StoryShort
REMOTE · STORYSHORT.APP
Make faceless AI short videos from a story idea: script, voiceover, captions, scenes.
Available components
Last scanned (13 hours ago)
Scores higher than 72% of remote servers
Reachable. Last reached 21 Nov 2026.
Category Design and Media
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security89
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token. View diagnostics → Pass
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
- The authorisation server offers only Dynamic Client Registration (RFC 7591), which MCP 2026-07-28 deprecated in favour of Client ID Metadata Documents. View diagnostics → Partial
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability59
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 11003 tokens (~323/item across 34 items; 34 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management30
- Stability observed for 9 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage95
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 85% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 35 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Checks we ran (13)
- TLS certificate
- Authorization
- HTTPS
- HSTS header
- DNSSEC
- Transport
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Does not apply to this hosted endpoint (2)
- Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
- Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 20 Nov 26 +1
- The server rewrote its instructions, which are the text every model session reads security
- 19 Nov 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Tool “create_video” rewrote its description, which is the text the model reads security
- Tool “draft_video” rewrote its description, which is the text the model reads security
- New tool “get_app_links” functional
- “create_video” added an optional parameter “prompt_handling” cosmetic
- “draft_video” added an optional parameter “prompt_handling” cosmetic
- 18 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.
- 17 Nov 26 0
- Tool “create_video” rewrote its description, which is the text the model reads security
- Tool “get_credit_balance” rewrote its description, which is the text the model reads security
- Tool “get_video” rewrote its description, which is the text the model reads security
- Tool “quote_video” rewrote its description, which is the text the model reads security
- Schema quality: 269 → 318 ▼ functional
- New tool “generate_motion_clip” functional
- New tool “list_motion_templates” functional
- New tool “list_pricing” functional
- New tool “quote_motion_clip” functional
- 15 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.
- 13 Nov 26 +1
- The server rewrote its instructions, which are the text every model session reads security
- Tool “create_video” rewrote its description, which is the text the model reads security
- Tool “draft_video” rewrote its description, which is the text the model reads security
- Tool “render_draft” rewrote its description, which is the text the model reads security
- Stability: unverified → 0.03 ▲ functional
- 12 Nov 26 74
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 21 Nov 2026 · Probed https://storyshort.app/api/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=storyshort.app | CN=YE1,O=Let's Encrypt,C=US | 20 Oct 2026 | 18 Jan 2027 | ECDSA 256 | ECDSA-SHA384 | 6e53de6406989838d44b6338db58a843533 |
| SANs: storyshort.app | ||||||
| CN=YE1,O=Let's Encrypt,C=US (CA) | CN=Root YE,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | ECDSA 384 | ECDSA-SHA384 | 5ddd70dd31f801c85c186a7a04b80afe |
| CN=Root YE,O=ISRG,C=US (CA) | CN=ISRG Root X2,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | ECDSA-SHA384 | 872165fc34b6e5fba8add5b3705fb53a |
| CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | SHA256-RSA | 6c8f1dc727c7117f7baf853ac980f9cd |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of storyshort.app. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | Trust anchor | 20326, 38696 | 8, 8 | Verified |
| app. | DS published | 23684 | 8 | Verified |
| storyshort.app. | No DS | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication Enforced and verified
The endpoint asked for a token and published valid RFC 9728 metadata describing how to get one.
| Result | Enforced and verified |
|---|---|
| Enforced | On tool calls |
| HTTP status | 200 |
WWW-Authenticate challenge Bearer resource_metadata="https://storyshort.app/.well-known/oauth-protected-resource/api/mcp"
Bearer resource_metadata="https://storyshort.app/.well-known/oauth-protected-resource/api/mcp" | Header | Value |
|---|---|
| x-content-type-options | nosniff |
| x-frame-options | DENY |
| referrer-policy | strict-origin-when-cross-origin |
| permissions-policy | camera=(), microphone=(), geolocation=() |
Protected resource metadata
| Document | https://storyshort.app/.well-known/oauth-protected-resource/api/mcp |
|---|---|
| Retrieved | Yes |
| Resource | https://storyshort.app/api/mcp |
| Authorisation server | https://storyshort.app |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://storyshort.app/api/mcp | Verified | 200 | |
| http (plaintext) | http://storyshort.app/api/mcp | HTTPS enforced | 301 | https://storyshort.app/api/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
cancel_video Cancel a video ~142
Cancel a video that has NOT started rendering: a draft, a video still queued (PENDING), or one whose failed render is waiting for an automatic retry. The video ends as FAILED "Cancelled" and is never rendered. Credits are charged only after a render succeeds, so normally nothing had been charged; if the ledger holds a charge for it, exactly that is refunded (idempotent, never twice) and refundedCredits says how much. A video that is already rendering, finished, or a clip made straight from a prompt is refused (CANNOT_CANCEL_STARTED) and left untouched. Requires the "video:create" scope.
| Name | Type | Req | Description |
|---|---|---|---|
| videoId | string | yes | – |
No output schema declared.
