ClipUGC
NPM · CLIPUGC · SCANNED SEP 30
Create AI influencer characters, looks, video clips and merged UGC app ads with ClipUGC.
Available components
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
- 40 of 116 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 26 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability80
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 2439 tokens (~187/item across 13 items; 11 tools + 2 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 Management90
- Stability observed for 27 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
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
- All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 13 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
How do I install the ClipUGC MCP server?
ClipUGC runs locally as an npm package, launched with npx -y clipugc. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · clipugc
claude mcp add clipugc-clipugc -- npx -y clipugc
{
"mcpServers": {
"clipugc-clipugc": {
"command": "npx",
"args": [
"-y",
"clipugc"
]
}
}
} {
"servers": {
"clipugc-clipugc": {
"command": "npx",
"args": [
"-y",
"clipugc"
]
}
}
} codex mcp add clipugc-clipugc -- npx -y clipugc
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"clipugc-clipugc": {
"type": "local",
"command": [
"npx",
"-y",
"clipugc"
],
"enabled": true
}
}
} openclaw mcp add clipugc-clipugc --command npx --arg -y --arg clipugc
mcp_servers:
clipugc-clipugc:
command: "npx"
args: ["-y", "clipugc"] {
"McpServers": {
"clipugc-clipugc": {
"Transport": "stdio",
"Command": "npx",
"Arguments": [
"-y",
"clipugc"
]
}
}
} assistant mcp add clipugc-clipugc -t stdio -c npx -a -y clipugc
{
"mcpServers": {
"clipugc-clipugc": {
"command": "npx",
"args": [
"-y",
"clipugc"
]
}
}
} 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.
- 29 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
- 28 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
- 26 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.
- 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 +1
No change was recorded against any check on this day. Stability & Change Management went from 67 to 70. That category is still filling its 30-day observation window: 20 days of observed history at the previous scan, 21 at this one. The score rises as the window fills, whether or not the server changes.
- 22 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.
- 20 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 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 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.
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 30 Sept 2026 · Analysed npm/clipugc@1.2.2
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 116 packages
| Packages resolved | 116 |
|---|---|
| Stale | 40 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
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 →
create_character Create an AI character ~441
Create a new AI character from a plain-text description. Same as `clipugc characters create`. The server extracts the appearance DNA and generates the first look automatically (2 credits; confirm with get_credits). Be specific: nationality, age, hair, eyes, face shape, skin, style, and a realism anchor such as "natural skin texture, not airbrushed". Characters are public by default; set private=true to opt out. make_video=true also stages the first clip (extra clip cost). Returns the character with first_look_id. Looks generate in the background. Poll list_images with the same character id every 5 to 10 seconds until each new look has status "completed" (or "failed"), then pass the look id to create_clip. Advanced: pass name (2-120 chars) plus optional age, gender, dna_json instead of description for a structured create.
| Name | Type | Req | Description |
|---|---|---|---|
| age | integer | – | [advanced] Age 18-99 (same as --age). |
| description | string | – | Plain-words description of the person, 10-1000 chars (same as --description). Preferred path. |
| dna_json | string | – | [advanced] Appearance DNA fields as an inline JSON object string or a JSON file path (same as --dna-json). |
| gender | string | – | [advanced] Gender, e.g. male, female, other (same as --gender). |
| inspiration | array | – | Optional local file paths of up to 6 inspiration images (same as --inspiration). |
| make_video | boolean | – | Also stage the character's first video clip (same as --make-video). |
| motion_prompt | string | – | Motion prompt for that first clip; requires make_video (same as --motion-prompt). |
| name | string | – | [advanced] Full name, 2-120 chars, for the structured path without a description (same as --name). |
| private | boolean | – | Keep the character private (same as --private). Default: public. |
| scene | string | – | Optional scene/pose for the first look, up to 600 chars (same as --scene). |
No output schema declared.
