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.

Dinoctor

NPM · DINOCTOR-MCP

Direct animated videos in the free Dinoctor app: scenes, cast, camera, voice, music, render.

Available components

67 Trust /100

Last scanned (18 hours ago)

Scores higher than 38% of npm servers

Category Design and Media

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security98
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 31 of 92 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability60
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 13666 tokens (~248/item across 55 items; 55 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 Management0
  • Stability check failed: the tool surface changed between 0.1.0 and 0.2.0: 26 tool removals, 1 breaking changes, 12 additions. See how to fix → Fail
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
  • Structured output schemas are declared (7% 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
  • All 3 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
  • An AI judge read all 56 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
What we tested

Checks we ran (16)

  • Malware scan
  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Security disclosure
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

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.

  • 19 Nov 26 −2
    • Stability: 0.10 → fail ▼ security
    • Schema quality: 193 → 248 ▼ functional
    • First check of Tool coverage: 7 functional
    • Schema quality: excellent → good functional
    • Package version: 0.1.1 → 0.2.0 functional
  • 17 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

  • 16 Nov 26 +18
    • Malware scan: unverified → pass ▲ security
    • Schema quality: 150 → 193 ▼ functional
    • Tool coverage: 57% → 100% ▲ functional
    • Stability: unverified → 0.03 ▲ functional
    • Schema quality: good → excellent functional
    • Destructive annotations: All 3 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation. functional
    • Package version: 0.1.0 → 0.1.1 functional
  • 15 Nov 26 50

    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 · Analysed npm/dinoctor-mcp@0.2.0

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Dependencies 92 packages
Packages resolved 92
Stale 31
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 55 exposed · ~13,530 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
sound_effects ~398

Dinoctor's automatic sound effects (from the style's sound pack, worked out from what happens in each shot). Film-wide: on, volume, room tone. One shot: shot_on, shot_volume, and one sound by its event key: event_on, pick another sound, own_path (the person's own file), gain, nudge, reset. Call with just the shot (shot_id, or scene + shot) to list that shot's sounds and their event keys (no change). One undo step per change. For music use music; for any other sound file use upload as sound.

NameTypeReqDescription
eventstring–One sound's event key, from the list.
event_onboolean–That sound on or off.
gainnumber–That sound's volume in dB.
nudgenumber–Frames earlier (-) or later (+).
onboolean–Film-wide: sound effects on or off.
own_pathstring–Full path of the person's own sound file to use for that event.
pickstring–Another sound from that event's choices.
resetboolean–true: that sound back to automatic.
roomboolean–Film-wide: quiet room tone under everything.
sceneinteger–Scene index from 0 (with shot). Used when shot_id isn't given.
shot––Shot index from 0 inside that scene (with scene; alone: in the scene on screen). A shot id works here too.
shot_idstring–A shot's id (or give scene and shot). With only this, lists the shot's sounds.
shot_onboolean–This shot's sound effects on or off.
shot_volumenumber–This shot's volume in dB.
volumenumber–Film-wide volume in dB, -18 to 6.

No output schema declared.

No examples provided.

speak ~227

Make the voice for script lines with ElevenLabs, with the time of every word, and give it to the shots that speak each line (captions follow the words; shots fit the voice unless fit is false). Spends the person's ElevenLabs characters: the first call (without confirm) returns the cost and what's left; ask, then call again with confirm: true. Default: every line without a voice, in the film's voice. Returns what was made and characters left. For the person's own recording (free), use own_voice.

NameTypeReqDescription
againboolean–Make the voice again even for lines that have one.
confirmboolean–true only after the person agreed to the cost.
fitboolean–Shots get the voice's length (default true).
linesarray–Line ids from script with action get. Default: every line without a voice.
modelstring–Default eleven_multilingual_v2. Flash and turbo cost half.
voicestring–An ElevenLabs voice id (voices). Default: the film's voice.

No output schema declared.

No examples provided.

status ~64

Quick read-only check: is Dinoctor open, the project's style and format, how many scenes and shots, and which shot is on screen (id and indexes). Returns { open: false, note } when the app is closed. For every scene and shot, use get_project.

Input schema present but exposes no named parameters.

NameTypeReqDescription
formatstring––
notestring––
openboolean––
scenesnumber––
shotsnumber––
showingobject––
stylestring––

No examples provided.

style_job ~661

Build, fix and follow the person's own art styles: Claude Code runs inside Dinoctor and does the work. Only one style job runs at a time. action build: start a brand-new style from words and/or example pictures (name, words, files), the same as "Build your own style". Claude Code runs inside Dinoctor on this computer and builds the style in code: it plans the look, draws characters, objects and places, writes the style, runs the app's tests, checks a test shot and makes the pictures. Usually about 30 minutes (longer for a detailed 3D style), and it uses a lot of the person's own Claude usage (a smaller plan can hit its limit). Nothing is paid to Dinoctor. The person can keep working, and style_job with action cancel stops it at any time. Claude first writes a plan; when status shows status plan, show it to the person and answer it with action continue. action fix: ask Claude to fix a problem (words) in one of the person's own finished styles (id), like Fix a problem (about 10 minutes of their Claude usage); the style stays as it was until the fix passes. action continue: answer a new style's plan (build it, or send change to rework it), or resume a build or fix that stopped part way (status says canContinue: true). build, fix and continue use the person's Claude usage, so the first call only says what will happen; ask, then call again with the same arguments and confirm: true. action status (read-only unless close: true, which clears a finished job from Dinoctor's screen): status (running, plan, done, failed, cancelled), step, what Claude does now, minutes so far and left, tokens, errors. action cancel: stops the running job; the person's styles stay as they were. When done, use_style switches to it and rate_style records how it went.

