# Tsiky (npm · @captain_americka/tsiky-mcp)

Turn your photo into a cartoon character and make animated explainer videos, step by step

- Trust score: 65/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- npm · `@captain_americka/tsiky-mcp`: 65/100 (this document), [markdown](https://verifymcp.io/servers/erickarazafimbahiny-ux-tsiky/captain-americka-tsiky-mcp.md), [page](https://verifymcp.io/servers/erickarazafimbahiny-ux-tsiky/captain-americka-tsiky-mcp)

## Channel facts

- Registry: `npm`
- Package: `@captain_americka/tsiky-mcp`
- Version: `1.0.2`
- Transport: `stdio`

## Trust breakdown

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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 30 of 94 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 19/100
  - Repository check failed: no source repository is declared.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (ISC).
  - Actively maintained (last published 2 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 63/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 2150 tokens (~97/item across 22 items; 22 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 81/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 43% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 22 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 23 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Tsiky MCP server?

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

### Claude

```bash
claude mcp add erickarazafimbahiny-ux-tsiky -- npx -y @captain_americka/tsiky-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "erickarazafimbahiny-ux-tsiky": {
      "command": "npx",
      "args": [
        "-y",
        "@captain_americka/tsiky-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "erickarazafimbahiny-ux-tsiky": {
      "command": "npx",
      "args": [
        "-y",
        "@captain_americka/tsiky-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add erickarazafimbahiny-ux-tsiky -- npx -y @captain_americka/tsiky-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "erickarazafimbahiny-ux-tsiky": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@captain_americka/tsiky-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add erickarazafimbahiny-ux-tsiky --command npx --arg -y --arg @captain_americka/tsiky-mcp
```

### Hermes

```yaml
mcp_servers:
  erickarazafimbahiny-ux-tsiky:
    command: "npx"
    args: ["-y", "@captain_americka/tsiky-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "erickarazafimbahiny-ux-tsiky": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@captain_americka/tsiky-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add erickarazafimbahiny-ux-tsiky -t stdio -c npx -a -y @captain_americka/tsiky-mcp
```

