MakeAIVideo
NPM · @MAKEAIVIDEO/MCP · 2 COMPONENTS
AI video generator: make TikTok, Reels and Shorts videos with voiceover and captions, and post them.
Available components
Last scanned (4 hours ago)
Scores higher than 27% of npm servers
Category Design and Media
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 Security13
- Malware scan not yet available for this package.Unverified
- Known CVEs could not be checked: the version this server declares is not published in its registry.Unverified
- No install/post-install scripts declared.Pass
- Dependency health could not be checked: the version this server declares is not published in its registry.Unverified
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 0 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability65
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 15965 tokens (~228/item across 70 items; 70 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Tools include usage examples.Pass
Stability & Change Management99
- Stability check failed: the tool surface changed between 1.0.5 and 1.2.0: 0 tool removals, 1 breaking changes, 26 additions. See how to fix → Fail
Tool Coverage94
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 82% of tool parameters carry a description.Partial
Tool Safety95
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 4 of 5 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "get_publish_status" implies "publish" and declares readOnlyHint instead, contradicting what its own name says it does. See how to fix → Partial
- An AI judge read all 71 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
Checks we ran (13)
- Install scripts
- Source repository
- Provenance
- License
- Maintenance
- Security disclosure
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Checks we could not complete (3)
These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.
- Malware scan in Supply Chain SecurityMalware scan not yet available for this package.
- Known CVEs in Supply Chain SecurityKnown CVEs could not be checked: the version this server declares is not published in its registry.
- Dependency health in Supply Chain SecurityDependency health could not be checked: the version this server declares is not published in its registry.
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 →
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.
- 21 Nov 26 −26
- Known CVEs: pass → unverified ▼ security
- Malware scan: pass → unverified ▼ security
- Stability: 0.97 → fail ▼ security
- Stability: 0.97 → pass security
- Dependency health: 0.84 → unverified ▼ functional
- Schema quality: pass → fail ▼ functional
- Destructive annotations: 67% → 80% ▲ functional
- Tool coverage: 50% → 82% ▲ functional
- Tool coverage: 50% → 71% ▲ functional
- Schema quality: fail → pass ▲ functional
- Package version: 1.0.5 → 1.2.0 functional
- Package version: 1.0.5 → 1.1.0 functional
- 20 Nov 26 0
- Stability: pass → 0.97 functional
- 12 Nov 26 0
- Stability: 0.97 → pass security
- 11 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
- 9 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.
- 7 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.
- 5 Nov 26 −3
- Stability: pass → 0.77 functional
- 30 Oct 26 0
- Stability: 0.97 → pass security
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 Nov 2026 · Analysed npm/@makeaivideo/mcp@1.2.0
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 →
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 →
preview_voice ~69
Hear a voice say your text (up to 500 characters). Costs 1 credit per 100 characters (1 to 5). Returns a 1-hour audio URL. list_voices has free sample URLs (preview_url).
| Name | Type | Req | Description |
|---|---|---|---|
| text | string | yes | – |
| voice_id | string | yes | – |
No output schema declared.
No examples provided.
publish_video ~382
Post a finished video (status ready) to one or more connected social accounts, now or at a scheduled time. This posts publicly on the user's real accounts: confirm the accounts and caption with the user first. Asynchronous: returns a post id (pub_...) at once; then poll get_publish_status until done is true (respect poll_after_seconds). Platforms: TikTok, Instagram (posts as a Reel), YouTube (a 9:16 video posts as a Short, 16:9 as a regular video), Facebook (Pages only), LinkedIn, X (videos up to 140 seconds), Threads, Pinterest, Bluesky, Telegram and Discord. Set idempotency_key when retrying so the video is not posted twice.