No examples provided.
create_character_episode Create a character episode ~631
Make the episode: 3-8 shots, 12-60 seconds, the same fictional character in every shot, narrated with captions. CHARGES credits (up to 313 credits for a default 12-second episode; longer ones (up to 60 seconds) cost more). ALWAYS call quote_character_episode first and tell the human the price: the human, not the agent, decides to spend. This tool refuses unless confirm is true, expectedCredits equals the price computed now (a changed price answers 409 PRICE_CHANGED and charges nothing) and idempotencyKey is set; StoryShort has no daily spending cap per key, so these are the guard. The series must have a REVIEWED, CONFIRMED season plan and the episode must be one of its episodes exactly as planned (SEASON_PLAN_REQUIRED / SEASON_NOT_REVIEWED / EPISODE_NOT_IN_PLAN otherwise, with a nextAction, nothing charged); the narrator voice, language, style, look and outfit come from the plan. Credits are held when it starts. A shot that cannot be animated keeps a still image and its clip credits go back; if too few shots move, or anything else fails, everything goes back. Characters are fictional adults (or animals / mascots), AI-generated: no real or famous people, no children or anyone who looks under 18, no sexual content, no logos or protected characters (refused with CONTENT_POLICY, nothing charged). Everything made here is AI-generated and labelled as such. Takes about 10-25 minutes: poll get_video with arguments { id: <the returned id / videoId> }; it reports status, stage and, when COMPLETED, videoUrl. One episode at a time per account. Requires the "video:create" scope.
| Name | Type | Req | Description |
|---|---|---|---|
| confirm | boolean | yes | Must be true: making an episode spends credits, and the human has seen the price. |
| expectedCredits | integer | yes | The credits the quote showed the human. Must match the price computed now. |
| idempotencyKey | string | yes | Required. One new unique key per purchase; a repeat with the same key returns the first answer (replayed: true) and charges nothing. |
| language | string | – | Omit it: the narration language is the season plan's. If given it must equal the plan's. |
| script | string | – | The narration, about 29-147 words. The system splits it into shots by sentence. Give `script` OR `shots`, exactly as planned (get_season_plan). |
| seriesId | string | yes | A series id from list_series whose season plan is reviewed and confirmed. |
| sheetId | string | – | Omit it: the character sheet is the one the season plan names for this episode. If given it must equal that sheet. |
| shotCount | integer | – | With `script`: how many shots to split it into. Omit for an automatic count. |
| shots | array | – | The shots of the planned episode. Give `shots` OR `script`. |
| title | string | – | Optional title. |
No output schema declared.
No examples provided.
create_character_sheet Create a character sheet ~576
Make a character sheet for one of your series: 4-6 AI images (default 5: front portrait, full body, side, expressions) of ONE fictional character, from a text description. CHARGES credits: 23 credits for 5 images of a person, 11 for an animal or mascot. ALWAYS call get_character_sheet first and tell the human the price: the human, not the agent, decides to spend. This tool refuses unless confirm is true, expectedCredits equals the price computed now (a changed price answers 409 PRICE_CHANGED and charges nothing) and idempotencyKey is set; StoryShort has no daily spending cap per key, so these are the guard. Credits are taken when it starts and returned in full if no sheet comes back. If a non-primary view could not be made in time, the sheet still comes back with the images that exist (the answer says partial: true and lists missingViews) and only those images are charged: the difference is returned and creditsCharged shows what was kept. For a person the face is carried from the front portrait into the other views; the outfit follows the description and can drift a little. For an animal or mascot the views share one description and seed, so they look alike but are not guaranteed to be identical. Usually under a minute; the answer already contains the images (a slow image model fails the call and returns the credits). Characters are fictional adults (or animals / mascots), AI-generated: no real or famous people, no children or anyone who looks under 18, no sexual content, no logos or protected characters (refused with CONTENT_POLICY, nothing charged). Everything made here is AI-generated and labelled as such. A series can hold 3 sheets in total; the first sheet is chosen automatically. A series made with create_series has no saved character description: pass `description`. Requires the "video:create" scope.
| Name | Type | Req | Description |
|---|---|---|---|
| confirm | boolean | yes | Must be true: making a sheet spends credits, and the human has seen the price. |
| description | string | – | The character's look: age band, hair, outfit, colours. Omit to use the series' saved character description. |
| expectedCredits | integer | yes | The price the human saw (get_character_sheet quotes for this kind and image count). Must equal the price computed now. |
| idempotencyKey | string | yes | Required. One new unique key per purchase; a repeat with the same key returns the first answer (replayed: true) and charges nothing. |
| imageCount | integer | – | Images in the sheet (default 5). |
| seriesId | string | yes | A series id from list_series. |
| subjectKind | string | – | PERSON (fictional adult, default), ANIMAL (pet) or MASCOT. |
No output schema declared.
No examples provided.
create_series Create a series ~527
Create a series: StoryShort makes a video on this niche every scheduleIntervalDays, and can auto-post it to YouTube. The series NAME is the topic every video is written from, so put the user's own subject in it. Creating or changing a series is FREE. While active, the scheduler makes one video every scheduleIntervalDays (the first at its next run, within about 30 minutes) and charges each video like any video, 40 credits with the default render, at render time. It needs at least 40 credits in the balance: when the balance cannot pay for the next video the scheduler PAUSES the series (it never overdraws), so create_series and resume_series refuse with SERIES_NEEDS_CREDITS instead of making a series that would never run. Agents may keep at most 5 series active at once (SERIES_LIMIT_REACHED). StoryShort has no per-key daily spending cap: pause_series is the brake. Set startPaused: true to create it without generating (then resume_series). Accounts with fewer credits than one video (every new account starts at 0, and free accounts cannot run a series) are refused: you get SERIES_NEEDS_CREDITS with a topUpUrl, nothing is created. autoPostYouTube only works once YouTube is connected (get_connection_status) — nothing checks it here; madeForKids is the COPPA answer, ask the user. A name that already exists returns SERIES_EXISTS. TikTok auto-post is not available for series (use publish_video, which sends to Drafts). Pass idempotencyKey so a retry never makes a second series. Requires the "video:create" scope.
