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.

mcp-video

PYPI · MCP-VIDEO · SCANNED SEP 21

Compatibility package: mcp-video now installs Kinocut (formerly mcp-video).

Available components

+18 this week 75 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
  • Runs hatchling.build at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
  • 1 of 34 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency35
Schema Quality & AI Usability77
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 21532 tokens (~109/item across 197 items; 196 tools + 1 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 Management70
  • Stability observed for 21 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage73
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 7% of tool parameters carry a description.Partial
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety78
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 1 of 10 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "video_acceptance_eval" implies "eval" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Partial
  • An AI judge read all 198 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
Install

How do I install the mcp-video server?

mcp-video runs locally as a PyPI package, launched with uvx mcp-video. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

pypi · mcp-video

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

  • 20 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

  • 16 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

  • 15 Sept 26 +15
    • Malware scan: unverified → pass security
  • 14 Sept 26 −14
    • Malware scan: pass → unverified security
  • 11 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

  • 9 Sept 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.

  • 7 Sept 26 +4
    • Stability: unverified → 0.23 functional
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 Sept 2026 · Analysed pypi/mcp-video@1.6.12

Provenance No attestation

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

Result No attestation
Ecosystem pypi

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend allowlisted hatchling.build

Background: Why install scripts are a supply-chain risk →

Dependencies 34 packages
Packages resolved 34
Stale 1
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 196 exposed · ~21,443 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
video_quality_check ~80

Run visual quality checks on a video. Analyzes brightness, contrast, saturation, audio levels, and color balance. Returns quality scores and recommendations. Args: input_path: Absolute path to video file fail_on_warning: If True, treat warnings as failures

NameTypeReqDescription
fail_on_warningboolean
input_pathstringyes

Structured output declared, but exposes no named fields.

No examples provided.

video_read_metadata ~41

Read metadata tags from a video/audio file. Args: input_path: Absolute path to the video or audio file.

NameTypeReqDescription
input_pathstringyes

Structured output declared, but exposes no named fields.

No examples provided.

video_recipe_capture ~38

Capture a workflow recipe (writer); idempotent by canonical digest.

NameTypeReqDescription
project_dirstringyes
recipeobjectyes

Structured output declared, but exposes no named fields.

No examples provided.

video_release_checkpoint ~78

Create preview artifacts only after the video passes quality gates. Use this before publishing or chaining more polish effects. It runs a hard quality gate, then writes a thumbnail and storyboard for human inspection.

NameTypeReqDescription
frame_countinteger
input_pathstringyes
min_scorenumber
output_dir

Structured output declared, but exposes no named fields.

No examples provided.

video_remote_egress_plan ~33

Plan explicit remote egress and fake adapter receipts without network I/O.

NameTypeReqDescription
requestobjectyes

Structured output declared, but exposes no named fields.

No examples provided.

video_repurpose ~127

Submit one durable projectstore repurpose job for platform clips. ``min_score`` is accepted for signature parity with sync ``repurpose`` and is **not applied**. Durable jobs do not run ``assert_quality``. Use CLI/Client ``repurpose`` (default 80) for the fail-closed ship seam.

NameTypeReqDescription
include_release_checkpointboolean
input_pathstringyes
min_scorenumber
moment_selection_record_id
output_dir
platforms
start_jobboolean

Structured output declared, but exposes no named fields.

No examples provided.

video_repurpose_plan ~43

Create a dry-run local repurposing manifest for platform-ready assets.

NameTypeReqDescription
input_pathstringyes
output_dir
platforms

Structured output declared, but exposes no named fields.

No examples provided.

video_rescue_inspect ~30

Inspect a rescue plan or receipt and re-check artifact integrity.

NameTypeReqDescription
receiptstringyes

Structured output declared, but exposes no named fields.

No examples provided.

video_rescue_plan ~89

Analyze one local video and return a policy-classified rescue plan. Planning never changes the source or renders final media. It records findings, safe repair ids, recommendations, unavailable and blocked work, local capability evidence, previews, and an execution estimate.

