# io.github.farssaadeldin7-ux/code-to-visual-interpreter (mcpb · code-to-visual-interpreter.mcpb)

Translate between generative code and the geometry it produces, keeping output assets lean...

- Trust score: 36/100 (low)
- Change this week: 0
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- mcpb · `code-to-visual-interpreter.mcpb`: 36/100 (this document), [markdown](https://verifymcp.io/servers/farssaadeldin7-ux-code-to-visual-interpreter/code-to-visual-interpreter.md), [page](https://verifymcp.io/servers/farssaadeldin7-ux-code-to-visual-interpreter/code-to-visual-interpreter)

## Channel facts

- Registry: `mcpb`
- Package: `https://github.com/farssaadeldin7-ux/claude-plugin-suite/releases/download/mcpb-v0.1.3/code-to-visual-interpreter.mcpb`
- Version: `0.1.3`
- Transport: `stdio`
- SHA-256: `8459807b1b7504830a940c3b1c3ddfedf3ae09a08224cd7dd11d8df8f45bf82d`

## 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**: 0/100
  - No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.
  - Known CVEs could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none).
  - Install-script risk not yet assessed.
  - Dependency health could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none).
- **Provenance & Transparency**: 32/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - License check failed: no license is declared.
  - Actively maintained (last published 15 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 82/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1774 tokens (~126/item across 14 items; 14 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% 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 14 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 15 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 20/100
  - Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28.

**Unverified: 2 categories.** Categories scored 0 because we could not verify them: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the io.github.farssaadeldin7-ux/code-to-visual-interpreter MCP server?

io.github.farssaadeldin7-ux/code-to-visual-interpreter ships as an MCPB bundle, a single file you download and open in an MCP host that supports MCPB bundles, such as Claude Desktop. The host reads the launch command from the bundle's own manifest, so there is no command to copy. Before opening it, check the file's SHA-256 matches the one the MCP registry declares for it, 8459807b1b7504830a940c3b1c3ddfedf3ae09a08224cd7dd11d8df8f45bf82d; the commands to do that are on this page. If it does not match, do not open it.

- Download bundle: `https://github.com/farssaadeldin7-ux/claude-plugin-suite/releases/download/mcpb-v0.1.3/code-to-visual-interpreter.mcpb`
- SHA-256: `8459807b1b7504830a940c3b1c3ddfedf3ae09a08224cd7dd11d8df8f45bf82d`

### Verify on macOS / Linux

```bash
echo "8459807b1b7504830a940c3b1c3ddfedf3ae09a08224cd7dd11d8df8f45bf82d  code-to-visual-interpreter.mcpb" | shasum -a 256 -c
```

### Verify on Windows (PowerShell)

```powershell
(Get-FileHash -Algorithm SHA256 .\code-to-visual-interpreter.mcpb).Hash -eq "8459807b1b7504830a940c3b1c3ddfedf3ae09a08224cd7dd11d8df8f45bf82d"
```

## 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.

### 2026-10-21 (score 36)

First indexed and scored.

## MCP tools (14)

### `decomposition_taxonomy` (~92 tokens)

The decomposition tables: the ten structures with their visual signatures and core parameters, the seven modulations, the surface decisions, the discrimination tests, the five questions to ask of any image, and three worked decompositions. Lookup only — it does not look at an image. Omit layer to get everything.

Input parameters:

- `layer` (string): Optional single section: structure, modulation, surface, tests, questions or examples.

### `toolchain_notes` (~105 tokens)

Per-library notes for p5.js, three.js, GLSL, SVG, Canvas 2D, WebGL/WebGPU, D3 and Processing: what each is good at, its determinism story, and the bloat trap it reliably leads people into. Omit toolchain to list all of them.

Input parameters:

- `toolchain` (string): p5js, threejs, glsl, svg, canvas2d, webgl_webgpu, d3 or processing.

### `edge_conditions` (~65 tokens)

The degenerate-parameter table for reading generative code: what actually happens when noise frequency hits zero, alpha drops below the 8-bit floor, a radius exceeds half the grid spacing, a divisor reaches zero, and five more. Lookup only — it has not read any code.