| Name | Type | Req | Description |
|---|---|---|---|
| account_ids | array | yes | Account ids (acc_...) from list_social_accounts. |
| caption | string | yes | Caption for every platform (hashtags included). Max 10000 characters. |
| caption_overrides | object | – | Optional. A different caption per platform, keyed by platform id (e.g. {"linkedin": "..."}). Replaces caption on that platform only. |
| idempotency_key | string | – | Optional. Same key within 24 hours returns the same post instead of posting again. |
| scheduled_for | string | – | Optional. ISO 8601 time to post at (for example 2026-10-01T15:00:00Z). Omit to post now. Posts go out within about 2 minutes of the time. |
| timezone | string | – | Optional. IANA timezone for the schedule, e.g. Europe/London. |
| video_id | string | yes | Public video id, e.g. vid_abc123. Must be ready. |
| youtube_title | string | – | Optional. YouTube title (max 100). Default: the video's own title. |
No output schema declared.
No examples provided.
regenerate_scene ~464
Remake one scene of a finished video: a new clip (picture and motion), optionally with a new spoken line (narration) and/or a new picture description (visual_description). Paid from the credit balance; the price shows first. Call get_video first to see the scenes. Without max_credits this returns the price (remake + the export after it) and charges nothing; call again with max_credits to do it. If get_video shows free_remake on the scene (our quality check flagged it), set use_free_remake true: the remake and its export are free (same line and quality). With auto_export (default) the video file is exported again when the scene is done; then wait_for_video until done is true.
| Name | Type | Req | Description |
|---|---|---|---|
| auto_export | boolean | – | Default true: when the change is done, the video file is exported again by itself so the download has it (the export is included in the price). false: change only the project; call export_video later. |
| idempotency_key | string | – | Optional. Re-sending the same key returns the first answer instead of doing (and charging for) the change again. Set it when retrying. |
| max_credits | integer | – | The price the user agreed to. Without it the call only returns the price (nothing is charged); call again with max_credits set to that price (or more) to do it. Above it, nothing is charged. |
| narration | string | – | Optional new spoken line for the scene (the voice is re-recorded with it). |
| quality | string | – | Optional. "best" remakes a scene of a Fast video in Best quality, at the Best price. |
| scene_number | integer | yes | Scene number, from get_video's scenes[].scene_number. |
| use_free_remake | boolean | – | Use the scene's free remake (get_video scenes[].free_remake, or a trial's first free remake). Keeps the line and quality. |
| video_id | string | yes | Public video id, e.g. vid_abc123 (from list_my_videos or a create result). |
| visual_description | string | – | Optional new description of what the scene shows. Default: the scene's current one. |
No output schema declared.
{"scene_number":2,"video_id":"vid_abc123"}{"max_credits":120,"scene_number":2,"video_id":"vid_abc123","visual_description":"A close-up of the coffee cup on a sunny windowsill"} regenerate_voice ~297
Re-record the whole voiceover with another voice (voice_id from list_voices). Paid (about 2 credits per second of narration, plus the export with auto_export); the price shows first. Without max_credits this returns the price and charges nothing; call again with max_credits to do it. Characters who speak their own lines keep their voices. After it starts, then wait_for_video until done is true.
| Name | Type | Req | Description |
|---|---|---|---|
| auto_export | boolean | – | Default true: when the change is done, the video file is exported again by itself so the download has it (the export is included in the price). false: change only the project; call export_video later. |
| idempotency_key | string | – | Optional. Re-sending the same key returns the first answer instead of doing (and charging for) the change again. Set it when retrying. |
| max_credits | integer | – | The price the user agreed to. Without it the call only returns the price (nothing is charged); call again with max_credits set to that price (or more) to do it. Above it, nothing is charged. |
| video_id | string | yes | Public video id, e.g. vid_abc123 (from list_my_videos or a create result). |
| voice_id | string | yes | A voice from list_voices. |
| voice_stability | string | – | Optional. Default: the video's current setting (balanced). |
No output schema declared.
{"video_id":"vid_abc123","voice_id":"EXAVITQu4vr4xnSDxMaL"} report_video ~114
Free. Report a bad video to our team for review: wrong, broken, unsafe or off-brand. Say what is wrong in reason (and which scene). It does not change or refund the video; to fix it, use regenerate_scene or edit_scene_*.
| Name | Type | Req | Description |
|---|---|---|---|
| category | string | – | Default other. |
| reason | string | yes | What is wrong, in the user's words. |
| video_id | string | yes | Public video id, e.g. vid_abc123 (from list_my_videos or a create result). |
No output schema declared.