| Name | Type | Req | Description |
|---|---|---|---|
| autoPostYouTube | boolean | – | Upload each finished video to the connected YouTube channel. |
| defaultDuration | integer | – | Seconds per video; longer lengths need a paid plan. |
| idempotencyKey | string | – | Retry-safe: a repeat with the same key returns the first answer (replayed: true). |
| language | string | – | Narration language code, e.g. "en" (default). |
| madeForKids | boolean | – | COPPA answer for YouTube uploads from this series. Ask the user. |
| name | string | yes | The series topic/name; every video is generated from it. |
| niche | string | yes | Content niche (list_niches). |
| quality | string | – | – |
| scheduleIntervalDays | integer | – | One video every N days (default 1 = daily). |
| startPaused | boolean | – | Create without generating until resume_series. |
No output schema declared.
No examples provided.
create_video Create a video ~680
Create (enqueue) a new AI faceless video from a topic. Returns immediately with a video id and status "PENDING"; the render runs asynchronously — poll get_video every 20-30 seconds until status is "COMPLETED" (playable videoUrl) or "FAILED". Costs 40 credits with the default voice (+25 for a language only ElevenLabs speaks, e.g. Persian); art style does not change the price. A short balance is refused up front with 402 INSUFFICIENT_CREDITS stating credits needed, available and a top-up URL. A new account with no credits that has not had its free first video gets it here instead of an error: watermarked, labelled AI-generated, up to 30 seconds, standard voice, one per account, subject to the day's availability. (Standard 30-second style; niche, art style and motion do not apply to it.) Set prompt_handling to "as_written" to use my words exactly. If the model refuses a scene, it fails instead of being reworded. Requires the "video:create" scope on the API key. OPTIONAL AI MOTION: pass motion_scenes (0-3, default 0 = a normal video) to turn that many scenes, starting with the first, into a 5-second AI video clip instead of a still image. Price: 115 credits per motion scene EXTRA (so 1 scene = 155 credits in total with the default voice). Call quote_video first and tell the user the price before creating. Any account with enough credits can use it: there is no plan or trial limit. A clip that cannot be made falls back to the still image and its 115 credits are refunded. Content is checked first: children, real people, sexual content, protected characters and lip-sync/deepfakes are refused (422 PROMPT_BLOCKED, nothing charged). For a pasted cinematic video prompt (camera, lens, lighting, one shot) use generate_motion_clip instead: it sends the prompt as written and makes one silent clip, with no script or voice.
| Name | Type | Req | Description |
|---|---|---|---|
| artStyle | string | – | Optional visual art style. Defaults to AUTOSHORTS (cinematic). Call list_niches for the full list. |
| duration | number | – | Target length in seconds for the multi-scene faceless video: 30, 60 or 90 (default 30). |
| language | string | – | Optional BCP-47 language code (e.g. "en", "vi", "es"). Defaults to "auto". |
| motion_scenes | integer | – | Optional. How many scenes (from the first) to animate as AI clips. 115 credits each, on top of the video price. Default 0. |
| niche | string | – | Optional content niche. Call list_niches for the authoritative list with labels. |
| prompt_handling | string | – | "as_written": Use my words exactly. If the model refuses a scene, it fails instead of being reworded. Scenes the user wrote nothing for are still generated. "assist" (default): the product may reword… |
| topic | string | yes | What the video is about. The full script is AI-generated from this. e.g. "3 tiny habits that quietly change your life". |
No output schema declared.
No examples provided.
draft_video Draft a video script ~380
Write a video's script and scenes WITHOUT rendering or charging, so the user can read and change it first. Returns draftId, the scenes (narration + visual prompt each) and the exact render price. Free, but it runs the script writer once: needs a balance that can pay for a render and is limited to 20 drafts per hour. Then: show it → update_draft / revise_scene → render_draft only after the user approves the price. A new account with no credits that has not had its free first video gets it here instead of an error: watermarked, labelled AI-generated, up to 30 seconds, standard voice, one per account, subject to the day's availability. For that video the draft is up to 30 seconds (about 80 words) and 3 drafts per hour. Set prompt_handling to "as_written" to use my words exactly. If the model refuses a scene, it fails instead of being reworded. Each scene says who wrote its picture text (promptSource). Use create_video instead when no review is wanted. Requires the "video:create" scope.
| Name | Type | Req | Description |
|---|---|---|---|
| artStyle | string | – | Optional art style (default AUTOSHORTS). |
| duration | number | – | Target length in seconds (default 30; 90 needs a paid plan). |
| language | string | – | Optional BCP-47 narration language, e.g. "en", "vi". |
| prompt_handling | string | – | "as_written": Use my words exactly. If the model refuses a scene, it fails instead of being reworded. "assist" (default): the product may reword picture text, as before. |
| title | string | – | Optional title (defaults to the topic). |
| topic | string | yes | What the video is about; the script is written from it. |
No output schema declared.
