WaveSpeedのライブカタログから画像、動画、音声、3Dモデルを実行できます。スキーマの参照、料金見積もり、実行履歴の確認も可能です。
別名 WaveSpeedAI/mcp-server, mcp-server, @wavespeed/mcp
- スター
- 37
- ツール
- 16
- ダウンロード数(30日間)
- —
- 最新バージョン
- 1.2.15
- 最終コミット
- 2026年11月10日
- ライセンス
- MIT
WaveSpeed MCPとは
WaveSpeedのライブカタログから画像、動画、音声、3Dモデルを実行できます。スキーマの参照、料金見積もり、実行履歴の確認も可能です。 16個のツールを提供しており、list_models, get_model_schema, run_modelなどがあります。
プロジェクトのREADMEから生成された概要
WaveSpeed MCP server について
WaveSpeedは、ライブカタログにある画像、動画、音声、3DモデルをAI開発環境内で直接実行することを可能にします。Claude Desktop、Cursor、Claude Code、Clineを使用している開発者は、ハードコードされた設定を必要とせずに、多種多様な生成モデルにアクセスできます。このサーバーは、1時間ごとにカタログを更新するライブAPIに接続しているため、プラットフォーム上で新しいモデルがリリースされるとすぐに利用可能になります。
ユーザーは、run_modelのような汎用的なツールや、generate_image、edit_video、extend_videoといった専用のショートカットを通じてカタログを操作できます。ローカルファイルに対して @path マーカーを使用すると、システムがファイルのアップロードを自動的に処理します。コスト管理のために、get_priceツールを実行前に見積もりを提供します。サーバーは、ホストされたURLを介したリモート設定、またはWAVESPEED_API_KEYを使用したnpxによるローカル設定のどちらも可能です。また、アカウント残高の確認、list_predictionsによる実行履歴の表示、明細付きの請求詳細の確認といった管理機能も備えています。
できること
- 1生成コストの見積もりリクエストを送信する前に、特定のモデルの実行にいくらかかるかをAIに確認させます。
- 2ローカルファイルのアップロード自動化AIにローカルファイルのパスを渡すことで、ファイルを自動的にアップロードし、モデルの入力として使用させます。
プロジェクトの README から作成されています。すべてのユースケースは、その引用と照らし合わせて確認されています。
WaveSpeed MCPのインストール方法
フォーマット検証日 2026年11月10日Cursor に追加Gooseに追加Claude CodeにWaveSpeed MCPをインストール
$ claude mcp add --env 'WAVESPEED_API_KEY=<YOUR_WAVESPEED_API_KEY>' mcp-server -- npx -y @wavespeed/mcpCursorにWaveSpeed MCPをインストール
~/.cursor/mcp.json
{
"mcpServers": {
"mcp-server": {
"command": "npx",
"args": [
"-y",
"@wavespeed/mcp"
],
"env": {
"WAVESPEED_API_KEY": "<YOUR_WAVESPEED_API_KEY>"
}
}
}
}VS CodeにWaveSpeed MCPをインストール
.vscode/mcp.json
{
"servers": {
"mcp-server": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@wavespeed/mcp"
],
"env": {
"WAVESPEED_API_KEY": "<YOUR_WAVESPEED_API_KEY>"
}
}
}
}VS Code CLIにWaveSpeed MCPをインストール
$ code --add-mcp '{"name":"mcp-server","type":"stdio","command":"npx","args":["-y","@wavespeed/mcp"],"env":{"WAVESPEED_API_KEY":"<YOUR_WAVESPEED_API_KEY>"}}'Claude DesktopにWaveSpeed MCPをインストール
claude_desktop_config.json
{
"mcpServers": {
"mcp-server": {
"command": "npx",
"args": [
"-y",
"@wavespeed/mcp"
],
"env": {
"WAVESPEED_API_KEY": "<YOUR_WAVESPEED_API_KEY>"
}
}
}
}CodexにWaveSpeed MCPをインストール
$ codex mcp add mcp-server --env 'WAVESPEED_API_KEY=<YOUR_WAVESPEED_API_KEY>' -- npx -y @wavespeed/mcpCodex config.tomlにWaveSpeed MCPをインストール
~/.codex/config.toml
[mcp_servers.mcp-server] command = "npx" args = ["-y", "@wavespeed/mcp"] [mcp_servers.mcp-server.env] WAVESPEED_API_KEY = "<YOUR_WAVESPEED_API_KEY>"
Gemini CLIにWaveSpeed MCPをインストール
$ gemini mcp add -s user -e 'WAVESPEED_API_KEY=<YOUR_WAVESPEED_API_KEY>' mcp-server npx -- -y @wavespeed/mcpGemini settings.jsonにWaveSpeed MCPをインストール
~/.gemini/settings.json
{
"mcpServers": {
"mcp-server": {
"command": "npx",
"args": [
"-y",
"@wavespeed/mcp"
],
"env": {
"WAVESPEED_API_KEY": "<YOUR_WAVESPEED_API_KEY>"
}
}
}
}HostedMCP が 2026年11月16日 に起動を確認
@wavespeed/mcp 1.2.15 をネットワークもキーもない隔離コンテナでこのコマンドで起動しました。応答があり、16個のツールが一覧表示されました。
WaveSpeed MCPツール 16
