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.

Cuttr AI Video Editing

REMOTE · SKILLS.GETCUTTR.COM

26 AI video editors for Claude: raw phone take in, finished Reel, TikTok or Short out.

64 Trust /100

Last scanned (21 hours ago)

Scores higher than 46% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Design and Media

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 Security63
Transport & Reachability100
Schema Quality & AI Usability68
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 1180 tokens (~84/item across 14 items; 14 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management17
  • Stability observed for 5 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage87
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 61% of tool parameters carry a description.Partial
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "report_problem" implies "send" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 15 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
  • Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
What we tested

Checks we ran (12)

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

Checks we could not complete (1)

These are gaps on our side, not findings about this hosted endpoint. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • Authorization in Endpoint SecurityAuthorisation not fully verified: no authorisation is required to call this server, and 8 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.

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 +1

    No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

  • 19 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.

  • 17 Nov 26 +1
    • Stability: unverified → 0.03 ▲ functional
  • 16 Nov 26 61

    First indexed and scored.

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://skills.getcuttr.com/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=*.getcuttr.com CN=YR2,O=Let's Encrypt,C=US 25 Oct 2026 23 Jan 2027 RSA 2048 SHA256-RSA 6d2e2ed2ed30b69ab874f9b049970f6e1c4
SANs: *.getcuttr.com, getcuttr.com
CN=YR2,O=Let's Encrypt,C=US (CA) CN=Root YR,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 RSA 2048 SHA256-RSA 4ebd24947e24d394802d84a52fd5b319
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 insecure

Validation of skills.getcuttr.com. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
com. DS published 19718 13 Verified
getcuttr.com. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
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
content-security-policy frame-ancestors 'none'; base-uri 'self'; object-src 'none'
x-content-type-options nosniff
x-frame-options DENY
referrer-policy strict-origin-when-cross-origin
permissions-policy camera=(), microphone=(), geolocation=(), payment=(), usb=()

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

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://skills.getcuttr.com/mcp Verified 200
http (plaintext) http://skills.getcuttr.com/mcp HTTPS enforced 308 https://skills.getcuttr.com/mcp
MCP tools · 14 exposed · ~1,014 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
add_video_link ~80

When the member pastes the Instagram, TikTok or YouTube link of a video they posted, record it. Cuttr reads its public view count after 1, 7 and 30 days. Without video_id it attaches to their latest video that has no link yet.

NameTypeReqDescription
urlstringyes–
video_idstring––

No output schema declared.

No examples provided.

doctor ~56

A checklist to run on this computer for Cuttr skills (ffmpeg, Python, Node, Whisper, connectors), with the fix for each missing piece. Pass a slug to check only what that skill needs.

NameTypeReqDescription
slugstring––

No output schema declared.

No examples provided.

forget ~40

Deletes one saved style note by its id (ids are in get_profile). Use when the member says a preference no longer applies.

NameTypeReqDescription
idstringyes–

No output schema declared.

No examples provided.

get_bundle ~56

A download link (valid 15 minutes) for a skill's scripts and templates as a zip. Only call it when the skill's instructions say to. Download with curl and unzip where the instructions say.

NameTypeReqDescription
slugstringyes–

No output schema declared.

No examples provided.

get_profile ~45

This member's saved style notes, how their own posted videos did against their usual views (winners and misses), and their niche. Call it before planning any edit and apply it.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_skill ~64

The current full instructions for one Cuttr skill. Follow them exactly, as if they were the skill file. Call this every time the skill runs: it is always the latest version.

NameTypeReqDescription
slugstringyesThe skill's slug, e.g. remake-any-reel

No output schema declared.

No examples provided.

list_skills ~38

Every editor in Cuttr AI Video Editing: slug, name, what it makes, what it needs, and whether this member has it unlocked.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

log_video ~146

Call once after handing over a finished video. Records which editor made it, its hook and look, so Cuttr can learn from how it does once it is posted.

NameTypeReqDescription
hookstring–The opening line or on-screen hook
length_snumber–Length in seconds
platformstring––
run_idstring–The run_id given at the end of the editor's instructions
slugstringyesThe editor's slug
stylestring–The look in a few words, e.g. bold captions, punch-ins, animated lists
titlestring–What the video is about, a few words

No output schema declared.

No examples provided.

rate_video ~84

When log_video asks you to: the member's 1 to 5 answer to "How did this video turn out?", with their words. A low score reaches the Cuttr team, who help them the same day.

NameTypeReqDescription
commentstring–What they said about it, in their words
scoreintegeryes–
video_idstringyes–

No output schema declared.

No examples provided.

remember ~101

Saves one lasting preference of this member (e.g. "captions always bigger", "never black and white") so every future edit applies it. One short line. Not for one-off notes about a single video.

NameTypeReqDescription
notestringyesThe preference in one short line, in plain words
slugstring–The editor it came from, if any
sourcestring–import = copied from ~/.cuttr/BRAND.md

No output schema declared.

No examples provided.

report_problem ~132

Sends a problem to the Cuttr AI team, who reply by email. Include the exact error text and the step that failed. Never include API keys, passwords or tokens.

NameTypeReqDescription
errorstring–The exact error text
run_idstring–The run_id given at the end of the editor's instructions, if any
slugstring––
stepstring–Which step of the skill failed
summarystringyesOne line: what went wrong
systemstring–OS, tool (Claude Code, Codex, Claude app) and versions

No output schema declared.

No examples provided.

set_niche ~108

Saves the member's niche. One of: business (Business and marketing), ai-tech (AI and tech), coaching (Coaching and personal growth), health (Health and wellness), fitness (Fitness), beauty-fashion (Beauty and fashion), food (Food and cooking), parenting (Parenting and family), money (Money and finance), travel-lifestyle (Travel and lifestyle), education (Education and how-to), entertainment (Comedy and entertainment), other (Something else).

NameTypeReqDescription
nichestringyes–

No output schema declared.

No examples provided.

setup_step ~50

Only when the cuttr-test instructions say so: tells the member's setup page that the test edit finished.

NameTypeReqDescription
secondsnumber–How long the test edit took
stepstringyes–

No output schema declared.

No examples provided.

whats_new ~14

Recent new skills and updates.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

Install

How do I install the Cuttr AI Video Editing MCP server?

Cuttr AI Video Editing is a hosted endpoint at https://skills.getcuttr.com/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 · skills.getcuttr.com

# add to Claude Code
claude mcp add --transport http com-getcuttr-cuttr 'https://skills.getcuttr.com/mcp'
Common questions

What is the Cuttr AI Video Editing MCP server?

Cuttr AI Video Editing is an MCP server listed in the public MCP registry as com.getcuttr/cuttr. 26 AI video editors for Claude: raw phone take in, finished Reel, TikTok or Short out. This page covers its hosted endpoint (https://skills.getcuttr.com/mcp).

Is the Cuttr AI Video Editing MCP server safe to use?

Cuttr AI Video Editing scores 64 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 Cuttr AI Video Editing MCP server expose?

Cuttr AI Video Editing exposes 14 tools: list_skills, get_skill, get_bundle, doctor, report_problem, and 9 more. Their descriptions and schemas cost roughly 1,014 tokens of context every time the server is loaded.

Does the Cuttr AI Video Editing MCP server require authentication?

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

Is the Cuttr AI Video Editing MCP server still maintained?

Cuttr AI Video Editing 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 Cuttr AI Video Editing MCP server?

VerifyMCP ran 12 checks on Cuttr AI Video Editing, covering TLS certificate, HTTPS, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about Cuttr AI Video Editing: Authorization. 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.