Integration

PeekShot integration

PeekShot captures website screenshots. Capture any web page URL (viewport or full page, device emulation, retina, custom CSS or JavaScript, ad, cookie-banner and popup blocking, one element by selector, proxy or saved cookie session) or render raw HTML to an image, then read back the image URL, list past screenshots and list projects. Each capture spends PeekShot credits (one per full-page capture; API access is on the Advance and Premium plans). Authentication is a PeekShot API key sent in the x-api-key header.

Connect PeekShot How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in PeekShot.Built from the 5 PeekShot tools below, on the connection you add once.

What you can do with PeekShot

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.

Screenshot, 3 operations

capture_screenshotCapture screenshotPOSTCaptures a screenshot of a web page URL and returns the finished record: screenshotUrl (the image), status COMPLETE. Spends PeekShot credits. Waits for the job and returns the finished result; gives up after 5 minutes.
get_screenshotGet screenshotGETReads one screenshot request by id: status PENDING, COMPLETE or FAILED, screenshotUrl once COMPLETE, the recorded capture options, size, credits used and dates.
list_screenshotsList screenshotsGETLists the account's screenshots, a page at a time (page, limit), optionally filtered by projectId, captured url or status (PENDING, COMPLETE, FAILED): each with its id, status, screenshotUrl and options.

Html screenshot, 1 operation

capture_html_screenshotCapture html screenshotPOSTRenders raw HTML into a screenshot image and returns the finished record: screenshotUrl (the image), status COMPLETE. Spends PeekShot credits. Waits for the job and returns the finished result; gives up after 5 minutes.

Project, 1 operation

list_projectsList projectsGETLists the account's screenshot projects, a page at a time (page, limit, optional name filter): id (the project_id of capture_screenshot), name, dates and the creating user's name and email.

Use PeekShot from Claude Code, Cursor or Codex

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

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