tools/list でサーバーから取得list_models読み取り専用Search the live WaveSpeed model catalog (image, video, audio, 3D). Returns model IDs usable with run_model. Do not invent model IDs — always pick one returned by this tool.
get_model_schema読み取り専用Get a model's real input schema (required fields, properties, defaults). Call this before run_model so inputs match what the model actually accepts.
run_modelアクションRun any WaveSpeed model. input keys come from get_model_schema; unknown keys are rejected before submission. Local files: pass "@./path" in a media field (image, images, video, audio, mask …) — it is uploaded and replaced with hosted URLs (bare paths are NOT uploaded). Returns the prediction id right away (done=false); call get_prediction with that id and wait_seconds until done=true to get the output URLs. The task keeps running on the server. Pass wait_seconds here to wait for a quick model in the same call.
generate_imageアクションCreate an image from a text description with the same models as the WaveSpeed /chat page (seedream-5-5, seedream-5-pro, nano-banana-2.1, nano-banana-2, nano-banana-pro, gpt-image-2.6, gpt-image-2.5, gpt-image-2; default seedream-5-5). Give reference_images to use existing images as subject, product, face or style (the model's edit endpoint is used). To change existing images use edit_image. In the prompt, name input media as @image 1, @image 2, @video 1, @audio 1 (counted in the order the lists are given); they are renamed to what the model expects.
edit_imageアクションChange existing images with the same models as the WaveSpeed /chat page: edits, restyles, backgrounds, adding or removing things, combining several images. In the prompt, name input media as @image 1, @image 2, @video 1, @audio 1 (counted in the order the lists are given); they are renamed to what the model expects.
generate_videoアクションCreate a video with the same models as the WaveSpeed /chat page (default seedance-2.5). Give first_frame to animate an image; give reference_images / reference_videos / reference_audios to keep characters, products, motion, voice or music. The right mode (text, image or reference to video) is picked from what you give. Videos can cost dollars: use estimate_only first when unsure. In the prompt, name input media as @image 1, @image 2, @video 1, @audio 1 (counted in the order the lists are given); they are renamed to what the model expects.
edit_videoアクションEdit an existing video with the same models as the WaveSpeed /chat page. Name the video and any references in the prompt (e.g. "replace the cat in @video 1 with the lion from @image 1"). In the prompt, name input media as @image 1, @image 2, @video 1, @audio 1 (counted in the order the lists are given); they are renamed to what the model expects.
extend_videoアクションContinue an existing video with new footage after its end, with the same models as the WaveSpeed /chat page (Seedance 2.5 Flash included). Turbo models, Flash Turbo too, cannot extend. In the prompt, name input media as @image 1, @image 2, @video 1, @audio 1 (counted in the order the lists are given); they are renamed to what the model expects.