### `structure_match` (~194 tokens)

Filter the structure table by answers to the five questions — placement, spacing, whether neighbours are similar, the largest and smallest visual scales. Returns every structure consistent with the answers, the modulation class the neighbours answer implies, and the octave estimate. Mechanical filtering on stated signatures: it narrows candidates, it does not identify a piece, and it has not seen the image. Requires a paid plan.

Input parameters:

- `largest_scale` (number): Size of the largest visual blob, any consistent unit.
- `neighbours` (string): Adjacent elements: "similar" or "unrelated".
- `placement` (string): Do elements sit on a lattice, flow along paths, or neither: "lattice", "paths" or "neither".
- `smallest_scale` (number): Size of the smallest detail that is not just an edge, same unit.
- `spacing` (string): "constant", "gradient" or "clustered".

### `cost_budget` (~177 tokens)

Place an element count against the switch-point table: the technology band it falls in, the per-technology arithmetic (SVG style recalculation, Canvas 2D call overhead batched and unbatched, WebGL draw calls, per-frame allocation), and — if a technology is stated — which side of its ceiling the count sits. Table lookup and multiplication only: it is not a profiler and every figure carries ±3x. Requires a paid plan.

Input parameters:

- `animated` (boolean): True if the piece animates. Static exports stretch further. Default false.
- `elements` (number, required): Elements drawn per frame (animated) or in the output (static). Multiply nested loops out first.
- `technology` (string): Optional current technology to check against its ceiling: svg, canvas2d, webgl, p5, d3_dom.

### `svg_export_budget` (~159 tokens)

Estimate SVG path-data size from point count and coordinate precision, at every precision level, raw and gzipped — plus the Ramer-Douglas-Peucker epsilon and typical point reduction for a stated use case. Arithmetic from the byte table only: markup overhead is extra and the real file is larger. Requires a paid plan.

Input parameters:

- `elements` (number): Optional element count, for the parse/layout band and the size wins.
- `points` (number, required): Total path points across the export.
- `precision` (string): Coordinate precision: "full", "6", "3" (default) or "integer".
- `use_case` (string): Optional, for the RDP epsilon: zoomable_or_print, standard_web or background_texture.

### `source_scan` (~126 tokens)

Line-by-line textual scan of pasted source for the determinism markers (Math.random, the GLSL sin hash, global noiseDetail, which seeding calls are present) and the known bloat-trap calls (createGraphics, shadowBlur, getImageData, loadPixels, save/restore). Every finding quotes its line. Not a parse: it cannot see aliased calls or tell which loop a call sits in, and it has not run or rendered anything. Requires a paid plan.

Input parameters:

- `source` (string, required): The source to scan — the actual code, including line breaks.

### `render_preview` (~268 tokens)

Turn supplied CSS, Canvas 2D or GLSL source into one self-contained interactive HTML file: the code running in a stage, one slider per extracted parameter (numeric literals attached to named constants — CSS custom properties, JS const/let/var, GLSL const and #define — plus detected GLSL float uniforms), live updates, and a copyable JSON block of the current values that feeds straight into apply_params. A canvas2d source must define draw(ctx, params, t); anything else is refused with the expected shape, never guessed at. The preview is a harness, not the user's environment. Requires a paid plan.

Input parameters:

- `code` (string, required): The source itself. css: the stylesheet, animations included. canvas2d: JS defining draw(ctx, params, t). glsl: a WebGL1 fragment shader; the harness supplies uniforms "resolution" (vec2) and "time" (…
- `html` (string): css only: optional markup snippet for the stage. Defaults to a single square subject element.
- `kind` (string, required): What the code is: "css", "canvas2d" or "glsl".
- `out_path` (string): Where to write the HTML file. Defaults to ./cvi-preview.html.

