Run any model on the live WaveSpeed catalog: image, video, audio, 3D.
ai.wavespeed/mcp (WaveSpeed MCP Server)
The ai.wavespeed/mcp server runs models on the live WaveSpeed catalog. It supports generating and working with image, video, audio, and 3D content. The server is associated with the Model Context Protocol (MCP) and is listed under the WaveSpeed ecosystem.
An MCP server for the WaveSpeed platform: run any model on the live catalog โ image, video, audio, 3D โ 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_model executes anything; get_model_schema tells the agent what inputs a model actually accepts, so it reads before it writes. generate_image, edit_image, generate_video, edit_video and extend_video skip 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 @path marker โ a "@./photo.jpg" value inside input uploads the file and substitutes its hosted URL. Bare paths are passed through untouched. The shortcut tools (generate_image etc.) are the exception: they pick the endpoint and fit the request to the model, and report what they changed in notes.
Quote before you spend.get_price takes the same input as run_model and 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 โ 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:
text
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 ยท <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:
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) โ one login covers both tools. Keys: wavespeed.ai/accesskey.
Claude Code
bash
claude mcp add wavespeed -- npx -y @wavespeed/mcp@latest
Claude Desktop / other clients (mcpServers config):