generate_slideshow

Make a slideshow with Wavegrain's MCP server: the generate_slideshow tool needs the generate permission. Inputs, outputs and an example call.

Make a slideshow. Permission: generate. Changes saved work.

Write and illustrate a slideshow about a topic. For a post link or a tailored style, use copy_post or create_tailored_slideshow. Read get_brand_brief first. Each slide gets a photo where one fits, else an AI image. Credits: script 1, photos 1, each AI image 1, typically 3; photosOnly makes no AI image. Refused, spending nothing, above maxCredits, your balance or this key's daily limit. Answers a jobId: poll get_generation_status; never call this again meanwhile (each call is charged).

Inputs

InputTypeRequiredNotes
topicstringyesWhat the slideshow is about. up to 500 characters
formatIdstringnoA saved format from list_formats. Default: your active brand with the settings below. up to 200 characters
brandIdstringnoOnly without formatId: the brand to write for. Default: your active brand. up to 200 characters
groupIdstringnoOnly without formatId: an account group (list_accounts) whose notes shape the script. up to 200 characters
slideCountintegernoOnly without formatId: how many slides. Default 6. 3 to 10
structure"hook-proof-cta" | "listicle" | "before-after" | "educational" | "story" | "quote" | "ranking"noThe kind of post: hook-proof-cta (Hook, proof, then a clear call to action); listicle (A numbered list); before-after (A transformation or comparison); educational (Teaches one idea step by step); story (A first-person narrative arc); quote (Quote or affirmation cards); ranking (Tier list or best-to-worst ranking); get_playbook gives each one's slides. Default: picked from the topic.
outputProfile"clean-square" | "clean-portrait" | "instagram-feed" | "instagram-feed-3-4" | "clean-vertical" | "tiktok" | "instagram-reels"noSlide size, width:height: clean-square 1:1, clean-portrait 4:5, instagram-feed 4:5 (default), instagram-feed-3-4 3:4, clean-vertical 9:16, tiktok 9:16, instagram-reels 9:16.
styleId"clean-ugc" | "clean-social" | "quiet-editorial" | "bold-statement" | "mens-looksmaxxing" | "comparison-grid" | "study-notes" | "aesthetic-soft" | "accent-pop"noText look: clean-ugc (Effortless lowercase native look); clean-social (Bold sans in normal case with a strong shadow); quiet-editorial (Serif); bold-statement (Big all-caps hook over a dramatic scene); mens-looksmaxxing (Dark portrait); comparison-grid (Before-after or best-worst decks); study-notes (Small clean caption low on a desk/flatlay); aesthetic-soft (Airy scene); accent-pop (Clean sans with a warm accent color).
hookstringnoThe cover's hook line, or the idea for it, in the brand's voice. up to 160 characters
ctaCardIdstringnoA CTA card from get_brand to close with. up to 200 characters
photosOnlybooleannotrue: no AI image, so only the script costs; a slide no photo fits stays empty.
maxCreditsintegeryesMost credits this call may spend; refused, spending nothing, if it could cost more. 0 to 1000
idempotencyKeystringnoOptional: your own unique id, such as a UUID. The same key within 24 hours returns the first job and charges nothing again. up to 200 characters

The fields inside an object or a list are in the JSON Schema at /developers/mcp-tools.json.

Returns

FieldTypeNotes
jobIdstringPass to get_generation_status to follow the job.
status"writing"The job started with the script.
estimatenumberThe most credits it can spend.
notestringWhat to do next.

Example call

Send it to POST https://wavegrain.com/api/mcp with an access key that has the generate permission; Authentication shows how to make one.

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "generate_slideshow",
    "arguments": {
      "topic": "<topic>",
      "maxCredits": 1
    }
  }
}

The call shows only the required inputs, with placeholder values: put your own in.

Something wrong or missing? Write to support@wavegrain.com.