Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Shorti

REMOTE · SHORTI.AI · 2 COMPONENTS

What short-form formats to shoot this week, how their hits were made, and a check of your take.

+6 this week 82 Trust /100

Last scanned (17 hours ago)

Scores higher than 81% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Marketing and SEO

Trust breakdown (7 categories)

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 Security83
  • The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
  • No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation. See how to fix → View diagnostics → Partial
  • HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
  • The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
  • DNSSEC is configured correctly; the domain's records validate against the full chain to the root. View diagnostics → Pass
Transport & Reachability100
Schema Quality & AI Usability74
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (fair).Partial
  • Context-footprint check failed: tool/resource definitions use about 1999 tokens (~117/item across 17 items; 6 tools + 11 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 Management57
  • Stability check failed: schema churn in the 30 days we've observed: 3 tool removals, 0 breaking changes, 0 auth/transport breaks, 2 additions. See how to fix → Fail
Tool Coverage92
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 73% of tool parameters carry a description.Partial
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
  • Supports UI / widget rendering.Pass
What we tested

Checks we ran (14)

  • TLS certificate
  • Authorization
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol
  • Capabilities

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 →

Changelog

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.

  • 21 Nov 26 0
    • Server version: 04a9268b98786d2837c195442a918688b8a0aa1d → a30718e63e1fbd9edabed3af2d5463b26511d5a1 functional
  • 20 Nov 26 0
    • Server version: 00f09a0e870c13220b309bc3108f4779aafec1cc → 04a9268b98786d2837c195442a918688b8a0aa1d functional
  • 19 Nov 26 +6
    • Tool “shorti_what_to_shoot” rewrote its description, which is the text the model reads security
    • Server version: 2dacc7b1838ec030682cbc39cdaf7b4ed09c242c → 00f09a0e870c13220b309bc3108f4779aafec1cc functional
    • “shorti_what_to_shoot” reworded the description of “lens” cosmetic
  • 18 Nov 26 0
    • Server version: d51a147def556a865b718d9e2549ce52f7ff5fd6 → 2dacc7b1838ec030682cbc39cdaf7b4ed09c242c functional
  • 17 Nov 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “shorti_how_to_shoot” rewrote its description, which is the text the model reads security
    • Tool “shorti_read” rewrote its description, which is the text the model reads security
    • Tool “shorti_what_to_shoot” rewrote its description, which is the text the model reads security
    • Server version: 07fb999dbdb08acd70c82ba4a1da1f8bfdd80180 → d51a147def556a865b718d9e2549ce52f7ff5fd6 functional
    • “shorti_how_to_shoot” reworded the description of “detail” cosmetic
    • Tool “shorti_how_to_shoot” changed its title: How it was shot → The move behind a hit cosmetic
  • 16 Nov 26 0
    • Server version: 9850605e5bae66aed0b357f95328a98ec33f223e → 07fb999dbdb08acd70c82ba4a1da1f8bfdd80180 functional
  • 15 Nov 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Server version: 1788bfbbfd753a57442a2f57f6fef586f896aabc → 9850605e5bae66aed0b357f95328a98ec33f223e functional
    • New tool “shorti_read” functional
  • 14 Nov 26 0
    • Server version: 1f3c795362cb6919e43f5b23b84c9dd9233a4dfe → 1788bfbbfd753a57442a2f57f6fef586f896aabc functional
Diagnostics

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://shorti.ai/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=shorti.ai CN=YR1,O=Let's Encrypt,C=US 19 Nov 2026 17 Feb 2027 RSA 2048 SHA256-RSA 59550453f222990d7c84c425ce12e5354ec
SANs: shorti.ai
CN=YR1,O=Let's Encrypt,C=US (CA) CN=Root YR,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 RSA 2048 SHA256-RSA a20253f15f2691c05dc1ce13b9bcca4e
CN=Root YR,O=ISRG,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 RSA 4096 SHA256-RSA f24b6d17f9d9ad7cb1c9fea78782699f

Background: What to check on a remote MCP endpoint →

DNSSEC secure

Validation of shorti.ai. — Secure

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
ai. DS published 1814 8 Verified
shorti.ai. DS published 7692 13 Verified
shorti.ai. Verified address RRset verified with the apex keys
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=63072000; includeSubDomains
content-security-policy frame-ancestors 'self'
x-content-type-options nosniff
x-frame-options SAMEORIGIN
referrer-policy strict-origin-when-cross-origin
permissions-policy camera=(self), microphone=(self), geolocation=(self)