No examples provided.
generate_motion_clip Generate an AI motion clip ~1,318
Turn a text-to-video prompt into ONE AI motion clip (Seedance 2.0 Mini). The prompt is sent EXACTLY as written: no script is written, no still images are made, no voice is added, nothing is rewritten or shortened. USE THIS TOOL when the user pastes or asks for a cinematic / video-model prompt (camera moves, lens, lighting, a scene description, "9:16 vertical", "slow dolly-in", the kind ChatGPT or Claude writes for Seedance, Sora or Veo). For a narrated story or facts video use create_video. The clip is silent (no audio, no lip-sync, no talking), 4-12 seconds (default 5), 480p. Price: 4 s = 92 credits, 5 s = 115, 12 s = 276; call quote_motion_clip first and tell the user the price before creating. These are the standard prices. A lower price applies for the credits bought in the last 31 days (an active paid plan period or a credit pack): the standard clip then costs 10 credits per second (5 s = 50). quote_motion_clip returns the exact price for THIS account. The credits are held when the clip is accepted and returned in full if no clip comes back. The only text added to the prompt is a short server suffix ("No spoken dialogue, no lip-sync, no talking to camera, no watermark."); the answer echoes promptSent and the seed so the user can see and repeat exactly what was made. Not accepted (CONTENT_POLICY, nothing charged): real or famous people, minors, sexual content, protected characters or brands, deepfakes and lip-sync. A first-frame photo is not supported. Optional templateId: one of the 26 ready clip templates from list_motion_templates; its prompt, seconds and aspect ratio are used. If you also pass prompt, the prompt wins and the template is ignored. An unknown templateId is refused (INVALID_INPUT, nothing charged). Any account with enough credits can use it: there is no plan or trial limit, too few credits is the only account refusal (INSUFFICIENT_CREDITS, nothing charged). At most 2 clips run at once; a daily capacity limit applies (DAILY_CAP_REACHED). Renderi…
| Name | Type | Req | Description |
|---|---|---|---|
| aspect_ratio | string | – | Frame shape (default 9:16, vertical). |
| duration | integer | – | Clip length in whole seconds (default 5). Up to 12 without tier; up to 30 with an optional tier. From 4 without tier; from 2 on a tier that makes shorter clips. |
| idempotencyKey | string | – | Retry-safe: a repeat with the same key returns the first answer (replayed: true) and charges nothing. |
| prompt | string | – | The video prompt, exactly as the user wrote or pasted it (8-2000 characters). Do not summarise, translate or "improve" it: it is sent to the video model unchanged. Required unless templateId is given. |
| seed | integer | – | Optional. The answer always returns the seed used; pass it again to ask for a similar take (the provider treats it as best effort). |
| templateId | string | – | Optional. The id of a motion clip template (list_motion_templates): its ready-made prompt is sent as written. Ignored when prompt is also given. |
| tier | string | – | Optional. A higher-quality model with sound: seedance-2.5-480p = Seedance 2.5 480p (with sound); seedance-2.5-720p = Seedance 2.5 720p (with sound); wan-3.0-480p = Wan 3.0 480p (with sound); wan-3.0-… |
No output schema declared.
No examples provided.
get_app_links Get app download links ~166
Where to get StoryShort on each platform: the App Store listing for iPhone and iPad, the Mac App Store listing, the web app (any browser, Android included), the Android APK (direct download) and the Android closed beta, plus the URL of a QR code image for the App Store page. Also lists what does not exist yet (a public Google Play listing) so nobody is sent to a link that is not there. For a user who asks how to install, download or open StoryShort. Needs no credentials and no scope. Read-only and free: nothing is created or charged.
| Name | Type | Req | Description |
|---|---|---|---|
| platform | string | – | Optional. Return only this platform: ios (iPhone and iPad), macos, web or android. Omit for all of them. |
No output schema declared.
No examples provided.
get_character_sheet Get a character sheet ~187
Read the character sheets of one of your series: each sheet is a set of AI images of one fictional character, its images (id, view, url), which sheet and which image are chosen, how many sheets the series may still make (3 in total), and the exact price of a new sheet (23 credits for 5 images of a person, 11 for an animal or mascot). Free. Use this before create_character_sheet and tell the human the price. Characters are fictional adults (or animals / mascots), AI-generated: no real or famous people, no children or anyone who looks under 18, no sexual content, no logos or protected characters (refused with CONTENT_POLICY, nothing charged). Everything made here is AI-generated and labelled as such. Requires the "video:read" scope.
| Name | Type | Req | Description |
|---|---|---|---|
| seriesId | string | yes | A series id from list_series. |
No output schema declared.
No examples provided.
get_connection_status Check a platform connection ~140
Is this platform connected? If yes, returns the account. If not, returns connectUrl: the page that opens the platform's consent screen. Give it to the user — that consent is the only human step, once per platform; they must be signed in to the same StoryShort account as this API key — then call this again every 10 seconds (pollAfterSeconds) until connected is true and continue on your own. The link is not single-use and holds no secret. YouTube and TikTok need a paid plan (PLAN_UPGRADE_REQUIRED otherwise). Requires the "video:read" scope. Free.
| Name | Type | Req | Description |
|---|---|---|---|
| platform | string | yes | – |
No output schema declared.
No examples provided.
get_credit_balance Get credit balance ~140
Get the caller's current credit balance, monthly allocation and plan. Use this before create_video to confirm the account can afford a render (40 credits). Requires the "credits:read" scope (included by default in new keys); a key without it gets 403 INSUFFICIENT_SCOPE with a link to create a key that has it. Read-only, never charges credits. Also returns hasPaid: whether a plan charge or a credit pack purchase is on record for the account (a trial start fee alone does not count). usdPerCredit is what one credit costs this account in USD, and usdPerCreditBasis says where that number comes from.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_draft Get a draft ~68
Read a draft: its scenes (narration, visual prompt, length), whether the narration is long enough for the target duration, and the exact render price against the current balance. Free, read-only. Requires the "video:read" scope.
| Name | Type | Req | Description |
|---|---|---|---|
| draftId | string | yes | – |
No output schema declared.