### `apply_params` (~171 tokens)

Deterministically rewrite named constants' numeric literals in supplied source — the write-back half of render_preview's loop: values copied from the preview's JSON block feed straight in here. Handles CSS custom properties, JS const/let/var and GLSL const/#define declarations; units and float-ness are preserved. Any name that does not resolve to exactly one literal fails the whole call and nothing is rewritten — it never rewrites a guess. Returns the updated code and each change as old, new and line. Requires a paid plan.

Input parameters:

- `code` (string, required): The source to rewrite — the same code the preview was generated from.
- `params` (object, required): Parameter name to new numeric value, e.g. {"SPEED": 2.5} — the shape of the preview's JSON block.

### `license_status` (~52 tokens)

Check the Code-to-Visual Interpreter licence on this machine: plan, included capabilities, remaining quota and seat usage. Call this when a paid tool reports a licence problem, or when the user asks what their plan includes.

### `license_activate` (~69 tokens)

Store and activate a Code-to-Visual Interpreter licence key on this machine. Use when the user pastes a licence key, or after a purchase completes.

Input parameters:

- `license_key` (string, required): The licence key, e.g. PS-XXX-00000-00000-00000-0000

### `start_checkout` (~76 tokens)

Begin a Code-to-Visual Interpreter purchase. Returns a Stripe Checkout link. Call list_plans first if the user has not chosen a plan.

Input parameters:

- `email` (string): Email address for the receipt and licence.
- `plan` (string, required): Plan id: "pro" or "team". Use list_plans to see the options.

### `list_plans` (~26 tokens)

List the available Code-to-Visual Interpreter plans, prices and what each one includes.

### `billing_portal` (~32 tokens)

Open the Stripe billing portal to change plan, update the card, or cancel the Code-to-Visual Interpreter subscription.

## Diagnostics

Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/farssaadeldin7-ux-code-to-visual-interpreter/code-to-visual-interpreter#diagnostics

## Score history

- 2026-11-05: 36
- 2026-11-04: 36
- 2026-11-03: 36
- 2026-11-02: 36
- 2026-11-01: 36
- 2026-10-31: 36
- 2026-10-30: 36
- 2026-10-29: 36
- 2026-10-28: 36
- 2026-10-27: 36
- 2026-10-26: 36
- 2026-10-25: 36
- 2026-10-24: 36
- 2026-10-23: 36
- 2026-10-22: 36
- 2026-10-21: 36

## Common questions

### What is the io.github.farssaadeldin7-ux/code-to-visual-interpreter MCP server?

io.github.farssaadeldin7-ux/code-to-visual-interpreter is an MCP server listed in the public MCP registry as io.github.farssaadeldin7-ux/code-to-visual-interpreter. Translate between generative code and the geometry it produces, keeping output assets lean... This page covers its MCPB bundle (https://github.com/farssaadeldin7-ux/claude-plugin-suite/releases/download/mcpb-v0.1.3/code-to-visual-interpreter.mcpb).

### Is the io.github.farssaadeldin7-ux/code-to-visual-interpreter MCP server safe to use?

io.github.farssaadeldin7-ux/code-to-visual-interpreter scores 36 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 io.github.farssaadeldin7-ux/code-to-visual-interpreter MCP server expose?

io.github.farssaadeldin7-ux/code-to-visual-interpreter exposes 14 tools: decomposition_taxonomy, toolchain_notes, edge_conditions, structure_match, cost_budget, and 9 more. Their descriptions and schemas cost roughly 1,612 tokens of context every time the server is loaded.

## Links

- Repository: https://github.com/farssaadeldin7-ux/claude-plugin-suite
- Changelog RSS feed: https://verifymcp.io/servers/farssaadeldin7-ux-code-to-visual-interpreter/code-to-visual-interpreter.xml
- Changelog JSON feed: https://verifymcp.io/servers/farssaadeldin7-ux-code-to-visual-interpreter/code-to-visual-interpreter.json
- HTML version of this page: https://verifymcp.io/servers/farssaadeldin7-ux-code-to-visual-interpreter/code-to-visual-interpreter