get_priceアクションEstimate the cost of a run before executing it (no charge). Provide the same input you would pass to run_model — pricing often depends on inputs like duration or resolution, and a quote made without them can be lower than the real charge.
get_balance読み取り専用Show the WaveSpeed account credit balance, with the link to top up.
list_predictions読み取り専用List past predictions (run history), newest window first. Defaults to the last 24 hours; pass since/until (ISO or YYYY-MM-DD) for other ranges. Use get_prediction with an id for one task in full.
list_billings読み取り専用List itemized charges and refunds (billing records). Requires an API key with Billing access.
| list_models | Search the live WaveSpeed model catalog (image, video, audio, 3D). Returns model IDs usable with run_model. Do not invent model IDs — always pick one returned by this tool. | 読み取り専用 |
| get_model_schema | Get a model's real input schema (required fields, properties, defaults). Call this before run_model so inputs match what the model actually accepts. | 読み取り専用 |
| run_model | Run any WaveSpeed model. input keys come from get_model_schema; unknown keys are rejected before submission. Local files: pass "@./path" in a media field (image, images, video, audio, mask …) — it is uploaded and replaced with hosted URLs (bare paths are NOT uploaded). Returns the prediction id right away (done=false); call get_prediction with that id and wait_seconds until done=true to get the output URLs. The task keeps running on the server. Pass wait_seconds here to wait for a quick model in the same call. | アクション |
| generate_image | Create an image from a text description with the same models as the WaveSpeed /chat page (seedream-5-5, seedream-5-pro, nano-banana-2.1, nano-banana-2, nano-banana-pro, gpt-image-2.6, gpt-image-2.5, gpt-image-2; default seedream-5-5). Give reference_images to use existing images as subject, product, face or style (the model's edit endpoint is used). To change existing images use edit_image. In the prompt, name input media as @image 1, @image 2, @video 1, @audio 1 (counted in the order the lists are given); they are renamed to what the model expects. | アクション |
| edit_image | Change existing images with the same models as the WaveSpeed /chat page: edits, restyles, backgrounds, adding or removing things, combining several images. In the prompt, name input media as @image 1, @image 2, @video 1, @audio 1 (counted in the order the lists are given); they are renamed to what the model expects. | アクション |
| generate_video | Create a video with the same models as the WaveSpeed /chat page (default seedance-2.5). Give first_frame to animate an image; give reference_images / reference_videos / reference_audios to keep characters, products, motion, voice or music. The right mode (text, image or reference to video) is picked from what you give. Videos can cost dollars: use estimate_only first when unsure. In the prompt, name input media as @image 1, @image 2, @video 1, @audio 1 (counted in the order the lists are given); they are renamed to what the model expects. | アクション |
| edit_video | Edit an existing video with the same models as the WaveSpeed /chat page. Name the video and any references in the prompt (e.g. "replace the cat in @video 1 with the lion from @image 1"). In the prompt, name input media as @image 1, @image 2, @video 1, @audio 1 (counted in the order the lists are given); they are renamed to what the model expects. | アクション |
| extend_video | Continue an existing video with new footage after its end, with the same models as the WaveSpeed /chat page (Seedance 2.5 Flash included). Turbo models, Flash Turbo too, cannot extend. In the prompt, name input media as @image 1, @image 2, @video 1, @audio 1 (counted in the order the lists are given); they are renamed to what the model expects. | アクション |
| get_price | Estimate the cost of a run before executing it (no charge). Provide the same input you would pass to run_model — pricing often depends on inputs like duration or resolution, and a quote made without them can be lower than the real charge. | アクション |
| get_balance | Show the WaveSpeed account credit balance, with the link to top up. | 読み取り専用 |
| list_predictions | List past predictions (run history), newest window first. Defaults to the last 24 hours; pass since/until (ISO or YYYY-MM-DD) for other ranges. Use get_prediction with an id for one task in full. | 読み取り専用 |
| list_billings | List itemized charges and refunds (billing records). Requires an API key with Billing access. | 読み取り専用 |
16個のツールをすべて表示ツールを折りたたむ
get_usage読み取り専用Usage statistics: spend, request counts, daily series and per-model breakdown. Defaults to the last 7 days. Requires an API key with Billing access.
