Ejecuta modelos de imagen, video, audio y 3D desde el catálogo en vivo de WaveSpeed, con consulta de esquemas, estimaciones de precios e historial de ejecuciones.
También conocido como WaveSpeedAI/mcp-server, mcp-server, @wavespeed/mcp
- Stars
- 37
- Herramientas
- 16
- Descargas, 30 días
- —
- Última versión
- 1.2.15
- Último commit
- 10 nov 2026
- Licencia
- MIT
¿Qué es WaveSpeed MCP?
Ejecuta modelos de imagen, video, audio y 3D desde el catálogo en vivo de WaveSpeed, con consulta de esquemas, estimaciones de precios e historial de ejecuciones. Expone 16 herramientas, como list_models, get_model_schema, run_model.
Resumen generado a partir del README del proyecto
Acerca del MCP server de WaveSpeed
WaveSpeed permite ejecutar modelos de imagen, video, audio y 3D desde un catálogo en vivo directamente dentro de tu entorno de desarrollo de IA. Los desarrolladores que utilizan Claude Desktop, Cursor, Claude Code o Cline pueden acceder a una amplia variedad de modelos generativos sin necesidad de configuraciones manuales. El servidor se conecta a una API en vivo que actualiza su catálogo cada hora, asegurando que los nuevos modelos estén disponibles tan pronto como se lancen en la plataforma.
Los usuarios pueden interactuar con el catálogo mediante herramientas generales como run_model o atajos especializados como generate_image, edit_video y extend_video. El sistema gestiona las subidas de archivos automáticamente al usar el marcador @path para archivos locales. Para controlar los costos, la herramienta get_price proporciona estimaciones antes de cualquier ejecución. El servidor puede configurarse de forma remota mediante una URL alojada o localmente usando npx con una WAVESPEED_API_KEY. También ofrece capacidades administrativas como consultar el saldo de la cuenta, ver el historial de ejecuciones mediante list_predictions y revisar los detalles de facturación desglosados.
Qué puedes hacer con él
- 1Estimar costos de generaciónPide a la IA que verifique cuánto costará la ejecución de un modelo específico antes de enviar la solicitud.
- 2Automatizar la subida de archivos localesProporciona una ruta de archivo local a la IA para que se suba automáticamente y se utilice como entrada del modelo.
Escrito a partir del README del proyecto. Cada caso de uso se verifica con una cita del mismo.
Cómo instalar WaveSpeed MCP
Formatos verificados el 10 nov 2026Añadir a CursorAñadir a GooseInstalar WaveSpeed MCP en Claude Code
$ claude mcp add --env 'WAVESPEED_API_KEY=<YOUR_WAVESPEED_API_KEY>' mcp-server -- npx -y @wavespeed/mcpInstalar WaveSpeed MCP en Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"mcp-server": {
"command": "npx",
"args": [
"-y",
"@wavespeed/mcp"
],
"env": {
"WAVESPEED_API_KEY": "<YOUR_WAVESPEED_API_KEY>"
}
}
}
}Instalar WaveSpeed MCP en VS Code
.vscode/mcp.json
{
"servers": {
"mcp-server": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@wavespeed/mcp"
],
"env": {
"WAVESPEED_API_KEY": "<YOUR_WAVESPEED_API_KEY>"
}
}
}
}Instalar WaveSpeed MCP en VS Code CLI
$ code --add-mcp '{"name":"mcp-server","type":"stdio","command":"npx","args":["-y","@wavespeed/mcp"],"env":{"WAVESPEED_API_KEY":"<YOUR_WAVESPEED_API_KEY>"}}'Instalar WaveSpeed MCP en Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"mcp-server": {
"command": "npx",
"args": [
"-y",
"@wavespeed/mcp"
],
"env": {
"WAVESPEED_API_KEY": "<YOUR_WAVESPEED_API_KEY>"
}
}
}
}Instalar WaveSpeed MCP en Codex
$ codex mcp add mcp-server --env 'WAVESPEED_API_KEY=<YOUR_WAVESPEED_API_KEY>' -- npx -y @wavespeed/mcpInstalar WaveSpeed MCP en Codex config.toml
~/.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>"
Instalar WaveSpeed MCP en Gemini CLI
$ gemini mcp add -s user -e 'WAVESPEED_API_KEY=<YOUR_WAVESPEED_API_KEY>' mcp-server npx -- -y @wavespeed/mcpInstalar WaveSpeed MCP en Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"mcp-server": {
"command": "npx",
"args": [
"-y",
"@wavespeed/mcp"
],
"env": {
"WAVESPEED_API_KEY": "<YOUR_WAVESPEED_API_KEY>"
}
}
}
}Iniciado por HostedMCP el 16 nov 2026
Ejecutamos este comando para @wavespeed/mcp 1.2.15 en un contenedor aislado sin red ni claves. Respondió y listó 16 herramientas.
