Integration

RenderForm integration

RenderForm generates images, PDFs and short videos from templates designed in its editor. List and read templates with their editable properties, render an image or PDF (or an MP4/WebM video, which waits for the asynchronous render) with your data, take website screenshots, turn a web page into a PDF, browse and delete render results, create templates, update their metadata or HTML/CSS content, list fonts and read credit usage. The GET image URL (query-string) rendering, signed URLs and the deprecated v1 render and template routes are not exposed. Authentication is an API key sent in the X-API-KEY header (Account, API Keys tab); the API allows 60 requests per minute.

Connect RenderForm How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in RenderForm.Built from the 16 RenderForm tools below, on the connection you add once.

What you can do with RenderForm

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.

Template, 5 operations

create_templateCreate templatePOSTCreates a new empty template with a name, width, height and editor (html-editor, canvas-editor or canvas-html). Tags are created automatically if they do not exist.
delete_templateDelete templateDELETEPermanently deletes a template. Irreversible.
get_templateGet templateGETReturns a template with its size, output format, editor, tags, fonts and properties: each property key (componentId.property) is a data key you can set in render_image or render_video.
list_templatesList templatesGETLists your templates with name, size, output format, editor, tags and preview URL. Use the identifier as template in render_image or render_video; read editable property keys with get_template.
update_template_metadataUpdate template metadataPATCHUpdates a template's name, width, height, output format (jpeg, png, pdf) or tags. Only the fields you send change; tags replaces the full tag set.

Render result, 3 operations

delete_render_resultDelete render resultDELETEPermanently deletes a render result and its file. Irreversible.
get_render_resultGet render resultGETReturns one render result by its identifier: href, status (pending, done, failed), type, error message and, for videos, thumbnail and duration.
list_render_resultsList render resultsGETLists rendered images, PDFs, screenshots and videos, with href, status (pending, done, failed) and template. Filter by template or batch name.

Template content, 2 operations

get_template_contentGet template contentGETReturns the raw html, css and sampleData of a template. Works only for templates using the html-editor.
update_template_contentUpdate template contentPUTOverwrites the html (required), css and sampleData of an html-editor template and returns what was stored. Read get_template_content first and send back what you keep.

Font, 1 operation

list_fontsList fontsGETLists every font available to the account: Google fonts and custom fonts you uploaded (source GOOGLE or CUSTOM), with family name and variants.

Image, 1 operation

render_imageRender imagePOSTRenders an image or PDF from a template with your data and returns requestId and href (the file URL). For a video template use render_video. Consumes credits unless the render is served from cache.

Pdf, 1 operation

create_pdf_from_urlCreate pdf from urlPOSTCaptures a web page URL as a PDF (page size A5, A4, A3, LETTER or LEGAL) and returns requestId and href (the PDF URL).

Screenshot, 1 operation

take_screenshotTake screenshotPOSTTakes a screenshot of a website URL at the given width and height, saves it and returns requestId and href (the image URL).

Usage, 1 operation

get_usageGet usageGETReturns the organization's credit usage for the current billing period, upload storage used and the subscription plan.

Video, 1 operation

render_videoRender videoPOSTRenders an MP4 or WebM video from a video template (Advanced Editor) and returns the result with href. Costs 5 credits per started second, refunded if the render fails. Waits for the job and returns the finished result; gives up after 5 minutes.

Use RenderForm from Claude Code, Cursor or Codex

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

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