Integration

Web Scraper Cloud integration

Web Scraper Cloud (webscraper.io) runs point-and-click sitemaps in the cloud. Import, update, rename, tag and delete sitemaps, start scraping jobs on a sitemap (optionally with custom start URLs), follow their progress, stop or continue them, read their problematic URLs and data quality statistics, configure the per-sitemap scheduler, and read account usage. Downloading the scraped records (JSONL, CSV or XLSX file streams) is not exposed as a tool. Authentication is the API token from the Web Scraper Cloud API page, sent as a Bearer token.

Connect Web Scraper Cloud How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Web Scraper Cloud.Built from the 21 Web Scraper Cloud tools below, on the connection you add once.

What you can do with Web Scraper Cloud

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.

Scraping job, 6 operations

continue_scraping_jobContinue scraping jobPOSTResume a stopped scraping job from where it stopped. Every setting is optional: leave one out to keep the job's current value.
create_scraping_jobCreate scraping jobPOSTStart a scraping job on a sitemap; it runs in the background and uses one URL credit per processed page. Track it with get_scraping_job (status finished or failed).
delete_scraping_jobDelete scraping jobDELETEDelete a scraping job.
get_scraping_jobGet scraping jobGETGet one scraping job: status (started, finished, failed, stopped...), pages scheduled, executed, failed, empty and no-value, and the number of records scraped.
list_scraping_jobsList scraping jobsGETList the organization's scraping jobs, optionally filtered by sitemap, sitemap tag or status. Paginated: pass page and read last_page.
stop_scraping_jobStop scraping jobPOSTStop a running scraping job. Its parallel task is freed at once; continue_scraping_job resumes it later from where it stopped.

Sitemap, 6 operations

delete_sitemapDelete sitemapDELETEDelete a sitemap.
get_sitemapGet sitemapGETGet one sitemap: its id, name and the sitemap definition as a JSON string (start URLs and selectors).
import_sitemapImport sitemapPOSTImport a sitemap from its JSON definition (the format the Web Scraper extension exports: _id, startUrl, selectors) and return its new id.
list_sitemapsList sitemapsGETList the organization's sitemaps (id and name), optionally only those with a tag. Paginated: pass page and read last_page.
rename_sitemapRename sitemapPUTRename a sitemap; the sitemap name shown on its scraping jobs is updated too.
update_sitemapUpdate sitemapPUTReplace the JSON definition of an existing sitemap. Read it first with get_sitemap, change it, and send back the whole definition.

Sitemap scheduler, 3 operations

disable_sitemap_schedulerDisable sitemap schedulerPOSTDisable the scheduler of a sitemap: no more scraping jobs start on its schedule.
enable_sitemap_schedulerEnable sitemap schedulerPOSTEnable the scheduler of a sitemap with a cron schedule: from then on, a scraping job (billed in URL credits) starts at every scheduled time.
get_sitemap_schedulerGet sitemap schedulerGETGet the scheduler settings of a sitemap: whether it is enabled, its cron fields and time zone, and the driver, proxy, intervals and priority of scheduled jobs.

Sitemap tag, 3 operations

add_sitemap_tagAdd sitemap tagPOSTAdd a tag to a sitemap. Tags filter list_sitemaps and list_scraping_jobs.
list_sitemap_tagsList sitemap tagsGETList the tags of a sitemap.
remove_sitemap_tagRemove sitemap tagDELETERemove a tag from a sitemap.

Account, 1 operation

get_accountGet accountGETGet the account behind the API token: email, name and the URL credits left.

Scraping job data quality, 1 operation

get_scraping_job_data_qualityGet scraping job data qualityGETGet the data quality checks of a scraping job: record count, failed, empty and no-value page shares and per-column record counts, each with the measured value, the threshold and pass or fail.

Scraping job problematic url, 1 operation

list_scraping_job_problematic_urlsList scraping job problematic urlsGETList the pages of a scraping job that failed (4xx, 5xx or did not load), came back empty, or had no value, with the URL and the problem type. Paginated.

Use Web Scraper Cloud from Claude Code, Cursor or Codex

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

Create your workspace
Sign up free. Nothing to install.
Connect Web Scraper Cloud once
Add your Web Scraper Cloud 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.