No examples provided.
get_season_plan Get a season plan ~139
Read the season plan of one of your series: the plan (logline, genre, narrator voice, language, style, cast with outfits, every episode), its hash, its status (none, saved, reviewed or confirmed) and the recorded season review (a checklist with pass or fail per rule, the season price and, if it ran, the AI review). Free. An episode can only be made from a plan that is reviewed and confirmed: use this to see where the plan stands and which episodes can be quoted. Requires the "video:read" scope.
| Name | Type | Req | Description |
|---|---|---|---|
| seriesId | string | yes | A series id from list_series. |
No output schema declared.
No examples provided.
get_series_performance Get series performance ~154
How YOUR OWN posted YouTube Shorts performed, per series: videos posted/measured, total/median/mean views, top 3 and bottom 3 videos (with outlierScore = views / series median), and views gained in the last 7 days vs the 7 days before. Use it to decide what to make next. Only your own videos; views come from daily YouTube snapshots; audience retention is not available. Requires the "video:read" scope. Free, read-only.
| Name | Type | Req | Description |
|---|---|---|---|
| days | integer | – | Only videos created in the last N days (default 30). |
| seriesId | string | – | One series id (from list_series). Omit for every series with posted videos. |
No output schema declared.
No examples provided.
get_video Get a video ~185
Get the status and details of one video the caller owns, by id. While rendering, status is PENDING/GENERATING_*/RENDERING and estimatedCompletionTime (seconds) is returned. When status is COMPLETED, a playable videoUrl and thumbnailUrl are returned; when FAILED, error says why, and a failure for lack of credits adds blockedReason "INSUFFICIENT_CREDITS" with creditsNeeded, creditsAvailable and topUpUrl (it will not be retried: top up and create the video again). Requires the "video:read" scope. Read-only, never charges credits. Also polls a motion clip made by generate_motion_clip: the answer then has kind "motion_clip", the promptSent, and on FAILED an errorCode and creditsRefunded.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | The video id returned by create_video or list_videos. |
No output schema declared.
No examples provided.
list_motion_templates List motion clip templates ~241
List the 26 AI motion clip templates (single-shot prompts for landscapes, macro food, animals, products, abstract loops, city nights, weather, miniatures, fantasy scenery and short-drama beats in thriller, comedy, horror, romance, action, epic and drama; the clips are silent, and any person is only a silhouette, seen from behind or as hands, never a face or a child). Each has the full prompt, genre, a six-slot breakdown (camera, subject, action, setting, style, lighting: each phrase is literally in the prompt), a one-line why, seconds, credits, a demoVideoUrl when a sample clip exists, and the arguments for generate_motion_clip (pass its id as templateId, or edit the prompt and pass it as prompt). Pass id for one template, or genre (drama, thriller, comedy, horror, romance, action, epic, nature, product, fantasy) to filter. Nothing is created or charged; show the user the price before you generate. Free.
| Name | Type | Req | Description |
|---|---|---|---|
| genre | string | – | Only templates of this genre. |
| id | string | – | Return just this template. |
No output schema declared.
No examples provided.
list_niches List niches and art styles ~53
List the available content niches, art styles, video qualities and durations that create_video accepts. Use this to pick valid niche/artStyle values. Requires the "video:read" scope. Read-only, never charges credits.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
list_pricing List prices ~177
The price list. Read-only and free: nothing is created or charged. Returns every plan on sale (name, USD per month, credits per month, USD per credit), every one-time credit pack (credits, USD, USD per credit) and, when this account would get it at checkout, the first-purchase offer. Also returns what things cost in credits: a video, and each add-on or clip product that is switched on, with its credits per unit (per scene, or per second with the length range). account.usdPerCredit is what one credit costs this account in USD (usdPerCreditBasis says where the number comes from), so a credit price can be told to the user in dollars. All prices are what customers pay; tax may be added at checkout. Requires the "video:read" scope.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
list_series List series ~74
List the user's series (autopilot channels), newest first, with schedule, auto-post flags, active/paused state, credits per video and an estimate per month. Paginated (page, limit). Requires the "video:read" scope. Free.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | – |
| page | integer | – | – |
No output schema declared.
No examples provided.
list_social_accounts List connected publishing accounts ~77
List the connected publishing accounts (YouTube, TikTok) with username, whether they need reconnecting, the publish mode, the AI-disclosure handling and today's platform limits. Never returns tokens. For a platform that is not connected, call get_connection_status to get a connectUrl. Requires the "video:read" scope. Free.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
list_videos List videos ~115
List the caller's videos, newest first, with pagination. Optionally filter by status (one of the VideoStatus values in the schema). Returns id, title, status, videoUrl, thumbnailUrl and timestamps. Requires the "video:read" scope. Read-only, never charges credits.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | number | – | Max videos to return (default 20, max 100). |
| offset | number | – | Number of videos to skip for pagination (default 0). |
| status | string | – | Optional status filter. |
No output schema declared.
No examples provided.
pause_series Pause a series ~56
Pause a series: the scheduler stops making (and charging for) its videos until resume_series. Videos already made are untouched. Requires the "video:create" scope. Free.
| Name | Type | Req | Description |
|---|---|---|---|
| seriesId | string | yes | Series id (or slug). |
No output schema declared.