delete_predictionsアクションDelete finished predictions from this account's run history, up to 100 at a time. This is a soft delete: each record stays, with status "deleted" and without its outputs, and list_predictions and get_prediction still return it that way; the output links are revoked (best effort). This tool cannot undo it. Runs that are still going are left alone, and only the key's own organization's records are deleted. Ask the user first, and pass confirm: true only after they agreed to delete these ids.
upload_fileアクションUpload a local file to WaveSpeed and get its hosted URL (identical bytes reuse the same upload for 24h). Usually unnecessary — run_model handles "@./path" inputs itself.
get_prediction読み取り専用Fetch the status and outputs of a past or in-flight prediction by id — use to pick up a run that returned done=false. Pass wait_seconds to keep waiting for it to finish.
| get_usage | Usage statistics: spend, request counts, daily series and per-model breakdown. Defaults to the last 7 days. Requires an API key with Billing access. | 読み取り専用 |
| delete_predictions | Delete finished predictions from this account's run history, up to 100 at a time. This is a soft delete: each record stays, with status "deleted" and without its outputs, and list_predictions and get_prediction still return it that way; the output links are revoked (best effort). This tool cannot undo it. Runs that are still going are left alone, and only the key's own organization's records are deleted. Ask the user first, and pass confirm: true only after they agreed to delete these ids. | アクション |
| upload_file | Upload a local file to WaveSpeed and get its hosted URL (identical bytes reuse the same upload for 24h). Usually unnecessary — run_model handles "@./path" inputs itself. | アクション |
| get_prediction | Fetch the status and outputs of a past or in-flight prediction by id — use to pick up a run that returned done=false. Pass wait_seconds to keep waiting for it to finish. | 読み取り専用 |
設定
WAVESPEED_API_KEYシークレットWaveSpeed API key (https://wavespeed.ai/accesskey). Optional when the wavespeed CLI is logged in.
WAVESPEED_BASE_URLOverride the WaveSpeed API base URL. Defaults to https://api.wavespeed.ai.
WAVESPEED_CLIENT_NAMEOverride the client name reported for channel attribution. Defaults to wavespeed-mcp.
| 名前 | 説明 | 種類 |
|---|---|---|
| WAVESPEED_API_KEY | WaveSpeed API key (https://wavespeed.ai/accesskey). Optional when the wavespeed CLI is logged in. | シークレット |
| WAVESPEED_BASE_URL | Override the WaveSpeed API base URL. Defaults to https://api.wavespeed.ai. | |
| WAVESPEED_CLIENT_NAME | Override the client name reported for channel attribution. Defaults to wavespeed-mcp. |
自動チェック
実行日 2026年11月16日完全なレポート →自動チェックに合格しました。これはセキュリティ監査ではありません。コードを読み、サーバーに必要最小限のアクセス権を与えてください。 チェックの仕組み
- ソースリポジトリがリンクされており、アクセス可能wavespeedai/mcp-server is public and reachablegithub.com/wavespeedai/mcp-server ↗合格
- パッケージがこのリポジトリをソースとして指定@wavespeed/mcp names wavespeedai/mcp-server as sourcenpmjs.com/package/@wavespeed/mcp ↗合格
- ビルドの来歴 (Sigstore 証明)Sigstore attestation for @wavespeed/mcpnpmjs.com/package/@wavespeed/mcp/v/1.2.14#provenance ↗合格
- オープンソースライセンス (OSI)MITspdx.org/licenses/MIT.html ↗合格
- 過去1年以内にコミットまたはリリースありLast commit or release 2026-11-15github.com/wavespeedai/mcp-server ↗合格
- OpenSSF Scorecard未チェック
- パッケージ名が有名なパッケージに酷似していないNo popular package one edit away from @wavespeed/mcp合格
- パッケージおよびその依存関係に重大な勧告なしthe package checked; no critical advisoryosv.dev ↗合格
- モデルへの隠れた指示がない16 tool descriptions and the README read; no override phrases, credential paths or hidden characters合格
- 破壊的なツールがラベル付けされているDestructive tools carry destructiveHint合格
- リモートエンドポイントが MCP ハンドシェイクに応答HTTPS endpoint answered 401 (sign-in required)合格
README
GitHubで見るWaveSpeed MCP Server
An MCP server for the WaveSpeed platform: run any model on the live catalog — image, video, audio, 3D — from Claude Code, Claude Desktop, Cursor, Cline, or any MCP client.