NameTypeReqDescription
output_dirstringyes
policystring
save_plan
sourcestringyes

Structured output declared, but exposes no named fields.

No examples provided.

video_rescue_render ~105

Render approved safe repairs from a reviewed rescue plan. Approval ids must name safe repairs in this exact immutable plan. The renderer fails closed on stale inputs, capabilities, policy, resume state, cancellation, or verification failure and never promotes failed output.

NameTypeReqDescription
approved_repair_ids
cancel_file
keep_intermediatesboolean
planstringyes
resume_receipt
save_receipt

Structured output declared, but exposes no named fields.

No examples provided.

video_resize ~212

Resize a video or change its aspect ratio. Returns JSON {success, output_path}. Use to fit a video to target dimensions or a preset ratio. Pass input_path as the source video (e.g. from video_info) and either width/height or aspect_ratio to define the target. Args: input_path: Absolute path to the input video. width: Target width in pixels. Use with height. height: Target height in pixels. Use with width. aspect_ratio: Preset aspect ratio (16:9, 9:16, 1:1, 4:3, 4:5, 21:9). Overrides width/height. quality: Quality preset (low, medium, high, ultra). output_path: Where to save the output. Auto-generated if omitted.

NameTypeReqDescription
aspect_ratio
height
input_pathstringyes
output_path
qualitystring
width

Structured output declared, but exposes no named fields.

No examples provided.

video_restoration_plan ~27

Plan or evaluate evidence-gated local restorative work.

NameTypeReqDescription
requestobjectyes

Structured output declared, but exposes no named fields.

No examples provided.

video_reverse ~60

Reverse video and audio playback so it plays backwards. Args: input_path: Absolute path to the input video. output_path: Where to save the output. Auto-generated if omitted.

NameTypeReqDescription
input_pathstringyes
output_path

Structured output declared, but exposes no named fields.

No examples provided.

video_review_decide ~74

Record human accept/reject/revise. Accept + EDL approval can render (N4).

NameTypeReqDescription
approval
decisionstringyes
edl
input_path
output_path
reasonstring
review_runobjectyes

Structured output declared, but exposes no named fields.

No examples provided.

video_review_decision ~40

Record a human review decision (writer); corrections supersede by record id.

NameTypeReqDescription
decisionobjectyes
project_dirstringyes

Structured output declared, but exposes no named fields.

No examples provided.

video_review_package ~47

Assemble a review package and publish-gate verdict for a candidate artifact.

NameTypeReqDescription
blocking_findings
candidate_artifactstringyes
project_dirstringyes

Structured output declared, but exposes no named fields.

No examples provided.

video_review_run ~35

Watching guardrail: run offline metric floor under a review policy.

NameTypeReqDescription
input_pathstringyes
policy

Structured output declared, but exposes no named fields.

No examples provided.

video_review_ui ~31

Write hot-reloading human review HTML surface (P4.3).

NameTypeReqDescription
output_dirstringyes

Structured output declared, but exposes no named fields.

No examples provided.

video_rotate ~145

Rotate and/or flip an existing video and render a new output file. Supports right-angle rotations plus horizontal and vertical flips; the input video is not modified.

NameTypeReqDescription
angleintegerClockwise rotation angle in degrees. Supported values are 0, 90, 180, and 270.
flip_horizontalbooleanMirror the video horizontally after rotation when true.
flip_verticalbooleanMirror the video vertically after rotation when true.
input_pathstringyesAbsolute path to an existing local video file. The input file is read only.
output_pathDestination video path. Auto-generated when omitted; an existing supplied path may be overwritten.

Structured output declared, but exposes no named fields.

No examples provided.

video_salvage ~70

Create one lineage-bound salvage derivative and a fresh review slot.

NameTypeReqDescription
acceptance_spec_idstringyes
authorization_decision_ids
policyobjectyes
project_dirstringyes
recipestringyes
source_asset_idstringyes

Structured output declared, but exposes no named fields.

No examples provided.

video_seek_frame ~37

Frame-accurate seek conversion (TE.9).