No examples provided.
plan_drama_season Plan a drama season ~413
Drama Studio writers room: turn a one-line premise into a short-drama season: a character bible (1-4 original fictional characters: name, role, look) and 2-8 episode scripts, each with a title, a logline, a script and a "cliffhangerLine". The cliffhanger is SPOKEN: the script's last sentence is exactly "cliffhangerLine" (an open hook for every episode but the last; a payoff plus one lingering question for the last), the first sentence is a hook and the next episode picks the hook up. Each script is already sized to pass quote_character_episode (12-60 seconds of narration); an episode that could not be made to fit comes back with needsEditing: true and the exact limit in `issue`. FREE: it spends no credits, starts nothing and saves nothing (it is limited per hour). Characters are fictional adults (or animals / mascots), AI-generated: no real or famous people, no children or anyone who looks under 18, no sexual content, no logos or protected characters (refused with CONTENT_POLICY, nothing charged). Everything made here is AI-generated and labelled as such. Next steps: create_series (startPaused: true; its name is only a label), create_character_sheet with the main character as `description` (show the human the price first), then save_season_plan (the whole season: cast, voice, style, every episode), review it, get the human's yes and confirm it; only then quote_character_episode and create_character_episode per episode. Requires the "video:read" scope.
| Name | Type | Req | Description |
|---|---|---|---|
| episodes | integer | yes | How many episodes. |
| genre | string | yes | drama, thriller, comedy, horror or romance. |
| language | string | – | Language code of the scripts, such as 'en' or 'vi'. Default 'en'. |
| premise | string | yes | The story in one to three sentences: who, what they want, what goes wrong. |
No output schema declared.
No examples provided.
publish_video Publish a video ~385
Publish one of the user's COMPLETED videos. YOUTUBE: uploads to the connected channel with your title/description and privacy (public, unlisted, private); the "altered or synthetic content" disclosure is always set; madeForKids is the user's COPPA answer (ask them for a kids audience); nothing is appended to the description unless addAttribution is true (default false — only when the user asked for "Made with StoryShort"). TIKTOK: sends the video to the creator's TikTok Drafts (inbox) — they add the caption, switch on the AI-generated label and post in the app; pass userConsent: true only after the user agreed. Idempotent per (videoId, platform): a repeat returns the first result and never posts twice (a video already posted from the website counts). Respects platform caps (YouTube ≈5 uploads/day; TikTok's pending-drafts limit). Not connected → NOT_CONNECTED with a connectUrl. Requires the "video:create" scope. Free.
| Name | Type | Req | Description |
|---|---|---|---|
| addAttribution | boolean | – | YouTube only. Append "Made with StoryShort", a link and #StoryShort to the description. Default false: set true ONLY if the user explicitly asked for it. |
| description | string | – | YouTube description. #Shorts is added if missing. |
| madeForKids | boolean | – | YouTube COPPA declaration. Omit to use the series answer, or the niche default. |
| platform | string | yes | – |
| privacy | string | – | YouTube visibility (default public). |
| title | string | – | YouTube title (cleaned and cut to 60 characters on a word). Defaults to the video title. |
| userConsent | boolean | – | TikTok only: the user agreed to send this video to their TikTok drafts. |
| videoId | string | yes | – |
No output schema declared.
No examples provided.
quote_character_episode Quote a character episode ~482
Price one PLANNED episode (12-60 seconds, 3-8 shots) of a series with a confirmed season plan, starring the character the plan names. FREE: it spends nothing and starts nothing. Returns the shot plan (narration, action, camera and seconds of every shot), the exact credits (up to 313 credits for a default 12-second episode; longer ones (up to 60 seconds) cost more: an AI clip per shot, a still per shot and the narration), and a ready-made nextAction for create_character_episode. Show the human the price and the shots, and call the create tool only after they say yes. The same safety checks as the real call run here: real or famous people, anyone who looks under 18, sexual content and protected characters are refused with CONTENT_POLICY. Only an episode of a REVIEWED, CONFIRMED season plan can be quoted or made: send its script or shots exactly as planned (get_season_plan). Without a confirmed plan the answer is SEASON_PLAN_REQUIRED or SEASON_NOT_REVIEWED, and for shots that are not a planned episode EPISODE_NOT_IN_PLAN, each with a nextAction. The narrator voice, the language, the style and the character come from the plan and cannot be overridden (SEASON_FIELD_LOCKED); to change an episode, edit the plan (that clears the review). Requires the "video:read" scope.
| Name | Type | Req | Description |
|---|---|---|---|
| language | string | – | Omit it: the narration language is the season plan's. If given it must equal the plan's. |
| script | string | – | The narration, about 29-147 words. The system splits it into shots by sentence. Give `script` OR `shots`, exactly as planned (get_season_plan). |
| seriesId | string | yes | A series id from list_series whose season plan is reviewed and confirmed. |
| sheetId | string | – | Omit it: the character sheet is the one the season plan names for this episode. If given it must equal that sheet. |
| shotCount | integer | – | With `script`: how many shots to split it into. Omit for an automatic count. |
| shots | array | – | The shots of the planned episode. Give `shots` OR `script`. |
| title | string | – | Optional title. |
No output schema declared.