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://shorti.ai/mcp Verified 200
http (plaintext) http://shorti.ai/mcp HTTPS enforced 308 https://shorti.ai/mcp
MCP tools · 6 exposed · ~1,301 tokens

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 →

Tool Tokens
shorti_arena ~147

Shorti(쇼티) for «what has nobody shot yet?» or «아직 아무도 안 찍은 거 뭐 있어?». The arena's open spots, first recorded takes, later breakouts and entrant standings. view='spots': open spots, their words, dates and how to shoot; 'board': first takes and finds; 'entrant': one entrant's standing. Unread: not_run, never an empty board.

NameTypeReqDescription
cursorstring––
entrantstring––
kindstring––
langstring––
limitinteger––
lineagestring––
viewstring––
NameTypeReqDescription
as_ofnull|string–when the data was compiled
boardarray|null––
countnull|object–the rows shown, over the rows the filters keep
descendantsnull|object––
entrantnull|string––
hintnull|string––
langnull|string––
memesnull|object–each meme the page's spots open, by id: its row
namesnull|object–the opted-in entrants' names beside the rows, read live
next_cursornull|string–the next page's cursor; none on the last page
notenull|string––
reasonnull|string––
refusalnull|string–why nothing was answered, by name
refusednull|object–published rows that failed the arena's own contract, counted
rowsnull|object–an entrant's rows, over every row the filters keep
rows_with_descendantsnull|object––
spotsarray|null––
statenull|string–published; not_run or refused with `reason`
totalnull|object–the rows the filters keep, over all published rows
viewnull|string–spots, board or entrant

No examples provided.

shorti_check ~210

Shorti(쇼티) for «check my take», «내가 찍은 거 봐줘», «내 피드백 보여줘» or «내 결과 공유해줘». The person's own video checked against its format's hits. `url` (a posted Reels, TikTok or Short): the page on Shorti to paste it on. `upload`: their own file, on that page. `token`: their summary, once they send it to this chat. Its feedback (피드백): a likeness is not a forecast of views.

NameTypeReqDescription
formatstring–A format_id to check against.
langstring–'en': Shorti's own English.
recipe_refstring–A recipe's recipe_ref.
tokenstring–The token a previous call gave.
uploadboolean–Their own file (shot, edited or generated).
urlstring–Their posted Reels, TikTok or Shorts link.

Structured output declared, but exposes no named fields.

No examples provided.

shorti_how_to_shoot ~263

Shorti(쇼티) for a TikTok, Reels or Shorts link with «how was this shot?», «이 영상 어떻게 찍었어?», «나도 이렇게 찍으려면?» or «분석해줘». One video's move, who else made it and the person's version, then how it was shot. `url` or `video_id`: also its hook, beats and numbers (not_in_corpus: not read yet). `format_id`: its plan and hits. `part`: plan, flow (how it moved; `lineage`), scene (where the phone stood).

NameTypeReqDescription
cursorstring––
detailstring–Leave it out: the default answers the person. full: Shorti's raw fields in pages, only when they ask for the data.
format_idstring–A format's id or its page's slug.
langstring–'en': Shorti's own English.
lineagestring–A lineage's id (lin_…).
partstring–Which answer about it.
urlstring–The post's link.
video_idstring–Shorti's id of the video.
NameTypeReqDescription
as_of––When the release these rows were read from was compiled.
format––That format, with its format_id.
formats––The formats it is in, each with its format_id.
hits––The format's strongest videos, each with its video_id.
how_to_shoot––Its reference hit step by step on its own clock, what to keep and what to change.
line––part=flow: the lineage's line.
note––What the numbers mean.
setups––part=scene: where the phone stood in each set-up.
state––Why it holds none of the above, where it does not.
video––That video, with its video_id: what happens, its hook, beats and numbers.
video_id––Shorti's id of the video a scene or plan is about.

No examples provided.

shorti_read ~160

Shorti(쇼티) for a pasted TikTok, Reels or Shorts link, or a Shorti link, with «read this» or «이 영상 읽어줘». One video's page whole: its move, who else made it and the person's version, then each stop: what happens, what viewers said there, the shot's set-up. `url`: the post's or a Shorti link. Each second links its page there. not_in_corpus: not read yet. `cursor`: a long page's next part.