{"category":"other","reason":"Scene 3 shows a different person than the other scenes.","video_id":"vid_abc123"} reschedule_post ~124
Change when a scheduled post goes out. Works only while the post's status is scheduled and it is more than about 2 minutes from going out; a post already publishing or published cannot be changed. Free. Confirm the new time with the user first. Returns the post (status, scheduled_for, destinations); get_publish_status reads it later.
| Name | Type | Req | Description |
|---|---|---|---|
| post_id | string | yes | Post id (pub_...) from publish_video or list_posts. |
| scheduled_for | string | yes | New ISO 8601 time with a timezone offset, at least a few minutes from now. |
No output schema declared.
No examples provided.
set_music ~137
Free. Change or remove a video's background music, or its volume. track_id from list_music_library (or a generated track from list_music), or "none" for no music. Saved to the video's project; then call export_video to put it in the file.
| Name | Type | Req | Description |
|---|---|---|---|
| track_id | string | – | A library or generated track id, or "none". |
| video_id | string | yes | Public video id, e.g. vid_abc123 (from list_my_videos or a create result). |
| volume | number | – | Music volume 0 to 1 under the voice. Default 0.15, or the current volume. |
No output schema declared.
{"track_id":"upbeat-01","video_id":"vid_abc123","volume":0.2}{"track_id":"none","video_id":"vid_abc123"} set_watermark ~175
Free. Set the logo watermark for the workspace's new exports: image_url uploads a new logo (a public https PNG, WebP or JPEG, up to 5 MB; a PNG with transparency works best) and shows it unless show_watermark is false; show_watermark turns it on or off; remove_watermark: true deletes it. Videos already exported do not change; export_video makes a new file with it. Needs the Plus or Pro plan (refused otherwise). Returns the brand kit as get_brand_kit does.
| Name | Type | Req | Description |
|---|---|---|---|
| image_url | string | – | Optional: a public https link to the logo. |
| remove_watermark | boolean | – | Optional: true deletes the logo. |
| show_watermark | boolean | – | Optional: true shows it on new exports, false hides it (the logo is kept). |
No output schema declared.
{"image_url":"https://example.com/logo.png"}{"show_watermark":false} structure_text ~61
Free (no credits). Turn prose or a hand-written script into our structured scene script, keeping the user's words. Then create_video_from_script with it.
| Name | Type | Req | Description |
|---|---|---|---|
| mode | string | – | – |
| target_duration | number | – | – |
| text | string | yes | – |
No output schema declared.
No examples provided.
suggest_caption ~145
Free (no credits). A ready-to-post caption with hashtags, written from the video's own script, as the web Post dialog fills it in, plus per_platform versions where the caption is too long for a platform and a youtube_title. Saved on the video, so a second call returns the same one; refresh: true writes a new one. fallback: true means the writer failed and the caption is the video's title. Show it to the user, then pass it as caption to publish_video.
| Name | Type | Req | Description |
|---|---|---|---|
| refresh | boolean | – | Optional. true writes a new caption instead of the saved one. |
| video_id | string | yes | Public video id, e.g. vid_abc123. |
No output schema declared.