No examples provided.
quote_motion_clip Quote an AI motion clip ~871
The exact credit price of ONE prompt-to-motion clip (generate_motion_clip) BEFORE it is made, and whether this account may start it right now. Read-only: nothing is created, reserved or charged, and no prompt is checked. Returns credits (5 s = 115), the balance, canAfford, canStart and, when it cannot be started, blockedBy (code + message) and a nextAction. The price is the account's own: 115 at the standard price, 50 at the low price, which applies for the credits bought in the last 31 days (an active paid plan period or a credit pack). lowPriceCreditsLeft says how many low-price credits are left; priceWithRecentPayment is present when this quote is at the standard price. Too few credits, clips already in flight and the daily limit show up here. Tell the user the price before you call generate_motion_clip. (quote_video is the other quote: animated scenes of a normal video.) Requires the "video:read" scope. Optional tier: "seedance-2.5-480p" (Seedance 2.5 480p (with sound), 4-30 s, 68 credits per second: 5 s = 340, 15 s = 1020; 30 per second at the low price); "seedance-2.5-720p" (Seedance 2.5 720p (with sound), 4-30 s, 152 credits per second: 5 s = 760, 15 s = 2280; 66 per second at the low price); "wan-3.0-480p" (Wan 3.0 480p (with sound), 2-30 s, 33 credits per second: 5 s = 165, 15 s = 495; 15 per second at the low price); "wan-3.0-720p" (Wan 3.0 720p (with sound), 2-30 s, 66 credits per second: 5 s = 330, 15 s = 990; 29 per second at the low price); "wan-3.0-1080p" (Wan 3.0 1080p (with sound), 2-30 s, 131 credits per second: 5 s = 655, 15 s = 1965; 57 per second at the low price). A tier with sound returns the clip WITH an AI-generated sound track (speech, ambience) and the "no spoken dialogue" suffix is not added. Lip-sync, face swaps and talking avatars (a person talking to the camera) stay refused on every tier, with or without sound. A clip on an optional tier can take up to 30 minutes: keep polling, the credits stay held while it is being made. Without ti…
| Name | Type | Req | Description |
|---|---|---|---|
| aspect_ratio | string | – | Frame shape (default 9:16). |
| duration | integer | – | Clip length in whole seconds (default 5). Up to 12 without tier; up to 30 with an optional tier. From 4 without tier; from 2 on a tier that makes shorter clips. |
| tier | string | – | Optional. A higher-quality model with sound: seedance-2.5-480p = Seedance 2.5 480p (with sound); seedance-2.5-720p = Seedance 2.5 720p (with sound); wan-3.0-480p = Wan 3.0 480p (with sound); wan-3.0-… |
No output schema declared.
No examples provided.
quote_video Quote a video with motion clips ~255
The exact credit price of a video with AI motion clips BEFORE it is made, and whether this account may make it. Read-only: nothing is created, reserved or charged, and no prompt is checked. approxUsd is totalCredits in USD at what a credit costs this account, and approxUsdBasis says how it is worked out. Returns baseCredits (the normal video), motionCredits (115 credits per motion scene, each a 5-second clip, on top of the normal video price), totalCredits, the balance and whether it covers the total, maxMotionScenes and, when it cannot be made, code + reason (MOTION_CLIPS_DISABLED: the feature is switched off). There is no plan or trial limit: enough credits is the only account condition. Motion scenes that cannot be made fall back to a still image with their credits refunded. Pass the same motion_scenes to create_video. Requires the "video:read" scope.
| Name | Type | Req | Description |
|---|---|---|---|
| language | string | – | Optional BCP-47 code (e.g. "en", "fa"). A language only ElevenLabs speaks adds its voice premium to baseCredits. |
| motion_scenes | integer | – | How many scenes to price as AI clips (default 1). |
No output schema declared.
No examples provided.
render_draft Render a draft ~264
Render an approved draft into the video. THIS IS THE ONLY STEP THAT COSTS CREDITS: the price is quote.credits from get_draft / draft_video, charged once after the render succeeds (a failed attempt costs nothing; StoryShort may retry a failed render automatically, up to 3 times, and the same video is never charged twice — cancel_video stops the retries). Call it first without confirmCredits to get QUOTE_REQUIRED and the price, show the user, then call again with confirmCredits set to that exact number. A wrong number is refused (PRICE_CHANGED); a short balance is refused up front (INSUFFICIENT_CREDITS). A new account with no credits that has not had its free first video gets it here instead of an error: watermarked, labelled AI-generated, up to 30 seconds, standard voice, one per account, subject to the day's availability. That first video needs no confirmCredits; the answer carries its video id. Calling it again on a draft that is already rendering starts nothing new. Poll get_video until COMPLETED or FAILED. Requires the "video:create" scope.
| Name | Type | Req | Description |
|---|---|---|---|
| confirmCredits | integer | – | The render price in credits the user approved (quote.credits). |
| draftId | string | yes | – |
No output schema declared.
No examples provided.
resume_series Resume a series ~209
Resume a paused series. Refused with SERIES_NEEDS_CREDITS when the balance cannot pay the next video, and with SERIES_LIMIT_REACHED at 5 active series. Creating or changing a series is FREE. While active, the scheduler makes one video every scheduleIntervalDays (the first at its next run, within about 30 minutes) and charges each video like any video, 40 credits with the default render, at render time. It needs at least 40 credits in the balance: when the balance cannot pay for the next video the scheduler PAUSES the series (it never overdraws), so create_series and resume_series refuse with SERIES_NEEDS_CREDITS instead of making a series that would never run. Agents may keep at most 5 series active at once (SERIES_LIMIT_REACHED). StoryShort has no per-key daily spending cap: pause_series is the brake. Requires the "video:create" scope.
| Name | Type | Req | Description |
|---|---|---|---|
| seriesId | string | yes | Series id (or slug). |
No output schema declared.
No examples provided.
revise_scene Revise one scene of a draft ~150
Change ONE scene of a draft in place: its narration (scriptText), its visualPrompt and/or its durationSeconds. Scene numbers start at 1 (see get_draft). Only the fields you pass change. Screened like any prompt. Free; draft only. Requires the "video:create" scope.
| Name | Type | Req | Description |
|---|---|---|---|
| draftId | string | yes | – |
| durationSeconds | number | – | Scene length (default 10). |
| scene | integer | yes | Scene number, starting at 1. |
| scriptText | string | – | The narration of this scene, exactly as it will be spoken. |
| visualPrompt | string | – | What the image should show. Leave empty to let StoryShort write it at render. |
No output schema declared.