NameTypeReqDescription
fpsnumber
frame
seconds

Structured output declared, but exposes no named fields.

No examples provided.

video_semantic_query ~28

Query source-backed semantic spans locally without inventing descriptions.

NameTypeReqDescription
requestobjectyes

Structured output declared, but exposes no named fields.

No examples provided.

video_semantic_timeline ~31

Build a local, source-time semantic timeline from supplied analyzer evidence.

NameTypeReqDescription
requestobjectyes

Structured output declared, but exposes no named fields.

No examples provided.

video_shape_mask ~105

Apply a geometric shape mask to a video. Args: input_path: Absolute path to the input video. shape: Shape to use — "circle", "rounded_rect", or "oval". output_path: Where to save the output. Auto-generated if omitted. feather: Feather radius in pixels (0 = sharp edges).

NameTypeReqDescription
featherinteger
input_pathstringyes
output_path
shapestring

Structured output declared, but exposes no named fields.

No examples provided.

video_speed ~148

Render a new video with playback speed changed; the source video is left unchanged. Returns JSON {success, output_path}. Use for slow-motion or fast-forward effects. Pass input_path as the source video and factor as the multiplier (below 1.0 slows, above 1.0 speeds up).

NameTypeReqDescription
factornumberPlayback speed multiplier. 2.0 is double speed, 0.5 is half speed, and 1.0 is unchanged.
input_pathstringyesAbsolute path to an existing local video file. The input file is read only.
output_pathDestination video path. Auto-generated when omitted; an existing supplied path may be overwritten.

Structured output declared, but exposes no named fields.

No examples provided.

video_split_screen ~101

Place two videos side by side or top/bottom. Args: left_path: Absolute path to the first video. right_path: Absolute path to the second video. layout: Layout type (side-by-side or top-bottom). output_path: Where to save the output. Auto-generated if omitted.

NameTypeReqDescription
layoutstring
left_pathstringyes
output_path
right_pathstringyes

Structured output declared, but exposes no named fields.

No examples provided.

video_stabilize ~108

Stabilize a shaky video using motion vector analysis. Args: input_path: Absolute path to the input video. smoothing: Smoothing strength (default 15, higher = more stable). zooming: Zoom percentage to avoid black borders (default 0). output_path: Where to save the output. Auto-generated if omitted.

NameTypeReqDescription
input_pathstringyes
output_path
smoothingnumber
zoomingnumber

Structured output declared, but exposes no named fields.

No examples provided.

video_storyboard ~81

Extract key frames and create a storyboard grid for human review. Args: input_path: Absolute path to the input video. output_dir: Directory to save frames. Auto-generated if omitted. frame_count: Number of key frames to extract.

NameTypeReqDescription
frame_countinteger
input_pathstringyes
output_dir

Structured output declared, but exposes no named fields.

No examples provided.

video_subtitles ~152

Burn subtitles (SRT/VTT/authored ASS) into a video. Args: input_path: Absolute path to the input video. subtitle_path: Absolute path to the subtitle file (.srt, .vtt, or .ass). output_path: Where to save the output. Auto-generated if omitted. style: Optional force_style override applied to any subtitle format including authored ASS (e.g. "FontSize=24,PrimaryColour=&H00FFFFFF"). Omit to preserve an authored ASS file's own styling/positioning.

NameTypeReqDescription
input_pathstringyes
output_path
style
subtitle_pathstringyes

Structured output declared, but exposes no named fields.

No examples provided.

video_subtitles_styled ~125

Burn subtitles from SRT/VTT with custom styling. Embeds subtitle file into video with customizable appearance. Args: input_path: Absolute path to input video. subtitles_path: Absolute path to SRT or VTT file. output_path: Absolute path for output video. style: Optional style dict with font, size, color, outline, etc. Returns: Dict with success status and output_path.

NameTypeReqDescription
input_pathstringyes
output_pathstringyes
style
subtitles_pathstringyes

Structured output declared, but exposes no named fields.