Built on the same design as the open-source @wavespeed/cli:
- No hardcoded models for
run_model. The catalog comes from the live API (1h cache); new platform models work the day they ship. - One general verb, five shortcuts.
run_modelexecutes anything;get_model_schematells the agent what inputs a model actually accepts, so it reads before it writes.generate_image,edit_image,generate_video,edit_videoandextend_videoskip that: they use the same models as the WaveSpeed /chat page, pick the endpoint for what you give them and fit the request to its live schema. - Inputs are never mutated. The one explicit transform is the
@pathmarker — a"@./photo.jpg"value insideinputuploads the file and substitutes its hosted URL. Bare paths are passed through untouched. The shortcut tools (generate_imageetc.) are the exception: they pick the endpoint and fit the request to the model, and report what they changed innotes. - Quote before you spend.
get_pricetakes the same input asrun_modeland returns an estimate; the amount actually charged for a run is authoritative.
Tools
| Tool | What it does |
|---|---|
list_models |
Search the live catalog by text or modality type |
get_model_schema |
A model's real input schema (required, properties, defaults), with a link to the model's playground page |
run_model |
Submit + wait; rejects input keys the model doesn't accept; @path inputs upload automatically; returns output URLs |
generate_image |
Image from a prompt with the /chat image models (default Seedream 5.5); reference images use the model's edit endpoint |
edit_image |
Edit, restyle or combine existing images with the same models |
generate_video |
Video from a prompt, a first/last frame or reference images/videos/audio, with the /chat video models (default Seedance 2.5); the mode (text, image, reference) is picked from the inputs |
edit_video |
Edit an existing video, optionally with reference images/audio |
extend_video |
Continue an existing video with new footage |
get_price |
Cost estimate for the inputs you pass (no charge), with a link to the model's playground page |
get_balance |
Account credit balance, with the top-up link |
list_predictions |
Run history (default last 24h); filter by model, status, time range |
list_billings |
Itemized charges and refunds (needs a Billing-access key) |
get_usage |
Spend, request counts and per-model breakdown (default last 7 days; needs a Billing-access key) |
delete_predictions |
Delete finished runs from the history (up to 100; needs confirm: true, cannot be undone from here) |
upload_file |
Local file → hosted URL (24h content-hash dedupe) |
get_prediction |
Status/outputs of any run by id; optional wait_seconds to wait for it |
The five shortcut tools take wait_seconds like run_model, and estimate_only: true returns the price and the exact request that would run without submitting or charging anything. In their prompts, media is named @image 1, @video 1, @audio 1 (in the order given); it is renamed to what each model expects. Models and defaults follow /chat: an unknown model is rejected, and a named model is never switched.
Some generations take minutes to hours. run_model submits the run and returns the prediction id right away (done: false); the assistant then calls get_prediction with that id and wait_seconds (max 1800) until done is true. The task keeps running server-side, so a dropped connection loses nothing. Pass wait_seconds to run_model to wait for a quick model in the same call. While waiting, both tools send MCP progress notifications that carry the prediction id.