### Other

```json
{
  "mcpServers": {
    "erickarazafimbahiny-ux-tsiky": {
      "command": "npx",
      "args": [
        "-y",
        "@captain_americka/tsiky-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-05 (score 65, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-03 (score 64, +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.

### 2026-11-01 (score 63, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-30 (score 62, +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.

### 2026-10-29 (score 61, 0)

- [security regression] Stability: 0.00 → unverified
- [security regression] Tool safety: pass → unverified
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified
- [functional] Package version: 1.0.1 → 1.0.2

### 2026-10-28 (score 61)

First indexed and scored.

## MCP tools (22)

### `create_project` (~102 tokens)

Create a video project

Start a new video. Step 1 (scenario) opens right away.

Input parameters:

- `format` (string)
- `language` (string): Language of voice and captions, e.g. "en" (default) or "fr".
- `targetSeconds` (integer)
- `title` (string, required): Working title, e.g. "Meta Muse explained"
- `tone` (string)
- `topic` (string, required): What the video is about and for whom.

### `list_projects` (~16 tokens)

List video projects

List existing projects, most recent first.

### `get_project` (~28 tokens)

Project status

Show where a project stands and what the next step is.

Input parameters:

- `projectId` (string, required)

### `validate_stage` (~40 tokens)

Validate a step

Lock in a step after the USER explicitly approved it. Unlocks the next step.

Input parameters:

- `projectId` (string, required)
- `stage` (string, required)

### `write_script` (~62 tokens)

Write the scenario

Store the full scenario, scene by scene (replaces any previous version). Returns a readable version to show the user.

Input parameters:

- `projectId` (string, required)
- `scenes` (array, required)
- `sources` (array): URLs used for the facts in the script.

### `update_scene` (~60 tokens)

Edit one scene

Change one scene of the scenario without touching the others.

Input parameters:

- `changes` (object, required): Only the fields to change; everything else stays as it is.
- `projectId` (string, required)
- `sceneId` (string, required): e.g. "s3"

### `get_script` (~24 tokens)

Show the scenario

Readable version of the current scenario.

Input parameters:

- `projectId` (string, required)

### `create_character` (~132 tokens)

Create the character from a photo

Build the cartoon character. Look at the user photo and describe ONLY what is visible: hair length/style/color, fringe, glasses and frame style/color/pattern, skin tone, top style/color, button color. Do not invent traits. Returns a character sheet image.

Input parameters:

- `name` (string, required): The person's first name, shown on the sheet.
- `notes` (string): Details you noticed that traits cannot express yet (they guide future versions).
- `photoPath` (string): Local path to the uploaded photo (copied into the project).
- `projectId` (string, required)
- `traits` (object, required)

### `update_character` (~51 tokens)

Adjust the character

Change some traits (partial update, e.g. {"hair":{"style":"bob"}}) and get a new character sheet.

Input parameters:

- `changes` (object, required): Partial traits object.
- `projectId` (string, required)

### `preview_character` (~27 tokens)

Character sheet

Render the current character sheet (5 expressions and poses).

Input parameters:

- `projectId` (string, required)

### `set_brand` (~413 tokens)

Visual identity (optional step)

Set the visual identity the whole video follows. Every field is optional; call it again to change only some fields. If the user shares a logo, a brand guide or their website colours, read the colours from it and fill them in. Bundled fonts: Bricolage Grotesque (sans-serif), Caveat (handwritten), DM Sans (sans-serif), DM Serif Display (serif), Fraunces (serif), Inter (sans-serif), Lora (serif), Montserrat (sans-serif), Nunito (sans-serif), Playfair Display (serif), Poppins (sans-serif), Space Grotesk (sans-serif). Or pass a font file path (woff2, woff, ttf, otf). Colours: bg = page background, surface/surface2 = shapes and panels, card = cards and bubbles, accent/accentDeep = highlights, ink = titles, text = body text, muted = small text.

Input parameters:

- `bodyFont` (string): Bundled font name or path to a font file.
- `captionStyle` (string): pill = rounded bubble, bar = accent band, plain = bold text only.
- `colors` (object)
- `corners` (string)
- `headingFont` (string): Bundled font name or path to a font file.
- `logo` (string): Path to the logo image (PNG with transparency or SVG works best). Use "" to remove it.
- `logoPlacement` (string): Corner tag in every scene (logo, or series name if there is no logo).
- `outro` (object): Added to the closing card: @handle, website, call to action.
- `pattern` (string): Subtle background pattern.
- `projectId` (string, required)
- `seriesName` (string): Name shown on title cards and in the corner tag, e.g. a series or brand name.
- `shape` (string): Shape drawn behind the character.
- `textCase` (string)

### `preview_brand` (~47 tokens)

Brand board

Render the brand board: palette, fonts, logo and three frames of this video in that identity. Show it to the user before validate_stage "brand".