No examples provided.
create_clip Create a video clip from a look ~307
Animate a character look (or your own photo) into a short video clip. Same as `clipugc videos create`. Costs 7 credits for 5 seconds or 13 for 10 seconds; adding scene makes it a scene-staged clip (9 at 5s, 15 at 10s). Confirm with get_credits first. Prefer a silent reaction prompt (mouth closed, no talking, an arc in beats, ambient motion): lip-sync from a still image is what makes AI video look fake. Provide exactly one of image or photo. Returns the clip id and status. Generation runs in the background. Poll get_video with {"id": <clip id>, "kind": "clip"} every 5 to 10 seconds until status is "completed" or "failed", then call download_video.
| Name | Type | Req | Description |
|---|---|---|---|
| duration | – | – | 5 or 10 seconds, default 5 (same as --duration). |
| image | string | – | Id of a generated character look (same as --image). |
| keep_sound | boolean | – | Keep the original sound (same as --keep-sound). |
| photo | string | – | Local path to your own photo, png/jpg/jpeg/webp; uploaded first (same as --photo). |
| prompt | string | – | What the character does, max 1500 chars (same as --prompt). |
| scene | string | – | Extra scene description, max 600 chars; makes it a scene-staged clip (same as --scene). |
No output schema declared.
No examples provided.
create_motion_clip Create a motion-control clip ~266
Animate a character look (or your own photo) by copying the motion of a driver video. Same as `clipugc videos motion`. Costs 3 credits per second of driver video, rounded up, capped at 30 seconds (confirm with get_credits). The driver must be mp4/mov, at most 50 MB and 30 seconds; it is uploaded first. Provide exactly one of image or photo. Returns the clip id and status. Generation runs in the background. Poll get_video with {"id": <clip id>, "kind": "clip"} every 5 to 10 seconds until status is "completed" or "failed", then call download_video.
| Name | Type | Req | Description |
|---|---|---|---|
| driver | string | yes | Local path of the driver video, mp4/mov, max 50 MB and 30s (same as --driver). |
| image | string | – | Id of a generated character look (same as --image). |
| keep_sound | boolean | – | Keep the driver video's original sound (same as --keep-sound). |
| photo | string | – | Local path to your own photo, png/jpg/jpeg/webp; uploaded first (same as --photo). |
| prompt | string | – | What the character does, max 1500 chars (same as --prompt). |
No output schema declared.
No examples provided.
download_video Download a clip or ad ~178
Download a completed clip (kind "clip", default; same as `clipugc videos download <id>`) or a completed merged ad (kind "ad"; same as `clipugc ads download <adId>`) to a local mp4 file. Pass an absolute output path; missing parent directories are created. Costs no credits. Fails if the video has not completed yet.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | Clip or ad id, as returned by other tools (numbers are fine as strings). |
| kind | string | – | "clip" (default) for a character video id, "ad" for a merged_video_id. |
| output | string | – | Destination file path (same as --output). Default: clipugc-video-<id>.mp4 or clipugc-ad-<id>.mp4 in the server's working directory. |
No output schema declared.
No examples provided.
generate_image Generate character looks ~254
Generate one or more new looks (reference images) of an existing character. Same as `clipugc images generate`. Every look is generated from the character's base image, so the face stays the same person: only describe the new setting, outfit and light in scene, never the person again. Costs 2 credits per shot (confirm with get_credits). Returns the created image ids. Looks generate in the background. Poll list_images with the same character id every 5 to 10 seconds until each new look has status "completed" (or "failed"), then pass the look id to create_clip.
| Name | Type | Req | Description |
|---|---|---|---|
| character | string | yes | Character id, as returned by other tools (numbers are fine as strings). |
| resolution | string | – | Resolution (same as --resolution). Default 2K. |
| scene | string | – | Scene prompt, max 600 chars (same as --scene). |
| shots | string | – | Comma-separated shot types: frontal, three_quarter, profile, back (same as --shots). Default "frontal". |
| template | string | – | Template (same as --template). Omit to let the server pick: scene_recreation when scene is set, else model_digitals. |
No output schema declared.
