Integration

Presenton integration

Presenton Cloud turns a prompt, uploaded documents or your own slide JSON into an editable presentation exported as PPTX, PDF or PNG. Generate decks synchronously or as background tasks, draft outlines, browse Standard templates and Smart Designs, build a Smart Design from a reference PPTX, export decks, create expiring embed links, and manage uploaded images and webhook subscriptions. One generated slide uses one account credit (answers report credits_consumed). Not exposed: the guide-only route that removes every webhook subscription at once, and the self-hosted open-source v1 API (your own host, its own keys). Authentication is a Presenton Cloud API key sent as a Bearer token.

Connect Presenton How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Presenton.Built from the 24 Presenton tools below, on the connection you add once.

What you can do with Presenton

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.

Presentation, 7 operations

create_presentation_embed_linkCreate presentation embed linkPOSTCreates an expiring frontend_url (with a scoped token) that opens one presentation in an iframe; anyone holding the URL gets the granted scopes (read, edit, export) until expires_at (default 24 h, at most 3 days).
create_presentation_from_jsonCreate presentation from jsonPOSTRenders and exports a presentation from your own slides, each a layout id plus a content object valid for that layout's schema (get_standard_template), with no story planning from a prompt. Returns presentation_id, path, edit_path.
export_presentationExport presentationPOSTExports an existing presentation (id from list_presentations or a generation answer) as pptx, pdf or png and returns path, the file URL, with edit_path and credits_consumed.
generate_presentationGenerate presentationPOSTGenerates an AI presentation and waits until it is exported: returns presentation_id, path (file URL) and edit_path. Pass content, slides or files. Uses one credit per generated slide (credits_consumed).
list_presentationsList presentationsGETLists the presentations of the account, one page at a time (page, page_size; type keeps only standard or smart decks): each with its id (for export_presentation or create_presentation_embed_link), title and dates.
start_presentation_from_jsonStart presentation from jsonPOSTStarts the same render as create_presentation_from_json as a background task and returns at once: id and status pending. Read the result with get_async_task (completed or error).
start_presentation_generationStart presentation generationPOSTStarts the same generation as generate_presentation as a background task and returns at once: id and status pending. Read the result with get_async_task (completed or error). Uses one credit per generated slide.

Image, 3 operations

delete_uploaded_imageDelete uploaded imageDELETEPermanently deletes one image from the account's image library. Answers 204 with no body.
list_uploaded_imagesList uploaded imagesGETLists the images uploaded to the account's image library: each with its id (for delete_uploaded_image), url, path and upload date.
upload_imageUpload imagePOSTUploads one image to the account's image library and returns its id (for delete_uploaded_image), path and url.

Webhook, 3 operations

list_webhooksList webhooksGETLists the account's webhook subscriptions: id (for unsubscribe_webhook), url, event and creation date. The subscription secret is not returned.
subscribe_webhookSubscribe webhookPOSTSubscribes an HTTPS url to one event (generation completed or failed); Presenton then calls it for every job started with trigger_webhook true. Returns the subscription id.
unsubscribe_webhookUnsubscribe webhookDELETERemoves one webhook subscription by id (from list_webhooks or subscribe_webhook); Presenton stops calling its url. Answers 204 with no body.

Smart design, 2 operations

create_smart_designCreate smart designPOSTStarts building a Smart Design from pptx_url, slide_image_urls and fonts returned by upload_pptx_and_preview and returns a task id at once. Poll get_smart_design_task until completed (data.design_id) or error.
list_smart_designsList smart designsGETLists the Smart Designs available to the account, a page at a time: id (pass it as smart_design to generate_presentation), name, thumbnail_url and dates.

Template, 2 operations

get_standard_templateGet standard templateGETReturns one Standard template with its layouts and, in schemas, one JSON schema per layout whose title is the layout id: build each slide's content against it for create_presentation_from_json.
list_standard_templatesList standard templatesGETLists the Standard templates available to the account, a page at a time: id (pass it as standard_template, or to get_standard_template), name, description, layout_count, thumbnail, is_default.

Font, 1 operation

check_pptx_fontsCheck pptx fontsPOSTInspects a reference PPTX and lists its fonts in two groups: available_fonts (Presenton can resolve them) and unavailable_fonts (supply a font file to upload_pptx_and_preview). First step of creating a Smart Design.

Outline, 1 operation

generate_outlineGenerate outlinePOSTDrafts the outline of a deck from content (or uploaded files) without creating a presentation: returns the outline as a list of strings. Use it to review the structure before generate_presentation.

Smart design preview, 1 operation

upload_pptx_and_previewUpload pptx and previewPOSTUploads the reference PPTX with up to 3 replacement fonts and returns slide previews, pptx_url and fonts: pass those three unchanged to create_smart_design.

Smart design task, 1 operation

get_smart_design_taskGet smart design taskGETReads a Smart Design creation task from create_smart_design: status pending or processing (still running), completed (data.design_id is the new Smart Design id) or error (see message and error).

Source file, 1 operation

upload_source_fileUpload source filePOSTUploads one source document (PDF, Word, PowerPoint, Excel, CSV, text, Markdown, HTML or AsciiDoc) and returns its file value; pass it in files to generate_presentation or generate_outline.

Task, 1 operation

get_async_taskGet async taskGETReads a background task from start_presentation_generation or start_presentation_from_json: status pending, completed or error. On completed, data holds presentation_id, path, edit_path, credits_consumed; on error see error and message.

Template example, 1 operation

get_standard_template_exampleGet standard template exampleGETReturns example slides for one Standard template: layout and content pairs that already satisfy its schemas, to show the nesting and content density create_presentation_from_json expects.

Use Presenton from Claude Code, Cursor or Codex

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

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