Input parameters:

- `projectId` (string, required)

### `preview_scene` (~66 tokens)

Preview one scene

Render one frame of one scene, at any step (a placeholder character is used until the character is made). Use it to check a drawn decor or a layout before the storyboard.

Input parameters:

- `projectId` (string, required)
- `sceneId` (string, required): e.g. "s3"

### `find_icons` (~63 tokens)

Find icons

Search the icon set (Lucide, about 2,000 line icons) by keyword, to use in scene "icons" or column "icon".

Input parameters:

- `query` (string, required): One or more keywords, e.g. "money", "calendar time", "security"

### `render_storyboard` (~54 tokens)

Storyboard (key images)

Render one key image per scene with the validated script and character, assembled into a storyboard board. Pass sceneIds to re-render only some scenes.

Input parameters:

- `projectId` (string, required)
- `sceneIds` (array)

### `list_voices` (~15 tokens)

Available voices

List the local synthetic voices.

### `generate_voice` (~152 tokens)

Generate the voice

Synthesize the narration of every scene (or only sceneIds). Each scene is said in its voiceTone (pitch, pace, energy, pauses, breaths and timbre), with *stressed* words and ... hesitations from the narration. Returns a voice-only preview. To change how one line sounds: update_scene with voiceTone or markup, then generate_voice with sceneIds.

Input parameters:

- `expressiveness` (number): 0 = flat reading, 1 = very expressive.
- `projectId` (string, required)
- `sceneIds` (array)
- `speed` (number)
- `voice` (string): See list_voices. Default: an English female voice (a French one for French projects).

### `use_recording` (~57 tokens)

Use the user's own voice

Replace the voice of one scene with a recording made by the user (any audio format). The mouth animation follows the recording.

Input parameters:

- `path` (string, required)
- `projectId` (string, required)
- `sceneId` (string, required)

### `choose_music` (~251 tokens)

Choose the music

Build the music bed and the full mix. With a voice-over, the music ducks under the voice. With voiceOver false, the video has background music only: no narration, the character does not speak and the narration stays on screen as captions. Moods: pop = Bright pop played on real recorded instruments (acoustic guitar, piano, bass, real drums); acoustic = Warm acoustic on real instruments (fingerpicked guitar, piano, shaker); lofi = Soft lo-fi (electric piano, round bass, light drums); piano = Calm piano, no drums; upbeat = Bright and light (nylon guitar, claps); halloween = Playful Halloween music box (celesta, A minor, no drums); none = No music, voice only.

Input parameters:

- `mood` (string, required)
- `projectId` (string, required)
- `soundEffects` (boolean): Real sound effects on the animation: whooshes on transitions, pops when items appear, a chime on the title and end cards. Default on.
- `voiceOver` (boolean): false = background music only, no voice-over. true = switch back to a voice-over (generate_voice first). Omit to keep the current choice.

### `preview_audio` (~24 tokens)

Play the full mix

Return the current voice + music mix.

Input parameters:

- `projectId` (string, required)

### `render_video` (~39 tokens)

Render the final video

Start rendering the final video in the background (needs steps 1 to 4 validated). Poll get_render_status.

Input parameters:

- `projectId` (string, required)

### `get_render_status` (~30 tokens)

Render progress

Progress of the final render; returns the video path when done.

Input parameters:

- `projectId` (string, required)

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/erickarazafimbahiny-ux-tsiky/captain-americka-tsiky-mcp#diagnostics

## Score history

- 2026-11-05: 65
- 2026-11-04: 64
- 2026-11-03: 64
- 2026-11-02: 63
- 2026-11-01: 63
- 2026-10-31: 62
- 2026-10-30: 62
- 2026-10-29: 61
- 2026-10-28: 61

## Common questions

### What is the Tsiky MCP server?

Tsiky is an MCP server listed in the public MCP registry as io.github.erickarazafimbahiny-ux/tsiky. Turn your photo into a cartoon character and make animated explainer videos, step by step. This page covers its npm package (@captain_americka/tsiky-mcp).

### Is the Tsiky MCP server safe to use?

Tsiky scores 65 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 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 Tsiky MCP server expose?

Tsiky exposes 22 tools: create_project, list_projects, get_project, validate_stage, write_script, and 17 more. Their descriptions and schemas cost roughly 1,753 tokens of context every time the server is loaded.

### Is the Tsiky MCP server still maintained?

Tsiky is still listed as active in the MCP registry. We last reached this channel on 5 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 Tsiky MCP server under?

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

## Links

- npm package: https://www.npmjs.com/package/@captain_americka/tsiky-mcp
- Socket report: https://socket.dev/npm/package/@captain_americka/tsiky-mcp
- Changelog RSS feed: https://verifymcp.io/servers/erickarazafimbahiny-ux-tsiky/captain-americka-tsiky-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/erickarazafimbahiny-ux-tsiky/captain-americka-tsiky-mcp.json
- HTML version of this page: https://verifymcp.io/servers/erickarazafimbahiny-ux-tsiky/captain-americka-tsiky-mcp