No examples provided.
talking_avatar ~384
Talking avatar from your own filmed video: the person in the video says a new script (we voice it and lip-sync it onto the clip). Paid from the credit balance. Priced on how long the words take to say: a 6-second line is about 52 credits. Free quote first: estimate_video_cost with kind "talking-avatar" and text = the script. Needs avatar_video_key from upload_video_from_url (a clip of one person facing the camera). For an AI presenter instead, use create_spokesperson_video with a character_id; for a photo that talks, use image_to_video with narration. Returns video_id with started: true; then call wait_for_video with it until done is true, and give the user download_url. If there is no plan, the price is above max_credits, or the balance does not cover it, nothing is created or charged: the result has started: false and held { reason, credits, balance, options[], next_call }; show the user the options (and start_trial_url or top_up_url when given).
| Name | Type | Req | Description |
|---|---|---|---|
| add_broll | boolean | – | Optional. true cuts in stock footage over parts of the clip. Default false. |
| avatar_video_key | string | yes | From upload_video_from_url. |
| idempotency_key | string | – | Optional. Re-sending the same key returns the SAME video instead of making (and charging for) a second one. Set it when retrying. |
| max_credits | number | – | Optional price confirm: the most credits this call may spend. Above it nothing is created; the result is held with reason price_over_limit and the price. |
| script | string | yes | The exact words the person says. |
| title | string | – | – |
| voice_id | string | – | Optional: a voice from list_voices. Default: our standard voice. |
No output schema declared.
{"avatar_video_key":"uploads/123/clip.mp4","script":"Hi, I'm Sam. Here are three quick tips for better sleep tonight."} test_webhook ~68
Free. Send one signed test event (data.test = true) to the webhook's URL now, to check the receiver and its signature check. Returns delivered, status_code, duration_ms and error.
| Name | Type | Req | Description |
|---|---|---|---|
| webhook_id | string | yes | Webhook id from list_webhooks or create_webhook. |
No output schema declared.
No examples provided.
update_character ~104
Free. Rename one of your own characters, change its description, or give it another voice (voice_id from list_voices). Preset characters cannot be edited. The new voice is used by videos made after the change.
| Name | Type | Req | Description |
|---|---|---|---|
| character_id | number | yes | Your own character's id, from list_characters (characters, not presets). |
| description | string | – | – |
| name | string | – | – |
| voice_id | string | – | A voice from list_voices. |
No output schema declared.
{"character_id":1234,"name":"Coach Maya","voice_id":"21m00Tcm4TlvDq8ikWAM"} update_video ~291
Free. Edit a video's title, topic, script or captions. A title works at any time. Captions: caption_style ("none" turns them off) and caption_alignment; on a finished video they are saved to the project, then call export_video to put them in the file. A script edit applies on the next generate_video (to change one scene of a finished video use edit_scene_narration or edit_scene_visual instead). Edits other than the title are refused while the video is being made.
| Name | Type | Req | Description |
|---|---|---|---|
| caption_alignment | string | – | Where captions sit. Default: the style's own. |
| caption_style | string | – | Caption look. "basic": Classic (default when captions are on); "ali": Subtle; "movie": Subtitle (italic); "word-pop": Word pop; "hormozi": Hormozi; "bold": Bold; "beat": Beat; "outline": Outline; "ba… |
| script | object | – | The whole script (as get_video returns it, camel or snake case), for a draft. |
| title | string | – | – |
| topic | string | – | – |
| video_id | string | yes | Public video id, e.g. vid_abc123 (from list_my_videos or a create result). |
No output schema declared.
{"caption_alignment":"bottom","caption_style":"bold","video_id":"vid_abc123"}{"title":"Spring sale","video_id":"vid_abc123"} update_workspace ~133
Free. Rename the workspace, change its description, or change its saved defaults (default_aspect_ratio, default_style, default_character_id: null clears it). Owners and admins only. These are the settings on the web app's Workspace settings page; the create tools do not read them, so still pass aspect_ratio / character_id on each create.
| Name | Type | Req | Description |
|---|---|---|---|
| default_aspect_ratio | string | – | – |
| default_character_id | number|null | – | A character id from list_characters, or null to clear it. |
| default_style | string | – | – |
| description | string | – | – |
| name | string | – | – |
No output schema declared.