Herramientas de WaveSpeed MCP 16
Leído del servidor con tools/listlist_modelsSolo lecturaSearch 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_schemaSolo lecturaGet a model's real input schema (required fields, properties, defaults). Call this before run_model so inputs match what the model actually accepts.
run_modelAcciónRun 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_imageAcciónCreate 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_imageAcciónChange 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_videoAcciónCreate 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_videoAcciónEdit 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_videoAcciónContinue 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_priceAcciónEstimate 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_balanceSolo lecturaShow the WaveSpeed account credit balance, with the link to top up.
list_predictionsSolo lecturaList 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_billingsSolo lecturaList 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. | Solo lectura |
| 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. | Solo lectura |
| 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. | Acción |
| 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. | Acción |
| 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. | Acción |
| 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. | Acción |
| 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. | Acción |
| 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. | Acción |
| 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. | Acción |
| get_balance | Show the WaveSpeed account credit balance, with the link to top up. | Solo lectura |
| 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. | Solo lectura |
| list_billings | List itemized charges and refunds (billing records). Requires an API key with Billing access. | Solo lectura |
Mostrar las 16 herramientasMostrar menos herramientas
get_usageSolo lecturaUsage statistics: spend, request counts, daily series and per-model breakdown. Defaults to the last 7 days. Requires an API key with Billing access.
delete_predictionsAcciónDelete 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_fileAcciónUpload 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_predictionSolo lecturaFetch 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. | Solo lectura |
| 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. | Acción |
| 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. | Acción |
| 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. | Solo lectura |
Configuración
WAVESPEED_API_KEYSecretoWaveSpeed 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.
| Nombre | Descripción | Tipo |
|---|---|---|
| WAVESPEED_API_KEY | WaveSpeed API key (https://wavespeed.ai/accesskey). Optional when the wavespeed CLI is logged in. | Secreto |
| 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. |
Verificaciones automáticas
Ejecutado 16 nov 2026Informe completo →Pasó nuestras verificaciones automáticas. Esto no es una auditoría de seguridad: lee el código y dale al servidor el acceso más limitado que necesite. Cómo funcionan las verificaciones
- Repositorio de origen vinculado y accesiblewavespeedai/mcp-server is public and reachablegithub.com/wavespeedai/mcp-server ↗Aprobado
- El paquete indica este repositorio como su origen@wavespeed/mcp names wavespeedai/mcp-server as sourcenpmjs.com/package/@wavespeed/mcp ↗Aprobado
- Procedencia de la compilación (atestación de Sigstore)Sigstore attestation for @wavespeed/mcpnpmjs.com/package/@wavespeed/mcp/v/1.2.14#provenance ↗Aprobado
- Licencia de código abierto (OSI)MITspdx.org/licenses/MIT.html ↗Aprobado
- Commit o lanzamiento en el último añoLast commit or release 2026-11-15github.com/wavespeedai/mcp-server ↗Aprobado
- OpenSSF ScorecardNo verificado
- El nombre del paquete no es similar a un paquete popularNo popular package one edit away from @wavespeed/mcpAprobado
- No hay avisos críticos en el paquete ni en sus dependenciasthe package checked; no critical advisoryosv.dev ↗Aprobado
- Sin instrucciones ocultas para el modelo16 tool descriptions and the README read; no override phrases, credential paths or hidden charactersAprobado
- Las herramientas destructivas están etiquetadasDestructive tools carry destructiveHintAprobado
- El endpoint remoto responde al handshake de MCPHTTPS endpoint answered 401 (sign-in required)Aprobado
README
Ver en GitHubWaveSpeed 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
Preguntas sobre WaveSpeed MCP
¿Cómo agrego WaveSpeed MCP a Claude Code?
Ejecuta claude mcp add --env 'WAVESPEED_API_KEY=<YOUR_WAVESPEED_API_KEY>' mcp-server -- npx -y @wavespeed/mcp en tu terminal. Añade --scope user para que esté disponible en todos los proyectos.
¿Cómo agrego WaveSpeed MCP a Cursor?
Abre ~/.cursor/mcp.json y añade el servidor en mcpServers, usando la configuración de Cursor que se muestra en la sección de instalación de arriba.
¿Qué herramientas proporciona WaveSpeed MCP?
Expone 16 herramientas, incluidas list_models, get_model_schema, run_model, generate_image, edit_image.
¿Cómo me autentico con WaveSpeed MCP?
El servidor local lee una clave de API de WaveSpeed desde WAVESPEED_API_KEY o el inicio de sesión guardado en el CLI; los clientes alojados aprueban una conexión de navegador que crea una clave de API dedicada.
¿Puedo consultar el costo de una generación antes de ejecutarla?
Sí, get_price devuelve una estimación para los mismos parámetros que pasarías a run_model, sin realizar ningún cargo. El monto cobrado finalmente por una ejecución es el valor definitivo.
¿Cómo subo una imagen local para usarla como entrada?
Coloca un marcador @path como valor de entrada y el servidor subirá el archivo sustituyéndolo por su URL alojada. En el servidor alojado, usa create_upload o adjunta el archivo en ChatGPT para obtener un download_url.
¿Qué modelos puedo ejecutar a través de este servidor?
Cualquier modelo del catálogo en vivo de WaveSpeed, que incluye imagen, video, audio y 3D. El catálogo se obtiene de la API en tiempo real con un caché de 1 hora, por lo que los nuevos modelos funcionan el mismo día de su lanzamiento.