No examples provided.

video_template_preview ~197

Preview what a video template would do before rendering. Analyzes the template and returns a list of operations, estimated output duration, resolution, and file size — without actually processing any video. Args: template: Template name (tiktok, youtube-shorts, instagram-reel, youtube, instagram-post). input_path: Absolute path to the input video (optional; used for duration probing). duration: Override the estimated duration in seconds. caption: Caption text for TikTok / Instagram Reel / Instagram Post templates. title: Title text for YouTube Shorts / YouTube video templates. music_path: Absolute path to background music file. outro_path: Absolute path to outro video file (YouTube template only).

NameTypeReqDescription
caption
duration
input_path
music_path
outro_path
templatestringyes
title

Structured output declared, but exposes no named fields.

No examples provided.

video_text_animated ~225

Add animated text to video. Overlay text with animation effects (fade, slide, etc.). Args: input_path: Absolute path to input video. text: Text to display. output_path: Absolute path for output video. animation: Animation type (fade, slide-up, typewriter). Default fade. font: Font family. Default Arial. size: Font size. Default 48. color: Text color. Default white. position: Text position. Default center. start: Start time in seconds. Default 0. duration: Display duration. Default 3.0. Returns: Dict with success status and output_path.

NameTypeReqDescription
animationstring
colorstring
durationnumber
fontstring
input_pathstringyes
output_path
positionstring
sizeinteger
startnumber
textstringyes
typewriter_speednumber

Structured output declared, but exposes no named fields.

No examples provided.

video_thumbnail ~89

Extract a single frame (thumbnail / frame grab) from a video. Args: input_path: Absolute path to the input video. timestamp: Time in seconds to extract frame. Defaults to 10% of video duration. output_path: Where to save the frame image. Auto-generated if omitted.

NameTypeReqDescription
input_pathstringyes
output_path
timestamp

Structured output declared, but exposes no named fields.

No examples provided.

video_timeline_edit_plan ~34

Plan explicit or ordinary-person timeline edits as a reviewable EDL and diff.

NameTypeReqDescription
requestobjectyes

Structured output declared, but exposes no named fields.

No examples provided.

video_timeline_ir_validate ~53

Validate Timeline IR and compile to render DAG (P3.0). Semantic timelines (shots/silences/words) also get agent-visible ``text`` (N2).

NameTypeReqDescription
timelineobjectyes

Structured output declared, but exposes no named fields.

No examples provided.

video_translate_captions ~57

Translate SRT captions with honest language-coverage reporting (EN→ES first).

NameTypeReqDescription
input_pathstringyes
output_path
source_langstring
target_langstring

Structured output declared, but exposes no named fields.

No examples provided.

video_trim ~234

Trim a video clip by start time and duration. Returns JSON {success, output_path} pointing at the rendered clip. Use to cut a segment out of a longer video. Pass input_path as the absolute path to the source video (e.g. from video_info), start as a timestamp, and duration or end to define the segment. Args: input_path: Absolute path to the input video. start: Start timestamp (e.g. '00:02:15' or seconds as string like '10.5'). duration: Duration to keep (e.g. '00:00:30' or '30'). Exclusive with end. end: End timestamp. Exclusive with duration. output_path: Where to save the trimmed video. Auto-generated if omitted. accurate: Frame-accurate seeking (slower). Default False uses fast input seeking which may land on the nearest keyframe.

NameTypeReqDescription
accurateboolean
duration
end
input_pathstringyes
output_path
startstring

Structured output declared, but exposes no named fields.

No examples provided.

video_validate_text_layout ~150

Validate a set of text overlays for visual failure modes before rendering. Checks for: text overlap, low contrast, unsafe positioning, excessive sequential overlays, and missing shadows. Args: overlays: List of overlay specs with keys: text, position, size, color, shadow (optional), start_time (optional), duration (optional). video_width: Video width in pixels. video_height: Video height in pixels. background_color: Background hex color for contrast checking. Returns: dict with warnings list and clean boolean.

NameTypeReqDescription
background_colorstring
overlaysarrayyes
video_heightinteger
video_widthinteger

Structured output declared, but exposes no named fields.

