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.

openmode

NPM · OPENMODE

Video editing and rendering for coding agents: look at footage, render edits to MP4, keep versions.

Available components

+4 this week 72 Trust /100

Last scanned (44 minutes ago)

Scores higher than 44% 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
  • 30 of 92 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability61
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 1437 tokens (~205/item across 7 items; 7 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 Management30
  • Stability observed for 9 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage99
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 97% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 7 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 8 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.

  • 22 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

  • 20 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 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.

  • 16 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.

  • 14 Nov 26 +15
    • Malware scan: unverified → pass ▲ security
    • Schema quality: 185 → 205 ▼ functional
    • Stability: unverified → 0.03 ▲ functional
    • Package version: 0.1.1 → 0.2.0 functional
  • 13 Nov 26 53

    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 22 Nov 2026 · Analysed npm/openmode@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 30
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 7 exposed · ~1,176 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
edit_schema ~30

The format of the edit file render_edit reads, with an example. Call once before writing your first edit.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

look ~196

See a video, an image or a folder of frames. Returns one contact sheet (evenly spaced frames, each labelled with its timestamp) and facts: duration, size, fps, loudness in LUFS, silent stretches, black stretches, missing frames. Use it before editing footage and after every render to check your own work. Pass `at` for one full-size frame, or `start`/`end` to look closer at a stretch.

NameTypeReqDescription
atnumber–Return one full frame at this second.
endnumber–Look up to this second.
framesinteger–Tiles on the sheet. Default 12.
outstring–Also save the sheet here (.jpg).
pathstringyesVideo file, image file, or folder of numbered frames.
quickboolean–Skip sound and black-frame analysis.
startnumber–Look from this second.

No output schema declared.

No examples provided.

render_blender ~295

Render a .blend file, or a Python script that builds a scene with bpy, to an MP4 using the Blender installed on this machine. quality draft is small (360p), low-sample and may skip frames so you can check the scene in seconds; look at it, then render final at the scene's own size and samples. Returns the MP4 path, duration, size, renderer and frame count. Needs Blender; status says if it is installed.

NameTypeReqDescription
allowScriptsboolean–Let Python stored inside the .blend run. Off by default.
audiostring–Soundtrack file to lay under the film.
filestringyesA .blend file or a .py scene script.
loudnessnumber–Target loudness in LUFS, e.g. -14.
outstring–Output .mp4 path. Default: renders/<name>-<quality>.mp4 next to the scene.
qualitystring–draft = fast and small, to check your work; final = full quality.
rangestring–Frames to render, e.g. "1-48" or "12". Default: the scene's range.
rendererstring–Override the scene's renderer.
samplesinteger–Override samples per pixel.
stepinteger–Render every Nth frame; the film keeps its length.

No output schema declared.

No examples provided.

render_edit ~231

Render an edit file to an MP4 with the local ffmpeg. An edit lists clips in order (video or image, with trims, speed, volume, cut or fade), audio tracks (music, voiceover), timed captions, an end card and a target loudness. Call edit_schema once to see the format. Render with quality draft first, look at it, then final. Returns the MP4 path, duration, size and render time.

NameTypeReqDescription
baseDirstring–With `edit`: the folder clip paths are relative to. Default: the working directory.
edit––Or the edit object itself, instead of a file.
filestring–Path to the edit JSON file. Clip paths inside are relative to this file. Preferred.
outstring–Output .mp4 path. Default: renders/<name>-<quality>.mp4 next to the edit file.
qualitystring–draft = fast and small, to check your work; final = full quality.
validateOnlyboolean–Check the edit and report the timeline without rendering.

No output schema declared.

No examples provided.

render_frames ~152

Join a folder of numbered image frames (frame_0001.png ...) into an MP4, with an optional soundtrack. Use it for a headless-browser capture or any renderer that writes frames. Reports missing frame numbers instead of producing a broken film.

NameTypeReqDescription
audiostring–Soundtrack file to lay under the frames.
dirstringyesFolder of numbered frames.
fpsnumber–Frames per second. Default 24.
loudnessnumber–Target loudness in LUFS, e.g. -14.
outstring–Output .mp4 path.
qualitystring–draft = fast and small, to check your work; final = full quality.

No output schema declared.

No examples provided.

status ~44

Check that ffmpeg is installed, whether Blender is, and which features work here (hardware encoder, captions). Call it if a render fails for a reason that is not the edit.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

versions ~228

Version history for the film folder (the working directory, or `dir`). save records every file with a message and the prompt that led to it; unchanged footage is stored once. list shows the history. restore puts the folder back to a version: unsaved work is saved first and the restore becomes a new version, so nothing is ever lost. diff shows which files changed between two versions (or a version and now), with a line diff for text files such as the edit.

NameTypeReqDescription
actionstringyes–
dirstring–Film folder. Default: the working directory.
fromstring–diff: older version, e.g. v2.
idstring–restore: the version to go back to, e.g. v3.
messagestring–save: what changed, in one line.
modelstring–save: the model that made it.
promptstring–save: the user's request that led to this version.
tostring–diff: newer version, or "current" (default).

No output schema declared.

No examples provided.

Install

How do I install the openmode MCP server?

openmode runs locally as an npm package, launched with npx -y openmode 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 · openmode

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

What is the openmode MCP server?

openmode is an MCP server listed in the public MCP registry as io.github.shansabnani/openmode. Video editing and rendering for coding agents: look at footage, render edits to MP4, keep versions. This page covers its npm package (openmode).

Is the openmode MCP server safe to use?

openmode scores 72 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 22 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 openmode MCP server expose?

openmode exposes 7 tools: look, render_edit, render_frames, render_blender, versions, and 2 more. Their descriptions and schemas cost roughly 1,176 tokens of context every time the server is loaded.

Is the openmode MCP server still maintained?

openmode is still listed as active in the MCP registry. We last reached this channel on 22 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 openmode MCP server under?

openmode 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 openmode MCP server?

VerifyMCP ran 16 checks on openmode, 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.