Integration

Browshot integration

Browshot takes screenshots of live web pages in real browsers (desktop and mobile, many screen sizes and countries). Request a screenshot, follow its status, download it as a PNG or JPEG thumbnail (cropped or resized), host it on S3 or Browshot, share it publicly or delete its data, crawl a whole domain, follow dashboard batches, and list instances, browsers and your account balance. The listing and multi-URL routes (their answers embed the API key in every screenshot URL), the rendered-HTML download and batch file upload are not exposed. Authentication is the API key from the Browshot dashboard, sent as the key query parameter; free accounts get 100 screenshots a month on free instances.

Connect Browshot How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Browshot.Built from the 14 Browshot tools below, on the connection you add once.

What you can do with Browshot

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.

Info, 5 operations

get_accountGet accountGETReturns your Browshot account: credit balance, free screenshots left this month, whether private instances and Browshot hosting are enabled, and with details 2 your private instances and custom browsers.
get_batchGet batchGETReturns the progress of a batch of screenshots started from the Browshot dashboard: status, URL count, processed and failed counts, and when finished the links to download the ZIP archive.
get_browserGet browserGETReturns one browser: its name, user agent string and identifiers, JavaScript support and whether it is mobile.
get_instanceGet instanceGETReturns one instance: its browser, screen size, country, current load, whether it is active and its cost per screenshot.
get_screenshotGet screenshotGETReturns the status and details of a screenshot: in_queue, processing, finished or error, plus page information (final URL, HTTP code, content type, timings, page assets) depending on details.

Crawl, 2 operations

create_crawlCreate crawlGETCrawls a domain from a start URL and screenshots every page found, up to max pages; returns the crawl id and status. Each screenshot costs an extra credit (details 3 is used to capture links). Check progress with get_crawl.
get_crawlGet crawlGETReturns the progress of a crawl started with create_crawl or the dashboard: status, page counts, and the screenshots taken so far with their ids.

List, 2 operations

list_browsersList browsersGETLists the predefined browsers (user agents) instances can use, keyed by browser id, each with its name, user agent string, JavaScript support and whether it is mobile.
list_instancesList instancesGETLists the instances you can take screenshots with (browser, screen size, country, load and cost per screenshot), grouped as free, shared (need a positive balance) and private.

Create, 1 operation

create_screenshotCreate screenshotGETRequests a screenshot of a web page and returns at once with its id and status (finished when served from cache). Call get_screenshot until status is finished or error, then get_screenshot_thumbnail for the image.

Delete, 1 operation

delete_screenshot_dataDelete screenshot dataGETDeletes stored data of a screenshot to remove confidential information: its image files (the default), the URL requested, its metadata (times, POST data, cookie, referrer), or all of them.

Host, 1 operation

host_screenshotHost screenshotGETHosts a finished screenshot or a thumbnail of it on your S3 bucket or on Browshot and returns its URL. Without width, height or scale the original screenshot is hosted. S3 hosting needs Browshot's upload access to the bucket.

Screenshot, 1 operation

get_screenshot_thumbnailGet screenshot thumbnailGETDownloads a finished screenshot as an image file (PNG by default, or JPEG), optionally cropped (left, right, top, bottom), then resized by width, height, scale or zoom.

Share, 1 operation

share_screenshotShare screenshotGETMakes a finished screenshot public on a Browshot sharing page, with an optional note, and returns the page URL.

Use Browshot from Claude Code, Cursor or Codex

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

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