NameTypeReqDescription
cursorstring––
langstring–'en': Shorti's own English.
urlstringyesThe post's link, or its page's on Shorti.
NameTypeReqDescription
as_of––When the release these rows were read from was compiled.
formats––The formats it is in, each with its format_id.
hint––What to do next, or what could not be read just now.
note––What the numbers mean.
pages––A long page comes in parts: this part, how many, and the cursor of the next.
state––Why it holds none of the above, where it does not (not_in_corpus: not read yet).
template––The meme it belongs to: its moves, and where this video keeps them.
video––The video, with its video_id and its numbers; `read`: its page line by line, each second a link that opens the page there.

No examples provided.

shorti_recipe ~261

Shorti(쇼티) for «how do I make this?» or «이거 어떻게 만들어?». A hit made their way: their clips to its clock, their AI video model or a 3D generator. `kind`: edit (their editor), remake (their video model: `mode`, `model`), scene (a 3D generator).

NameTypeReqDescription
canvasstring–The frame; a remake's 16:9 or pov (3:4) needs mode 'episode'.
cursorstring––
detailstring–full: every field, paged.
format_idstring–A format_id.
kindstring–Which recipe or edit.
langstring–'en': Shorti's own English.
modestring–What a remake changes.
modelstring–Their AI video model.
movesarray–A mosaic cut's moves, for a cut on them.
personastring–A remake's persona: anyone, in words.
productstring–A shop's product line.
urlstring–The hit's link.
video_idstring–The hit's video_id.

Structured output declared, but exposes no named fields.

No examples provided.

shorti_what_to_shoot ~260

Shorti(쇼티) for «what should I shoot this week?», «이번 주 뭐 찍지?», «find videos of…» or «… 영상 찾아줘». Today's rising hits and this week's ideas, each with its move, who else made it and a twist; from the West, or by their taste. `about`: a field, product, niche or @handle (Korean initials work). `category` narrows it ('food'). `lens`: radar (the West first).

NameTypeReqDescription
aboutstring–Their words: a profession, team, shop or field (피부과, 카페, 브랜드팀), a product, a niche, an action or an @handle.
categorystring–The creator's niche, when they have one.
cursorstring––
langstring–'en': Shorti's own English; never translate its Korean.
lensstring–radar: formats breaking out in the West no Korean video holds yet.
limitinteger––
platformstring–Only formats with videos on this platform.
statestring–With radar: none in Korea yet, or the first ones.
NameTypeReqDescription
as_ofnull|string–when the data was compiled
for_youboolean|null–true when a signed-in reader's own week leads the list
formatsarray|null––
hintnull|string––
left_outnull|object–at an address whose host limits one answer's size: how many rows of each list did not fit, by the list's name; each list says its first rows
nonenull|object––
notenull|string––
refusalnull|string–why nothing was answered, by name
todayarray|null–today's rising hits, newest first, the asker's side first
weeknull|string–the Monday (KST) the week's picks are fixed on

No examples provided.

Install

How do I install the Shorti MCP server?

Shorti is a hosted endpoint at https://shorti.ai/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 · shorti.ai

# add to Claude Code
claude mcp add --transport http ai-shorti-shorti 'https://shorti.ai/mcp'
Common questions

What is the Shorti MCP server?

Shorti is an MCP server listed in the public MCP registry as ai.shorti/shorti. What short-form formats to shoot this week, how their hits were made, and a check of your take. This page covers its hosted endpoint (https://shorti.ai/mcp).

Is the Shorti MCP server safe to use?

Shorti scores 82 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 Shorti MCP server expose?

Shorti exposes 6 tools: shorti_what_to_shoot, shorti_how_to_shoot, shorti_read, shorti_recipe, shorti_check, shorti_arena. Their descriptions and schemas cost roughly 1,301 tokens of context every time the server is loaded.

Does the Shorti MCP server require authentication?

No. We connected to Shorti without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the Shorti MCP server still maintained?

Shorti 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 Shorti MCP server?

VerifyMCP ran 14 checks on Shorti, covering TLS certificate, Authorization, HTTPS, HSTS header and 10 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.