and get ranked sources, a sourced answer, or JSON shaped by your schema.Read-onlySearch the Web
Search the live web with Linkup and get ranked sources, a sourced answer, or JSON shaped by your schema. Returns results (name, url, content snippets) for searchResults, an answer with sources for sourcedAnswer, or an object matching structured_output_schema. Use this for current facts and source discovery. Use linkup_page_fetch to read one known URL in full, and linkup_research_create for multi-step research that takes minutes.
Inputs
depthstringrequired- Search depth. flash is lowest latency (sources and snippets in a few hundred ms), fast is quick single-pass, standard is the default balance, deep iterates with more sources and costs more credits. Example: standard.one of
flashfaststandarddeep output_typestringrequired- Response shape: searchResults (ranked sources with snippets), sourcedAnswer (natural-language answer with sources) or structured (JSON matching structured_output_schema). Example: sourcedAnswer.one of
searchResultssourcedAnswerstructured qstringrequired- Natural-language question or query to search for. Be specific about entities, dates and the facts wanted. Example: What was Nvidia's revenue in Q2 fiscal 2026?.
exclude_domainsarray- Never return results from these domains. Example: ["wikipedia.org"]
from_datestring- Only consider results published on or after this date (YYYY-MM-DD). Must be before to_date. Example: 2026-01-01.
include_domainsarray- Only search these domains (up to 100). Omit to search the whole web. Example: ["sec.gov", "reuters.com"]
include_imagesboolean- Include image results. Linkup defaults to false. Example: false.
include_inline_citationsboolean- For sourcedAnswer only: add inline citations to the answer text. Linkup defaults to false. Example: true.
include_sourcesboolean- For structured output only: also return the sources used. This changes the response shape. Linkup defaults to false. Example: true.
max_resultsinteger- Maximum number of results to return. Example: 10.
structured_output_schemastring- JSON Schema, as a string, for the response when output_type is structured. Required only for structured output; the root must be of type object. Example: {"type":"object","properties":{"revenue":{"type":"string"}}}
to_datestring- Only consider results published on or before this date (YYYY-MM-DD). Must be after from_date. Example: 2026-06-30.
linkup_task_getGet one batch task by id, with its type, status and, once completed, its output.Read-onlyGet Batch Task
Get one batch task by id, with its type, status and, once completed, its output. Returns the task id, type, status and output. Use this to poll a task created by linkup_tasks_create. Use linkup_tasks_list to find ids.
Inputs
idstringrequired- Task id returned by linkup_tasks_create or linkup_tasks_list. Example: 6f1c2a9e-3b4d-4e5f-8a7b-1c2d3e4f5a6b.
linkup_tasks_listList batch tasks for your Linkup organization, optionally filtered by type and status, with pagination.Read-onlyList Batch Tasks
List batch tasks for your Linkup organization, optionally filtered by type and status, with pagination. Returns tasks with id, type, status and timestamps. Use this to check progress across a batch. Use linkup_task_get for one task's output.
Inputs
pageinteger- Page number, starting at 1. Linkup defaults to 1. Example: 1.
page_sizeinteger- Results per page, 1 to 100. Linkup defaults to 10. Example: 20.
sort_bystring- Field to sort by. Example: createdAt.one of
createdAtupdatedAt sort_directionstring- Sort direction. Linkup defaults to asc. Example: desc.one of
ascdesc statusarray- Only tasks with these statuses: pending, processing, completed or failed. Example: ["completed"]
typearray- Only tasks of these types: search, fetch, research or extract. Example: ["search"]
linkup_research_createStart an asynchronous Linkup research task: an agent browses the web over several steps and writes a sourced answer or structured result.WriteCreate Research Task
Start an asynchronous Linkup research task: an agent browses the web over several steps and writes a sourced answer or structured result. Returns the research task id and status; the result is not in this response. Use this for questions that need many sources or a report. Poll linkup_research_get with the id until status is completed. Use linkup_search for quick lookups.
Inputs
output_typestringrequired- sourcedAnswer for a written answer with sources, or structured for JSON matching structured_output_schema. Example: sourcedAnswer.one of
sourcedAnswerstructured qstringrequired- The research question, stated fully with the scope and the output you want. Example: Compare the pricing and API limits of the top five web search APIs for AI agents in 2026.
exclude_domainsarray- Never return results from these domains. Example: ["wikipedia.org"]
from_datestring- Only consider results published on or after this date (YYYY-MM-DD). Must be before to_date. Example: 2026-01-01.
include_domainsarray- Only search these domains (up to 100). Omit to search the whole web. Example: ["sec.gov", "reuters.com"]
modestring- Pin the research agent mode: answer, investigate or research. Omit (auto) to let the agent pick from the question. Example: research.one of
autoanswerinvestigateresearch reasoning_depthstring- Reasoning depth, S < M < L < XL. Higher depths are slower and more thorough. Linkup defaults to L. Example: M.one of
SMLXL structured_output_schemastring- JSON Schema, as a string, for the response when output_type is structured. Required only for structured output; the root must be of type object. Example: {"type":"object","properties":{"revenue":{"type":"string"}}}
to_datestring- Only consider results published on or before this date (YYYY-MM-DD). Must be after from_date. Example: 2026-06-30.
linkup_tasks_createQueue up to 100 search, fetch or research calls to run asynchronously in one batch.WriteCreate Batch Tasks
Queue up to 100 search, fetch or research calls to run asynchronously in one batch. Returns the created task ids; results are not in this response. Use this for bulk work. Poll linkup_task_get per id or linkup_tasks_list. Use linkup_search or linkup_page_fetch for a single synchronous call.
Inputs
tasksarrayrequired- Array of 1 to 100 task objects. Each has a type (search, fetch or research) and an input object that takes the same fields as that endpoint's body, for example q, depth and outputType for search, or url for fetch. Example: [{"type":"search","input":{"q":"Linkup API pricing","depth":"standard","outputType":"searchResults"}}]
No tools match.