Integration

Shotium integration

Shotium renders images in a real browser: take a PNG, JPEG or WebP screenshot of any public web page (viewport size, full-page capture, quality), or render a 1200x630 Open Graph social card from one of five built-in templates (blog, product, podcast, event, minimal). Each new render costs one credit; identical requests are served from a 24-hour cache for free, failed renders are never billed, and the rate limit is 60 requests per minute per key. A third tool checks that the stored key is valid without spending anything. Not exposed: the signed-URL form of the OG image route, which is authenticated by an HMAC signature computed per request rather than by the API key. Authentication is an API key (starting with sk_live_) created on the Shotium account page, sent as a Bearer token in the Authorization header.

Connect Shotium How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Shotium.Built from the 3 Shotium tools below, on the connection you add once.

What you can do with Shotium

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.

Each badge shows the default agent permission of an endpoint (allowed: an agent calls it without asking; ask first: you are asked before an agent calls it, when the agent or chat asks permission for sensitive actions; never: no agent may call it), which every user can change endpoint by endpoint in their credential settings.

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

Api key, 1 operation

get_api_key_infoGet api key infoGETAgents: ask firstChecks that the stored API key is valid and returns its non-secret prefix and its label. Renders nothing, costs nothing and does not touch the quota.

Og image, 1 operation

create_og_imageCreate og imagePOSTAgents: ask firstRenders a 1200x630 Open Graph (social share) image from a built-in template and returns the image file (PNG by default, or JPEG). One credit per new render; failed renders are not billed.

Screenshot, 1 operation

take_screenshotTake screenshotGETAgents: ask firstRenders a public web page in a real browser and returns the image file (PNG by default, or JPEG/WebP). One credit per new render; an identical request within 24 hours is served from cache for free. Renders time out after 30 seconds.

Use Shotium from Claude Code, Cursor or Codex

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

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