NameTypeReqDescription
actionstringyesbuild a new style, fix one, continue a plan or a stopped job, cancel the running job, or get its status.
changestring–continue, when status shows a plan: what the person wants changed. With it, Claude rewrites the plan instead of building.
closeboolean–status: clear a finished, failed or cancelled job from Dinoctor's screen.
confirmboolean–build, fix, continue: true starts it (uses the person's Claude usage). Only after the person said yes.
filesarray–build: full paths of pictures or short videos on this computer that show the look (up to 25 MB each). They show Claude far more than words.
idstring–fix: The person's own style id from my_styles (built-in styles can't be used here).
namestring–build: the style's name, up to 30 characters.
use_project_filesboolean–build: also send the files already added in Dinoctor's Build your own box.
wordsstring–build: the look (characters, world, mood, lettering), needed unless files are sent. fix: what's wrong, in plain words.

No output schema declared.

No examples provided.

templates ~157

The person's templates (saved whole projects to start from), like Dinoctor's Templates page. action list (read-only), save (name: saves the project as it is now), open (id: replaces the open project with the template; one undo step brings it back), delete (id: for good, needs confirm: true after the person agrees). For .dino project files use open_project / save_project; for shot recipes use samples.

NameTypeReqDescription
actionstringyesWhat to do (see the description).
confirmboolean–For delete: true only after the person agreed.
idstring–A template id from list (open, delete).
namestring–For save: the template's name.

No output schema declared.

No examples provided.

upload ~372

Bring a file from this computer into the project, like the app's upload. Pictures (PNG/JPG/WebP/GIF/SVG): as media, character or object (joins a shot's cast or replaces a member's picture), or background. Videos (MP4/MOV/WebM): as media, video-background or video-front in a shot. Sounds (MP3/WAV/M4A...): as sound (sound Media, and on the timeline at `at` if given), music, or voice. Default: media for pictures and videos, sound for sounds. The file is copied into Dinoctor; the original isn't changed. One undo step. For pictures made before with Higgsfield, use put_picture.

NameTypeReqDescription
asstring–How it goes into the project (see the description).
atnumber–For as: sound, seconds into the film to place it on a free sound line.
namestring–A short name for it in the project.
pathstringyesFull path of the file on this computer.
replacestring–A cast member id in that shot whose picture this replaces.
sceneinteger–Scene index from 0 (with shot). Used when shot_id isn't given.
shot––Shot index from 0 inside that scene (with scene; alone: in the scene on screen). A shot id works here too.
shot_idstring–The shot's id from get_project. Or give scene and shot instead. Left out: the shot on screen.
sound_kindstring–For as: sound, what it is (guessed from the name and length otherwise).
trimboolean–For a character/object picture: cut its empty see-through edges (default true).

No output schema declared.

No examples provided.

use_style ~123

Switch the project to another art style, a built-in id (list_styles) or one of the person's own (my_styles). Every shot is rebuilt in the new style: its characters, objects and places are replaced; words, cameras and timing stay. One undo step, and no confirm step, so ask the person first if the project has work. A style built since Dinoctor opened makes the window reload once. For built-in styles with a confirm step, set_style does the same.

NameTypeReqDescription
idstringyesA style id from list_styles or my_styles.

No output schema declared.

No examples provided.

voices ~85

List the ElevenLabs voices in the person's own account (id, name, what it sounds like), read-only. With pick: a voice id becomes the film's voice for speak (one undo step). Needs ElevenLabs connected (see generator_account). Making voices costs characters: that's speak.

NameTypeReqDescription
pickstring–A voice id from the list to make it the film's voice.

No output schema declared.

No examples provided.

Install

How do I install the Dinoctor MCP server?

Dinoctor runs locally as an npm package, launched with npx -y dinoctor-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · dinoctor-mcp

# add to Claude Code
claude mcp add dinoctor-dinoctor-mcp -- npx -y dinoctor-mcp
Common questions

What is the Dinoctor MCP server?

Dinoctor is an MCP server listed in the public MCP registry as io.github.Dinoctor/dinoctor-mcp. Direct animated videos in the free Dinoctor app: scenes, cast, camera, voice, music, render. This page covers its npm package (dinoctor-mcp).

Is the Dinoctor MCP server safe to use?

Dinoctor scores 67 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. It declares no install or post-install scripts. 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 Dinoctor MCP server expose?

Dinoctor exposes 55 tools: open_dinoctor, status, get_project, get_shot, go_to, and 50 more. Their descriptions and schemas cost roughly 13,530 tokens of context every time the server is loaded.

Is the Dinoctor MCP server still maintained?

Dinoctor 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 licence is the Dinoctor MCP server under?

Dinoctor declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

What did VerifyMCP test on the Dinoctor MCP server?

VerifyMCP ran 16 checks on Dinoctor, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.