No examples provided.

video_verdict ~36

Persist exact-asset analysis; approvals require active human evidence.

NameTypeReqDescription
project_dirstringyes
verdictobjectyes

Structured output declared, but exposes no named fields.

No examples provided.

video_visual_transform_plan ~32

Plan subject/camera analysis, reframing, or stabilization with crop budgets.

NameTypeReqDescription
requestobjectyes

Structured output declared, but exposes no named fields.

No examples provided.

video_watermark ~265

Overlay an image watermark onto an existing video and render a new output file. The video and watermark image are read only; output_path is created or overwritten. Supports named, pixel, and percentage positions plus opacity, margin, CRF, and preset controls.

NameTypeReqDescription
crfOptional FFmpeg CRF override from 0 to 51, where lower means higher quality.
image_pathstringyesAbsolute path to an existing local image file used as an overlay or watermark.
input_pathstringyesAbsolute path to an existing local video file. The input file is read only.
marginintegerNon-negative edge margin in pixels for named positions.
opacitynumberWatermark opacity from 0.0 fully transparent to 1.0 fully opaque.
output_pathDestination video path. Auto-generated when omitted; an existing supplied path may be overwritten.
positionWatermark position: named position such as bottom-right, pixel dict {"x": 100, "y": 50}, or percentage dict {"x_pct": 0.5, "y_pct": 0.5}.
presetOptional FFmpeg encoding preset: ultrafast, fast, medium, slow, or veryslow.

Structured output declared, but exposes no named fields.

No examples provided.

video_workflow_inspect ~242

Summarize any receipt this project emits, with a read-only integrity check. Reads a workflow render receipt, a dry-run ``workflow_plan`` artifact, or a ``layer_plan`` receipt (v1 legacy with NO ``receipt_kind`` field, or v2) at ``receipt_path`` and returns a NORMALIZED inspection: the kind (inferred from the ``tool`` field when ``receipt_kind`` is absent, per legacy tolerance), schema_version, tool, versions, a status summary (per-step statuses, failed step + error if any), a hash presence/integrity report (which recorded source/output hashes still match the bytes on disk NOW — a read-only re-check), outputs, warnings, cleanup state, plus human-review pointers and known limitations. Nothing is rendered or modified. A malformed/unreadable receipt fails closed with ``invalid_workflow_receipt``. Args: receipt_path: Absolute path to the receipt JSON file to inspect. compare_path: Optional second receipt; when set, also return a diff (N3).

NameTypeReqDescription
compare_path
receipt_pathstringyes

Structured output declared, but exposes no named fields.

No examples provided.

video_workflow_plan ~297

Produce a no-render plan for an agent workflow job-spec. Validates the spec first (fail-closed) and then builds a dry-run plan artifact WITHOUT rendering any media: the ordered operation graph, per-source ffprobe results (duration/resolution/codec) and sha256 content hashes where the source file exists, declared output intents, a variant-expansion summary, tool + FFmpeg versions, and warnings for runtime concerns that are not structural errors (e.g. a source file that does not exist yet). The only file written is the optional plan JSON at ``save_plan``; paths inside the artifact are workspace-relative. Pass ``variant`` to plan a single named batch variant: the plan reflects that variant's EFFECTIVE (post-override) steps and auto-named output paths and records ``workflow.variant``. An unknown variant or malformed override fails closed (``invalid_workflow_variant``). Returns the plan artifact on success. On a structurally invalid spec it fails closed with a specific error ``code`` (same codes as ``video_workflow_validate``). Args: spec_path: Absolute path to the workflow job-spec JSON file. save_plan: Optional path to write the plan artifact as JSON. variant: Optional declared variant id to plan its effective steps.

NameTypeReqDescription
save_plan
spec_pathstringyes
variant

Structured output declared, but exposes no named fields.