{"default_aspect_ratio":"9:16","name":"Acme socials"} upload_image_from_url ~136
Free. Import one image from a public https URL (JPEG, PNG, WebP, HEIC and other photos, up to 25 MB) into this workspace and get its image_key. Use the key as image_key for image_to_video, in photo_keys for character_swap, or in product_image_keys for create_ugc_video / create_demo_video (real product photos). The user's file must already be online (a link they share); you cannot upload from their computer here. Returns image_key, url (a short-lived preview), width, height.
| Name | Type | Req | Description |
|---|---|---|---|
| image_url | string | yes | Public https URL of the image. |
No output schema declared.
No examples provided.
upload_video_from_url ~102
Free. Import one video from a public https URL (MP4, MOV or WebM, up to 100 MB) into this workspace and get its video_key and duration_seconds. Use the key as avatar_video_key for talking_avatar or source_video_key for character_swap (send duration_seconds with it). Returns video_key, duration_seconds (null if it could not be read), url.
| Name | Type | Req | Description |
|---|---|---|---|
| video_url | string | yes | Public https URL of the video. |
No output schema declared.
No examples provided.
wait_for_video ~232
Free. Wait for a video on the server, up to about 50 seconds per call, and return its progress: status, stage (waiting_for_plan, scripting, waiting_for_slot, making_scenes, rendering, finishing_file, remaking_scene, re_voicing, updating_file, ready, failed, draft), progress_note and scenes_done of scenes_total. Also use it after regenerate_scene, edit_scene_narration, edit_scene_visual, regenerate_voice or export_video: it waits until the change is in the file. done: true means nothing more will happen without a call (ready, failed, or a draft that needs generate_video); otherwise call it again with the same video_id. waiting_for_plan: the account has no plan yet; give the user start_trial_url and say_to_user, and the video starts by itself once the trial is active. Once ready it gives web_url (the user's page, lasting) and download_url (15 minutes).
| Name | Type | Req | Description |
|---|---|---|---|
| video_id | string | yes | Public video id, e.g. vid_abc123 (from list_my_videos or a create result). |
No output schema declared.
{"video_id":"vid_abc123"} whoami ~37
Free. Who this key belongs to: user, organization, plan, scopes and the live credit balance. Call first to confirm the connection works.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
write_script ~126
Write the script only (no video, no render credits): title, hook and scenes with narration and visual directions. Give a topic, or a tool + fields from the create tools. Edit it, then create_video_from_script.
| Name | Type | Req | Description |
|---|---|---|---|
| fields | object | – | The tool's brief fields by name. |
| language | string | – | Language code or 'auto'. |
| mode | string | – | – |
| target_duration | number | – | Seconds, 10-1800. |
| tool | string | – | – |
| topic | string | – | Free-text topic. Use this OR tool+fields. |
No output schema declared.
No examples provided.
How do I install the MakeAIVideo MCP server?
MakeAIVideo runs locally as an npm package, launched with npx -y @makeaivideo/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 · @makeaivideo/mcp
claude mcp add ai-makeaivideo-video-generator -- npx -y @makeaivideo/mcp
What is the MakeAIVideo MCP server?
MakeAIVideo is an MCP server listed in the public MCP registry as ai.makeaivideo/video-generator. AI video generator: make TikTok, Reels and Shorts videos with voiceover and captions, and post them. This page covers its npm package (@makeaivideo/mcp).
Is the MakeAIVideo MCP server safe to use?
MakeAIVideo scores 56 out of 100 on VerifyMCP. 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 MakeAIVideo MCP server expose?
MakeAIVideo exposes 70 tools: create_explainer_video, create_listicle_video, create_story_video, create_ugc_video, create_demo_video, and 65 more. Their descriptions and schemas cost roughly 15,896 tokens of context every time the server is loaded.
Is the MakeAIVideo MCP server still maintained?
MakeAIVideo is still listed as active in the MCP registry. We last reached this channel on 21 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 MakeAIVideo MCP server under?
MakeAIVideo 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 MakeAIVideo MCP server?
VerifyMCP ran 13 checks on MakeAIVideo, covering Install scripts, Source repository, Provenance, License and 9 more. 3 items could not be completed, a gap on our side rather than a finding about MakeAIVideo: Malware scan, Known CVEs and Dependency health. 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.