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.

Envie

NPM · @GOLPRODUCTIONS/ENVIE · SCANNED SEP 26

Your AI writes HTML; Envie renders it to video on your machine, verifies it and shows it back.

68 Trust /100
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 Security100
  • 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
  • No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency32
Schema Quality & AI Usability78
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 648 tokens (~129/item across 5 items; 5 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 not yet verified: not enough scan history yet (needs a 30-day window).Unverified
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
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 5 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

Unverified: 1 category

A category scored 0 because we could not verify it: 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 Envie MCP server?

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

npm · @golproductions/envie

# add to Claude Code
claude mcp add com-golproductions-envie -- npx -y @golproductions/envie
// .cursor/mcp.json
{
  "mcpServers": {
    "com-golproductions-envie": {
      "command": "npx",
      "args": [
        "-y",
        "@golproductions/envie"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "com-golproductions-envie": {
      "command": "npx",
      "args": [
        "-y",
        "@golproductions/envie"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add com-golproductions-envie -- npx -y @golproductions/envie
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-golproductions-envie": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@golproductions/envie"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add com-golproductions-envie --command npx --arg -y --arg @golproductions/envie
# ~/.hermes/config.yaml
mcp_servers:
  com-golproductions-envie:
    command: "npx"
    args: ["-y", "@golproductions/envie"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "com-golproductions-envie": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@golproductions/envie"
      ]
    }
  }
}
# add to Vellum
assistant mcp add com-golproductions-envie -t stdio -c npx -a -y @golproductions/envie
// mcp.json
{
  "mcpServers": {
    "com-golproductions-envie": {
      "command": "npx",
      "args": [
        "-y",
        "@golproductions/envie"
      ]
    }
  }
}
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.

  • 25 Sept 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 24 Sept 26 68

    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 26 Sept 2026 · Analysed npm/@golproductions/envie@0.8.9

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 0 packages
Packages resolved 0
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 5 exposed · ~648 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
envie_guide ~36

Read this FIRST. Returns the authoring contract: how to write a composition HTML file that Envie can render into a verified video.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

envie_render ~261

Render a composition HTML file into an MP4 video with optional voiceover, then machine-verify it (6 gates: container, streams, silence, black frames, freezes, dead endings). Returns the verification report and output path. Only use after reading envie_guide.

NameTypeReqDescription
audio_pathstring–Absolute path to an audio file (wav/mp3/m4a) to lay over the video. Works on every platform, and takes priority over narration. This is how you supply sound on macOS and Linux, where local TTS is una…
formatstring–Delivery codec, default h264 (.mp4). prores/prores4444/dnxhr require a .mov out_path. h265 is 10-bit.
fpsnumber–Frames per second, default 24
html_pathstringyesAbsolute path to the composition HTML file
narrationstring–Voiceover script, spoken over the video using local TTS. WINDOWS ONLY. On macOS or Linux use audio_path instead. Videos with no audio at all fail verification (G2/G3).
out_pathstringyesAbsolute path for the output MP4
voicestring–Optional TTS voice name hint

No output schema declared.

No examples provided.

envie_see ~151

LOOK at your work. Returns actual frames (as images) from a composition HTML or a rendered MP4 at chosen timestamps. Use this to visually inspect layout, text readability, overlaps, and scene composition with your own eyes, then fix the composition and render again. The verification gates prove a video is alive; envie_see is how you judge whether it is good. Default: frames at 0%, 25%, 50%, 75%, 95% of the timeline.

NameTypeReqDescription
pathstringyesAbsolute path to a composition .html or a rendered .mp4
timestamps_msarray–Timeline positions in milliseconds to capture (max 12). Omit for the default five.

No output schema declared.

No examples provided.

envie_translate ~157

HEAR and MEASURE your work. Reads a finished video back as data you can act on without eyes or ears: per-frame motion, every cut, still holds, integrated loudness (LUFS), true peak, every audio transient, and how far each audio hit sits from the nearest cut in milliseconds. envie_see shows you stills and is blind between them; envie_translate measures motion and sound across the whole file. Use it after envie_render to judge pacing and audio sync, then fix the composition and render again.

NameTypeReqDescription
out_dirstring–Optional directory for the receipt assets (keyframes, spectrogram, timeline strip, contact sheet, HTML report)
video_pathstringyesAbsolute path to the rendered video

No output schema declared.

No examples provided.

envie_verify ~43

Run the 6 Envie verification gates against any existing MP4 and get the pass/fail report.

NameTypeReqDescription
video_pathstringyesAbsolute path to the MP4

No output schema declared.

No examples provided.

Common questions

What is the Envie MCP server?

Envie is an MCP server listed in the public MCP registry as com.golproductions/envie. Your AI writes HTML; Envie renders it to video on your machine, verifies it and shows it back. This page covers its npm package (@golproductions/envie).

Is the Envie MCP server safe to use?

Envie scores 68 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 26 September 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 Envie MCP server expose?

Envie exposes 5 tools: envie_guide, envie_render, envie_verify, envie_see, envie_translate. Their descriptions and schemas cost roughly 648 tokens of context every time the server is loaded.

Is the Envie MCP server still maintained?

Envie is still listed as active in the MCP registry. We last reached this channel on 26 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.