Integration

Linkup integration

Linkup is a web search API built for AI agents. Search the live web and get ranked sources, a natural-language answer with its sources, or JSON matching a schema you provide; fetch any public HTML or PDF page as clean markdown, optionally with JSON extracted from it; start long-running research tasks that produce cited answers and reports; submit batches of up to 100 search, fetch or research tasks and read their results; and check the remaining credit balance. The closed-beta Extract agent, the beta Rewind (web as of a past day) routes and the OpenAI-compatible responses proxy are not exposed. Authentication is a Linkup API key from app.linkup.so, sent as a Bearer token in the Authorization header; each search, fetch and research call is charged to the account's balance (calls that fail are not).

Connect Linkup How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Linkup.Built from the 9 Linkup tools below, on the connection you add once.

What you can do with Linkup

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Research, 3 operations

create_researchCreate researchPOSTStarts an asynchronous web research task and returns its id with status pending, not the result. Poll get_research with that id every 5 to 10 seconds until status is completed or failed: a task takes 2 to 5 minutes (depth S) up to 20 minutes (XL).
get_researchGet researchGETReturns one research task: its status (pending, processing, completed or failed), its input, and once completed its output (answer and sources, or the structured object). Poll every 5 to 10 seconds; more than once per second is rate-limited.
list_researchList researchGETLists the research tasks created by the organization, page by page, with their status, input and output.

Task, 3 operations

create_tasksCreate tasksPOSTSubmits 1 to 100 asynchronous search, fetch or research tasks in one call and returns one task per item (id, type, status pending), not results. Poll get_task or list_tasks until each status is completed or failed, at most once per second.
get_taskGet taskGETReturns one task from a batch: its type, status (pending, processing, completed or failed), the input it was submitted with, and once completed its output; on failure, error says why. Poll at most once per second.
list_tasksList tasksGETLists the batch tasks created by the organization, page by page, optionally filtered by task type and status.

Credit balance, 1 operation

get_credit_balanceGet credit balanceGETReturns the number of credits remaining in the Linkup account, from which every search, fetch and research call is paid.

Web, 1 operation

searchSearchPOSTSearches the live web for a query. outputType picks the result: searchResults (ranked sources with content), sourcedAnswer (an answer with its sources) or structured (JSON matching structuredOutputSchema). depth: flash, fast, standard or deep.

Webpage, 1 operation

fetch_webpageFetch webpagePOSTFetches one public HTML or PDF page by URL and returns it as clean markdown, optionally with its images, raw content, and JSON extracted against a schema. Reads that URL only (no link following, no login); HTML over 20 MB or PDF over 100 MB fails.

Use Linkup from Claude Code, Cursor or Codex

Connect Linkup in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Linkup operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Linkup

Create your workspace
Sign up free. Nothing to install.
Connect Linkup once
Add your Linkup connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.