Setup
Remote (nothing to install)
The same server is hosted at:
https://api.wavespeed.ai/mcp
-
Claude on the web / ChatGPT: add a custom connector with that address and approve the connection on the WaveSpeed page that opens. Approving creates a dedicated API key (named
MCP · <app>) that you can delete on the API Keys page to disconnect. -
Claude Code:
claude mcp add --transport http wavespeed https://api.wavespeed.ai/mcp -
Cursor:
-
VS Code:
code --add-mcp '{"name":"wavespeed","type":"http","url":"https://api.wavespeed.ai/mcp"}' -
Clients that only start local commands: connect through
mcp-remote, which opens the same browser approval on first start:{ "mcpServers": { "wavespeed": { "command": "npx", "args": ["-y", "mcp-remote", "https://api.wavespeed.ai/mcp"] } } } -
Any other client that sends request headers: point it at the URL with
Authorization: Bearer <your API key>.
The hosted server has the same tools, with one difference for files: it cannot read files on your computer, so pass public URLs, use create_upload from a tool that can send HTTP requests (it returns a temporary upload address and the download_url to use as an input), or, in ChatGPT, attach the file to the chat (the upload_attachment tool, which only ChatGPT can fill, imports it and returns a download_url). Full guide: wavespeed.ai/docs/mcp.
Local (npx)
@latest makes npx fetch the newest release on each start; without it, npx runs a globally installed @wavespeed/mcp if one exists, however old.
Auth resolves from WAVESPEED_API_KEY, or from the CLI's stored login (wavespeed login) — one login covers both tools. Keys: wavespeed.ai/accesskey.
Claude Code
claude mcp add wavespeed -- npx -y @wavespeed/mcp@latest
Claude Desktop / other clients (mcpServers config):
{
"mcpServers": {
"wavespeed": {
"command": "npx",
"args": ["-y", "@wavespeed/mcp@latest"],
"env": { "WAVESPEED_API_KEY": "wsk_..." }
}
}
}
Example prompts
- "Generate a 16:9 hero image of a cyberpunk skyline at golden hour."
- "Take ./photo.jpg and replace the background with a sunlit kitchen." (the agent passes
"@./photo.jpg") - "Animate ./hero.png with subtle parallax — check the price first."
Development
npm install
npm run dev # run from source (stdio)
npm run lint # typecheck
npm run build # tsc → dist/
License
WaveSpeed AI — AI image & video generation platform. Try it in the browser: Image generator · Video generator
WaveSpeed MCPのよくある質問
WaveSpeed MCPをClaude Codeに追加するには
ターミナルでclaude mcp add --env 'WAVESPEED_API_KEY=<YOUR_WAVESPEED_API_KEY>' mcp-server -- npx -y @wavespeed/mcpを実行します。すべてのプロジェクトで利用するには--scope userを追加します。
WaveSpeed MCPをCursorに追加するには
~/.cursor/mcp.jsonを開き、上記のインストールセクションに示すCursor設定を使ってmcpServersの下にサーバーを追加します。
WaveSpeed MCPが提供するツールは
16個のツールを提供しており、list_models, get_model_schema, run_model, generate_image, edit_imageなどがあります。
WaveSpeed MCPでの認証方法を教えてください。
ローカルサーバーの場合は、WAVESPEED_API_KEYまたは保存されたCLIログインからWaveSpeed APIキーを読み取ります。ホストされたクライアントの場合は、ブラウザ経由の接続を承認することで専用のAPIキーが作成されます。
実行前に生成コストを確認できますか?
はい、get_priceを使用すると、run_modelに渡すものと同じ入力値に基づいた見積もりを取得できます。これに料金は発生しません。実際に課金される金額は、実行時の確定値となります。
ローカルの画像をインプットとしてアップロードするにはどうすればよいですか?
入力値に @path マーカーを記述してください。サーバーがファイルをアップロードし、ホストされたURLに置き換えます。ホストされたサーバーを使用する場合は、create_uploadを使用するか、ChatGPTでファイルを添付してdownload_urlを取得してください。
このサーバーではどのモデルを実行できますか?
WaveSpeedのライブカタログにあるすべてのモデル(画像、動画、音声、3D)が対象です。カタログはライブAPIから取得され、1時間のキャッシュが適用されるため、新しいモデルがリリースされた当日には利用可能です。