Integration

Scrapeless integration

Scrapeless is a web scraping platform. Run its ready-made scrapers (Google Search, Images, Scholar, Flights, Shopping, Amazon, Shopee, TikTok and Brazilian tax registry lookups) by actor name, fetch any page through the Web Unlocker (anti-bot bypass, optional JavaScript rendering), scrape one page or a batch of pages to markdown, HTML, links or screenshots, crawl a website, manage Agent Browser profiles, extensions and real-time signals of running sessions, and read the account balance. Opening a browser session (a CDP WebSocket), its live-view URL, and the 1Password and team-credential stores are left out. Authentication is an API key from the Scrapeless dashboard sent in the x-api-token header.

Connect Scrapeless How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Scrapeless.Built from the 32 Scrapeless tools below, on the connection you add once.

What you can do with Scrapeless

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.

Profile, 5 operations

create_profileCreate profilePOSTCreates a browser profile, which keeps cookies, storage, cache and login state across Agent Browser sessions, and returns its profileId.
delete_profileDelete profileDELETEDeletes a browser profile and its stored browser data.
get_profileGet profileGETReturns one browser profile: name, id, count and size.
list_profilesList profilesGETLists browser profiles, optionally filtered by name or id, one page at a time (page starts at 1).
update_profileUpdate profilePUTRenames a browser profile.

Batch, 3 operations

cancel_batch_scrapeCancel batch scrapeDELETECancels a running batch scrape by id.
get_batch_scrapeGet batch scrapeGETReturns a batch scrape by id: status (scraping, completed or failed), total and completed page counts, and data, one entry per page scraped so far.
start_batch_scrapeStart batch scrapePOSTStarts scraping several URLs and returns its id at once. Read get_batch_scrape until status is completed or failed; get_batch_scrape_errors lists the failed URLs.

Crawl, 3 operations

cancel_crawlCancel crawlDELETECancels a running crawl by id.
get_crawlGet crawlGETReturns a crawl by id: status (scraping, completed or failed), total pages attempted, completed pages and data, one entry per page (markdown, html, links, screenshot, metadata).
start_crawlStart crawlPOSTStarts crawling a website from a base URL and returns its id at once. Set limit, the maximum number of pages. Read get_crawl until status is completed or failed.

Extension, 3 operations

delete_extensionDelete extensionDELETEDeletes an uploaded browser extension.
get_extensionGet extensionGETReturns one uploaded browser extension: id, team, manifest name, name and version.
update_extensionUpdate extensionPUTReplaces an uploaded browser extension with a new ZIP file and name.

Error, 2 operations

get_batch_scrape_errorsGet batch scrape errorsGETReturns the errors of a batch scrape: errors (per URL) and robotsBlocked (URLs refused by robots.txt).
get_crawl_errorsGet crawl errorsGETReturns the errors of a crawl: errors (per URL) and robotsBlocked (URLs refused by robots.txt).

List, 2 operations

list_extensionsList extensionsGETLists the browser extensions uploaded to the account with their id, name and version.
list_signalsList signalsGETLists the names of the pending signal events of a running Agent Browser session.

Request, 2 operations

run_scraperRun scraperPOSTRuns a Scrapeless scraper chosen by actor (e.g. scraper.google.search) with its input. A quick task answers with the data; a longer one returns taskId: read get_scraper_result until it returns the data.
unlock_web_pageUnlock web pagePOSTFetches a URL through the Web Unlocker (proxies, CAPTCHA and anti-bot handling) and returns the page body as text in data. Add input.jsRender to render JavaScript first.

Scrape, 2 operations

get_scrapeGet scrapeGETReturns a single-page scrape by id: status (scraping, completed or failed), data (markdown, html, rawHtml, links, screenshot, metadata) and error.
scrape_urlScrape urlPOSTScrapes one URL with a cloud browser. Returns status (completed or failed) and data: markdown by default or the formats asked for, plus page metadata. Waits for the job and returns the finished result; gives up after 5 minutes.

Status, 2 operations

get_actors_statusGet actors statusPOSTReturns the recent success rate of several scraper actors at once (data[].actor, data[].rate between 0 and 1). The body is a list of actor names.
get_actor_statusGet actor statusGETReturns the recent success rate of one scraper actor (e.g. scraper.amazon) as data[].rate between 0 and 1. data is null for an actor the service does not report.

Clear, 1 operation

clear_signalsClear signalsDELETEClears pending signal events of a running Agent Browser session: one event channel when event is given, else all of them.

Me, 1 operation

get_accountGet accountGETReturns the account balance (credits, excessCredits), the subscription plan (remaining credits, end date, price, status, usage), the account status and the user id.

Result, 1 operation

get_scraper_resultGet scraper resultGETReturns the result of a run_scraper task by taskId. While the task is still running the vendor answers HTTP 201 without data; call again after a few seconds (the vendor recommends 1 to 5).

Running, 1 operation

list_running_sessionsList running sessionsGETLists the Agent Browser sessions running now: taskId, state, creation and expiry times and session name.

Send, 1 operation

send_signalSend signalPOSTSends a data payload to an event channel of a running Agent Browser session, for example an MFA code the browser script is waiting for.

Stats, 1 operation

get_signal_statsGet signal statsGETReturns the signal queue statistics of a running Agent Browser session: number of pending events and of waiters.

Upload, 1 operation

upload_extensionUpload extensionPOSTUploads a browser extension as a ZIP file and returns its extensionId, which a browser session can load.

Wait, 1 operation

wait_for_signalWait for signalGETWaits for data on an event channel of a running Agent Browser session and returns it, or times out (timeout in milliseconds, vendor default 60000).

Use Scrapeless from Claude Code, Cursor or Codex

Connect Scrapeless in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Scrapeless 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 Scrapeless

Create your workspace
Sign up free. Nothing to install.
Connect Scrapeless once
Add your Scrapeless 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.