Server definition
- Hash
- sha256:1267656e003c46dacb19838ee11d1602971f097e80a8c0e95fc3272ee7e07883
- What it is
- What a remote MCP server returned when asked what it offers: 11 tools
The blob, as servednamed by its sha256
{
"instructions": "Promptify Ad Studio. Generate UGC-style video ad scripts for a product using the user's Promptify credits. Rendering is available: call render_ad with adId to get the credit quote without spending, show it to the user and ask for approval, then call again with confirm: true and expectedCredits equal to the quoted totalCredits. A changed quote needs approval again. Open the returned studio results URL to check progress and finish/export the video. When credits are short, point users to https://www.promptify.pro/pricing. Never invent ad-performance numbers (impressions, CTR, spend, ROAS): this product has none. Link clicks are real and may be compared between the user's own ads, but they are not a rate.",
"tools": [
{
"description": "Estimate an ad plan before anything is spent, using the render engine's cost tables. For a saved ad's exact remaining cost, call render_ad with adId and no confirmation. Starting a render requires the user to approve that quote.",
"inputSchema": {
"properties": {
"scenes": {
"description": "How many scenes the ad will have (typically 3-5).",
"type": "number"
}
},
"required": [
"scenes"
],
"type": "object"
},
"name": "draft_ad_plan",
"outputSchema": null
},
{
"description": "Generate a full ad script package for a product: 10 hooks, a scene-by-scene script, and model-native video prompts (Veo/Kling). Costs about 2-3 credits, metered and refunded in full if it fails. This CREATES an ad in the user's Promptify workspace and returns a link to it — it does not render video.",
"inputSchema": {
"properties": {
"format": {
"description": "UGC testimonial | Unboxing | Problem → solution | Street interview | Before/after | Founder story",
"type": "string"
},
"language": {
"description": "Language to write the ad in. Defaults to English.",
"type": "string"
},
"productDescription": {
"description": "What it is and who it's for. The more concrete, the better the script.",
"type": "string"
},
"productTitle": {
"description": "The product's name.",
"type": "string"
},
"productUrl": {
"description": "Optional product page URL.",
"type": "string"
},
"templateId": {
"description": "Optional template id from list_templates — builds the ad on that hook device and beat structure.",
"type": "string"
}
},
"required": [
"productTitle"
],
"type": "object"
},
"name": "generate_ad_script",
"outputSchema": null
},
{
"description": "One ad in full: its hooks, its scene-by-scene script, and its model-native prompts. Use after list_ads when the user wants the actual content.",
"inputSchema": {
"properties": {
"adId": {
"description": "The ad's id, from list_ads.",
"type": "string"
}
},
"required": [
"adId"
],
"type": "object"
},
"name": "get_ad",
"outputSchema": null
},
{
"description": "What this workspace has MADE, what it EXPORTED (downloaded — the only activation signal), and real CLICKS on its Promptify short links, grouped by format and language. Clicks may be compared between the user's own ads; they are NOT a rate — there are no impressions, CTR, spend or ROAS anywhere in this product, so never state or imply one.",
"inputSchema": {
"properties": {},
"type": "object"
},
"name": "get_ad_stats",
"outputSchema": null
},
{
"description": "The workspace's saved brand profile — category, channels, languages, markets, preferred model. Read it before proposing an ad so the suggestion fits what they actually sell.",
"inputSchema": {
"properties": {},
"type": "object"
},
"name": "get_brand_profile",
"outputSchema": null
},
{
"description": "Check remaining subscription, purchased and total credits in this workspace. Costs no credits. If credits are low, follow the pricing link to buy more.",
"inputSchema": {
"properties": {},
"type": "object"
},
"name": "get_credit_balance",
"outputSchema": null
},
{
"description": "Get Promptify's pricing page for credit packs and monthly plans. Costs no credits.",
"inputSchema": {
"properties": {},
"type": "object"
},
"name": "get_pricing_link",
"outputSchema": null
},
{
"description": "The ads in this Promptify workspace: title, status, format, language, whether the user exported it, and real link clicks. Use it to answer 'what have I made' or to pick an ad to talk about.",
"inputSchema": {
"properties": {
"limit": {
"description": "How many, newest first (default 20, max 50).",
"type": "number"
}
},
"type": "object"
},
"name": "list_ads",
"outputSchema": null
},
{
"description": "Promptify's ad template library: each is a hook device plus a timed beat structure (e.g. 'skeptic-converts', 'negative hook', 'problem-agitate-solve'). Pass a template's id to generate_ad_script to build the ad on that structure. These are craft patterns, not proven winners — no template has performance data behind it.",
"inputSchema": {
"properties": {
"language": {
"description": "Filter by language code: EN, ES, PT, AR, FR, ZH.",
"type": "string"
}
},
"type": "object"
},
"name": "list_templates",
"outputSchema": null
},
{
"description": "First call with adId to get the real credit quote without spending. Show the user the cost and ask for approval. Only then call again with confirm: true and expectedCredits equal to totalCredits from the quote. A changed quote requires approval again. Uses the studio's paid render service; check progress and finish/export in the results URL.",
"inputSchema": {
"properties": {
"adId": {
"description": "The ad's id, from list_ads or generate_ad_script.",
"type": "string"
},
"confirm": {
"description": "True only after the user approves the quoted credit cost.",
"type": "boolean"
},
"expectedCredits": {
"description": "The exact totalCredits the user approved.",
"type": "number"
}
},
"required": [
"adId"
],
"type": "object"
},
"name": "render_ad",
"outputSchema": null
},
{
"description": "Read a product page and return its title, description and price. Costs no credits. Use this before generating so the ad is grounded in what the page actually says, instead of what the model assumes.",
"inputSchema": {
"properties": {
"url": {
"description": "The product page URL.",
"type": "string"
}
},
"required": [
"url"
],
"type": "object"
},
"name": "scrape_product",
"outputSchema": null
}
]
}Verify it yourself
curl -s https://api.teppi.xyz/v1/evidence/sha256:1267656e003c46dacb19838ee11d1602971f097e80a8c0e95fc3272ee7e07883 | sha256sum