No examples provided.

video_workflow_render ~678

Execute an agent workflow job-spec and return a provenance receipt. Validates the spec first (fail-closed), then runs each allowlisted op (probe|trim|resize|convert|merge|add_text|composite_layers) SEQUENTIALLY in spec order via the backing engine functions. Intermediates are written to a per-run ``@work`` directory unique to this invocation and cleaned on success (kept on failure); final media lands at the declared ``@outputs`` paths. Batch variants: pass ``variant=<id>`` to render one declared variant (its overrides patch the shared steps/outputs, and the single ``@outputs`` path is auto-named with the variant id so N variants emit N distinct outputs); the receipt records ``workflow.variant``. Pass ``all_variants=True`` to render EVERY declared variant in turn and return a ``workflow_batch`` summary (one receipt per variant, each into its own ``@work`` dir); use ``save_receipt_dir`` to also write each variant's receipt to ``<dir>/<variant>.json``. ``variant`` and ``all_variants`` are mutually exclusive. Pass ``keep_intermediates=True`` to retain ``@work`` intermediates even on success (recorded as the ``keep-intermediates`` cleanup policy). Pass ``resume_receipt`` (a prior render receipt from a job that failed with its intermediates kept) to RESUME: the current spec_hash must equal the receipt's (else fail-closed ``resume_spec_mismatch``) AND, for a variant, the receipt's variant must match (else ``resume_variant_mismatch``); each step whose recorded status is ``completed`` AND whose recorded input hashes still match AND whose recorded output file still exists and re-hashes to the recorded hash is SKIPPED, and the first step failing any check plus everything after it re-runs. Returns a workflow receipt (``receipt_kind: "workflow"``) capturing tool + FFmpeg versions, the spec hash, per-source probes/hashes, per-step status with real sha256 hashes of every consumed input and produced output, the cleanup manifest, and the determinism-scope caveat. On the first f…

NameTypeReqDescription
all_variantsboolean
keep_intermediatesboolean
resume_receipt
save_receipt
save_receipt_dir
spec_pathstringyes
variant

Structured output declared, but exposes no named fields.

No examples provided.

video_workflow_validate ~226

Validate an agent workflow job-spec without rendering any media. Runs the fail-closed structural validator over the JSON job-spec at ``spec_path``: op allowlist (probe|trim|resize|convert|merge|add_text|composite_layers), symbolic ``@ref`` resolution (@sources.<id>, @work/<name>, @outputs.<id>), backward-reference-only ordering (a step may reference @work outputs from strictly-earlier steps only), per-op param introspection, and workspace-confined path safety (absolute paths and ../ / symlink escapes fail closed). Returns a structured verdict (``{"valid": true, ...}``) on success. On any structural violation it fails closed with a specific error ``code`` (``invalid_workflow_spec``, ``unknown_workflow_ref``, ``unsupported_workflow_op``, ``unsafe_workflow_source``, ``invalid_workflow_params``). Args: spec_path: Absolute path to the workflow job-spec JSON file.

NameTypeReqDescription
spec_pathstringyes

Structured output declared, but exposes no named fields.

No examples provided.

video_write_metadata ~94

Write metadata tags to a video/audio file. Args: input_path: Absolute path to the input file. metadata: Dict of tag key-value pairs (e.g. {'title': 'My Video', 'artist': 'Me'}). output_path: Where to save the output. Auto-generated if omitted.

NameTypeReqDescription
input_pathstringyes
metadataobjectyes
output_path

Structured output declared, but exposes no named fields.

No examples provided.

Common questions

What is the mcp-video server?

mcp-video is listed in the public MCP registry as io.github.KyaniteLabs/mcp-video. Compatibility package: mcp-video now installs Kinocut (formerly mcp-video). This page covers its PyPI package (mcp-video).

Is the mcp-video server safe to use?

mcp-video scores 75 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 September 2026. 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 mcp-video server expose?

mcp-video exposes 196 tools: video_info, video_trim, video_merge, video_add_text, video_add_texts, and 191 more. Their descriptions and schemas cost roughly 21,443 tokens of context every time the server is loaded.

Is the mcp-video server still maintained?

mcp-video is still listed as active in the MCP registry. We last reached this channel on 21 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.