Blender integration through the Model Context Protocol
AIVeed is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
What it does
Generate AI videos, images and audio (Veo 3.1, Seedance, Kling and more) with AIVeed credits.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --env 'AIVEED_API_KEY=${AIVEED_API_KEY}' --transport stdio aiveed-mcp '--' npx -y aiveed-mcp
# 2 — ask your agent for something these tools do
# list_models, get_credits, generate_video and 9 more
It needs AIVEED_API_KEY: this reads it from your environment, so export it first.
AIVeed costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts AIVeed as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads AIVEED_API_KEY (Your AIVeed API key (aiv_sk_...), from https://developer.aiveed.io/keys) from your environment each time it starts the server, so the value stays out of its config: export it in your shell profile (macOS, Linux), or run setx AIVEED_API_KEY … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user --env 'AIVEED_API_KEY=${AIVEED_API_KEY}' --transport stdio aiveed-mcp '--' npx -y aiveed-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
It reaches a system of yours, so it needs your own credential rather than the publisher’s: AIVEED_API_KEY — Your AIVeed API key (aiv_sk_...), from https://developer.aiveed.io/keys. You set it in your own client’s config, on your machine — this marketplace never holds it.
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
12 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Live AIVeed model catalog: every video, image and audio model with its options (aspect ratios, durations, resolutions, modes), accepted inputs and credit cost. Call this before generating; models and prices change.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| type | string | no | Only this kind of model |
The account's current credit balance. Generations are charged up front and refunded automatically if they fail.
No parameter schema on file.
Start a video generation job (text-to-video, image-to-video, first/last frame, references). Spends credits: tell the user the cost from list_models first. Returns a job id immediately; the video takes from about 30 s to several minutes, so follow up with get_job.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| model | string | yes | Model id from list_models, e.g. "veo3-fast", "seedance-2", "kling-3.0" |
| prompt | string | no | — |
| aspect_ratio | string | no | One of the model's aspect_ratios, e.g. "16:9" |
| duration | string | no | Seconds as a string, one of the model's durations, e.g. "8" |
| resolution | string | no | One of the model's resolutions, e.g. "720p" |
| mode | string | no | Model-specific mode, e.g. Kling "std"/"pro", Grok "normal" |
| image_url | string | no | Image-to-video source image (public URL, or the url from upload_media) |
| first_frame_url | string | no | — |
| last_frame_url | string | no | Requires first_frame_url; not every model supports it |
| reference_image_urls | array | no | — |
| reference_video_urls | array | no | — |
| reference_audio_urls | array | no | — |
| generate_audio | boolean | no | — |
| sound | boolean | no | Kling: false for a silent video |
| video_url | string | no | Lip sync: the source video |
| audio_url | string | no | Lip sync: the audio track |
| audio_duration | number | no | — |
| lip_sync_mode | string | no | — |
| multi_shots | boolean | no | Kling multi-shot |
| multi_prompt | array | no | Kling multi-shot prompts, as documented at https://api.aiveed.io/llms-full.txt |
Start an image generation or edit job (pass image_urls to edit or combine images). Spends credits: check the cost with list_models. Returns a job id; follow up with get_job.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| model | string | yes | Image model id from list_models, e.g. "nano-banana", "gpt-image-2" |
| prompt | string | no | — |
| aspect_ratio | string | no | — |
| resolution | string | no | — |
| output_format | string | no | e.g. "png" or "jpeg", where the model supports it |
| image_urls | array | no | Input images for editing |
| idempotency_key | string | no | Recommended: pass your own unique key (e.g. a UUID) and keep it. Retrying with the same key never charges twice, even if the first response was lost. Generated when omitted and returned in the result. |
Start a voiceover (model "voiceover": text + voice_id or voice_name) or music (model "music": style, lyrics or instrumental) job. Spends credits. Returns a job id; follow up with get_job.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| model | string | yes | — |
| text | string | no | Voiceover script |
| voice_id | string | no | — |
| voice_name | string | no | — |
| style | string | no | Music style |
| lyrics | string | no | — |
| title | string | no | — |
| instrumental | boolean | no | — |
| idempotency_key | string | no | Recommended: pass your own unique key (e.g. a UUID) and keep it. Retrying with the same key never charges twice, even if the first response was lost. Generated when omitted and returned in the result. |
Add about 7 seconds to a completed Veo 3.1 video job. Spends credits at the tier the video was made with (see list_models "extend").
| Parameter | Type | Required | Notes |
|---|---|---|---|
| job_id | string | yes | Job id returned by a generate call, e.g. "j_abc123def456" |
| prompt | string | yes | — |
| idempotency_key | string | no | Recommended: pass your own unique key (e.g. a UUID) and keep it. Retrying with the same key never charges twice, even if the first response was lost. Generated when omitted and returned in the result. |
Status of a generation job; result_url is set when status is "completed". Set wait_seconds to keep polling until the job finishes or the time is up. Failed jobs are refunded automatically.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| job_id | string | yes | Job id returned by a generate call, e.g. "j_abc123def456" |
| wait_seconds | integer | no | Poll for up to this many seconds (default 0: return at once; at most …, call again for longer jobs) |
Recent jobs, newest first. Use it to find a job after a timeout instead of generating again.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| status | string | no | — |
| model | string | no | — |
| type | string | no | — |
Cancel a job that is still queued (refunded). Jobs that already started cannot be cancelled.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| job_id | string | yes | Job id returned by a generate call, e.g. "j_abc123def456" |
The account's generated videos with permanent video_url links (a job's result_url can be temporary).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| model | string | no | — |
The account's generated images with permanent image_url links.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| model | string | no | — |
| favorite | boolean | no | — |
Upload a local image, audio or video file to use as a generation input (image_url, first_frame_url, reference_*_urls, audio_url). Free. The returned url is PUBLIC, so only upload a file the user explicitly asked you to use. Works only inside the folders the user listed in AIVEED_MCP_UPLOAD_DIRS;…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | yes | Absolute path of the local file |
| kind | string | yes | — |
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install AIVeed or to call it, at any volume.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tools were statically extracted from the published source (12 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
1 of the 12 recovered tools are registered only when opts.localFiles holds (dist/tools.js:237) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 11.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
11 tools are registered unconditionally · 1 more only when opts.localFiles holds (dist/tools.js:237) — typically when a key or option is configured. All 12 are in the table below and were analysed; the conditional ones are marked.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| list_models | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_credits | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| generate_video | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true, handler sends an HTTP POST (request("POST", …)) at dist/tools.js:86 |
| generate_image | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true, handler sends an HTTP POST (request("POST", …)) at dist/tools.js:86 |
| generate_audio | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true, handler sends an HTTP POST (request("POST", …)) at dist/tools.js:86 |
| extend_video | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true, handler sends an HTTP POST (request("POST", …)) at dist/tools.js:86 |
| get_job | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| list_jobs | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| cancel_job | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true, handler sends an HTTP DELETE (request("DELETE", …)) at dist/tools.js:224 |
| list_videos | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| list_images | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| upload_media conditional | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true, handler sends an HTTP POST (request("POST", …)) at dist/tools.js:246 |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
Supply chain and provenance
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.1.1. Pin a release below and the command asks for exactly that one.
No release note was published with this version.
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Any signed-in account that does not publish AIVeed can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.