No examples provided.
get_credits Get credit balance and costs ~77
Return the authenticated user's credit balance and the live per-action credit costs (image, clip, clip_10s, scene_staged, motion_per_second, merge). Same as `clipugc credits`. Call it before any generation tool so you can tell the user the cost and stop early when the balance is too low. Costs no credits.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_video Get clip or ad status ~149
Get the current status of a clip (kind "clip", default; same as `clipugc videos status <id>`) or of a merged ad (kind "ad"; same as `clipugc ads show <adId>`). This is the poll tool for create_clip, create_motion_clip and merge_ad. Status is pending, processing, completed or failed. A clip record also carries merge_status and merged_video_id once merged. Costs no credits.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | Clip or ad id, as returned by other tools (numbers are fine as strings). |
| kind | string | – | "clip" (default) for a character video id, "ad" for a merged_video_id. |
No output schema declared.
No examples provided.
list_characters List AI characters ~150
List ClipUGC AI characters (AI influencers). Same as `clipugc characters list`. scope "mine" (default) lists the authenticated user's own characters, "discover" the public feed, "feed" own characters first then public ones. Returns items with id, display_name, age, gender, is_public, status, plus pagination. Costs no credits.
| Name | Type | Req | Description |
|---|---|---|---|
| page | integer | – | Page number (same as --page). |
| per_page | integer | – | Results per page, max 50 (same as --per-page). |
| scope | string | – | Which list: mine (default), discover, or feed. |
| search | string | – | Search by name (same as --search). |
No output schema declared.
No examples provided.
list_hooks Suggest hook texts ~94
Get AI-suggested hook texts (the short attention-grabbing line burned over a UGC ad). Same as `clipugc hooks suggest`. Pass context describing the app for tailored hooks. Pick one (max 150 chars) and pass it as hook to merge_ad. Costs no credits.
| Name | Type | Req | Description |
|---|---|---|---|
| context | string | – | Describe the app, e.g. "my app is a habit tracker" (same as --context). |
No output schema declared.
No examples provided.
list_images List character looks ~88
List the looks (reference images) of a character with id, status (pending, processing, completed, failed), scene_prompt and image url when ready. Same as `clipugc images list --character <id>`. Also the poll call for generate_image and create_character. Costs no credits.
| Name | Type | Req | Description |
|---|---|---|---|
| character | string | yes | Character id, as returned by other tools (numbers are fine as strings). |
No output schema declared.
No examples provided.
merge_ad Merge a clip into a UGC ad ~261
Merge a completed clip with an app screen recording and a hook text overlay (plus optional background music) into the final UGC ad. Same as `clipugc videos merge <clipId>`. The clip must have status "completed" (check with get_video). Merging is free at the time of writing; the live cost is the "merge" entry of get_credits. Files are uploaded first. Returns merged_video_id: the AD id, which is a different id space from the clip id. The merge renders in the background. Poll get_video with {"id": <merged_video_id>, "kind": "ad"} every 5 to 10 seconds until status is "completed" or "failed", then call download_video with kind "ad".
| Name | Type | Req | Description |
|---|---|---|---|
| app_video | string | yes | Local path of the app screen recording, mp4/mov (same as --app-video). |
| hook | string | yes | Hook text overlaid on the video, max 150 chars (same as --hook). |
| music | string | – | Local path of background music, mp3/wav/m4a (same as --music). |
| video | string | yes | Clip (character video) id, as returned by other tools (numbers are fine as strings). |
No output schema declared.
No examples provided.
What is the ClipUGC MCP server?
ClipUGC is an MCP server listed in the public MCP registry as io.github.clipugc/clipugc. Create AI influencer characters, looks, video clips and merged UGC app ads with ClipUGC. This page covers its npm package (clipugc).
Is the ClipUGC MCP server safe to use?
ClipUGC scores 83 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 30 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 ClipUGC MCP server expose?
ClipUGC exposes 11 tools: list_characters, create_character, generate_image, list_images, create_clip, and 6 more. Their descriptions and schemas cost roughly 2,265 tokens of context every time the server is loaded.
Is the ClipUGC MCP server still maintained?
ClipUGC is still listed as active in the MCP registry. We last reached this channel on 30 September 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 ClipUGC MCP server under?
ClipUGC declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.