No examples provided.
save_season_plan Save or review a season plan ~497
Design, review and confirm the WHOLE season of a series before any episode is made. Free (no credits). A series is fully designed and reviewed before any video is produced, and its characters, voice and style are fixed in every episode. Three steps, one tool: (1) pass `plan` to save it (version 1: logline, genre, language, narratorVoiceId, styleTokens, characters[] with look, sheetId and wardrobeLock, rules[], at least 3 episodes[] with title, characterName, cliffhangerLine and shots[] or a script). Every edit clears the review and the confirmation. (2) pass `review: true` (with or without `plan`) to run the season review: a deterministic checklist (cliffhangers, hooks, one narrator and style, no on-screen text, one subject per look and per shot, outfit locked, season price) plus an advisory AI review that lists up to 8 concrete issues; if the AI review cannot run the answer says so and the checklist stands. (3) show the human the checklist, the AI issues and the season price, and ONLY after they say yes call again with `confirm: true` and `planHash` from the review. Every character an episode uses needs a READY sheet of this series (create_character_sheet, one sheet per character) whose id is in the plan. Then quote_character_episode / create_character_episode make the planned episodes. Characters are fictional adults (or animals / mascots), AI-generated: no real or famous people, no children or anyone who looks under 18, no sexual content, no logos or protected characters (refused with CONTENT_POLICY, nothing charged). Everything made here is AI-generated and labelled as such. Requires the "video:create" scope.
| Name | Type | Req | Description |
|---|---|---|---|
| aiReview | boolean | – | With review: also run the advisory AI review (default true). |
| confirm | boolean | – | The owner confirms the reviewed plan. Needs planHash; do not send `plan` in the same call. |
| plan | object | – | The whole season plan. Omit to review or confirm the stored one. |
| planHash | string | – | With confirm: the planHash the review returned. |
| review | boolean | – | Run the season review on the stored plan (after saving `plan` if given). |
| seriesId | string | yes | A series id from list_series. |
No output schema declared.
No examples provided.
select_character_image Select a character image ~114
Choose which character sheet a series uses and which of its images is the main one. The main image is the reference every still of an episode is made from. Only your own READY sheets and their images can be chosen. Free. Requires the "video:create" scope.
| Name | Type | Req | Description |
|---|---|---|---|
| assetId | string | – | An image id of that sheet to make the main image. Omit to keep the current main image. |
| seriesId | string | yes | – |
| sheetId | string | yes | A sheet id from get_character_sheet. |
No output schema declared.
No examples provided.
update_draft Update a draft ~118
Change a draft: its title and/or REPLACE all its scenes (1-12, each with scriptText and optional visualPrompt / durationSeconds). The narration you send is exactly what is spoken. To change one scene use revise_scene. Edits are screened like any prompt. Free; works only while the draft has not been rendered. Requires the "video:create" scope.
| Name | Type | Req | Description |
|---|---|---|---|
| draftId | string | yes | – |
| scenes | array | – | The complete new scene list (replaces the old one). |
| title | string | – | – |
No output schema declared.
No examples provided.
update_series Update a series ~279
Change a series: how often it runs, YouTube auto-post, the madeForKids answer or the language. Only the fields you pass change. The name and niche cannot be changed (create a new series). Making an ACTIVE series run more often raises its spend, so it goes through the same credit check as resume_series. Creating or changing a series is FREE. While active, the scheduler makes one video every scheduleIntervalDays (the first at its next run, within about 30 minutes) and charges each video like any video, 40 credits with the default render, at render time. It needs at least 40 credits in the balance: when the balance cannot pay for the next video the scheduler PAUSES the series (it never overdraws), so create_series and resume_series refuse with SERIES_NEEDS_CREDITS instead of making a series that would never run. Agents may keep at most 5 series active at once (SERIES_LIMIT_REACHED). StoryShort has no per-key daily spending cap: pause_series is the brake. Requires the "video:create" scope.
| Name | Type | Req | Description |
|---|---|---|---|
| autoPostYouTube | boolean | – | – |
| language | string | – | – |
| madeForKids | boolean | – | – |
| scheduleIntervalDays | integer | – | – |
| seriesId | string | yes | Series id (or slug) from list_series. |
No output schema declared.
No examples provided.
How do I install the StoryShort MCP server?
StoryShort is a hosted endpoint at https://storyshort.app/api/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · storyshort.app
claude mcp add --transport http app-storyshort-storyshort 'https://storyshort.app/api/mcp'
What is the StoryShort MCP server?
StoryShort is an MCP server listed in the public MCP registry as app.storyshort/storyshort. Make faceless AI short videos from a story idea: script, voiceover, captions, scenes. This page covers its hosted endpoint (https://storyshort.app/api/mcp).
Is the StoryShort MCP server safe to use?
StoryShort scores 78 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the StoryShort MCP server expose?
StoryShort exposes 34 tools: create_video, get_video, list_videos, list_niches, get_credit_balance, and 29 more. Their descriptions and schemas cost roughly 10,263 tokens of context every time the server is loaded.
Does the StoryShort MCP server require authentication?
Yes. StoryShort asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.
Is the StoryShort MCP server still maintained?
StoryShort is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What did VerifyMCP test on the StoryShort MCP server?
VerifyMCP ran 13 checks on StoryShort, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.