npm @wavespeed/mcpstdioMITupdated 9d ago
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.
wavespeed 能做什么?
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. The catalog comes from the live API (1h cache); new platform models work the day they ship.
- One generation verb.
run_modelexecutes anything;get_model_schematells the agent what inputs a model actually accepts, so it reads before it writes. - 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. - Honest pricing.
get_pricequotes before you spend and names the inputs the quote was blind to (unpriced_inputs) instead of presenting a formula's floor as "the" price.
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) |
run_model |
Submit + wait; @path inputs upload automatically; returns output URLs |
get_price |
Cost estimate with unpriced_inputs / at_base_price disclosure |
get_balance |
Account credit balance |
upload_file |
Local file → hosted URL (24h content-hash dedupe) |
get_prediction |
Recover status/outputs of any run by id |
If run_model hits its wait limit the task keeps running server-side — the error names the prediction id, and get_prediction picks it up.
Setup
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
Claude Desktop / other clients (mcpServers config):
{
"mcpServers": {
"wavespeed": {
"command": "npx",
"args": ["-y", "@wavespeed/mcp"],
"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
安装
把 wavespeed 添加到你的客户端。选择你正在使用的那个。
claude mcp add mcp -- npx -y @wavespeed/mcpcodex mcp add mcp -- npx -y @wavespeed/mcpamp mcp add mcp -- npx -y @wavespeed/mcp{
"mcpServers": {
"mcp": {
"command": "npx",
"args": [
"-y",
"@wavespeed/mcp"
]
}
}
}Add to `claude_desktop_config.json`, then restart Claude Desktop.
{
"mcpServers": {
"mcp": {
"command": "npx",
"args": [
"-y",
"@wavespeed/mcp"
]
}
}
}Add to `~/.cursor/mcp.json`, or `.cursor/mcp.json` for a single project.
code --add-mcp '{"name":"mcp","command":"npx","args":["-y","@wavespeed/mcp"]}'Or add the block manually to `.vscode/mcp.json` under `servers`.
{
"mcpServers": {
"mcp": {
"command": "npx",
"args": [
"-y",
"@wavespeed/mcp"
]
}
}
}Add to `~/.codeium/windsurf/mcp_config.json`.
{
"mcpServers": {
"mcp": {
"command": "npx",
"args": [
"-y",
"@wavespeed/mcp"
]
}
}
}Add to `cline_mcp_settings.json` via the MCP Servers panel.
{
"mcpServers": {
"mcp": {
"command": "npx",
"args": [
"-y",
"@wavespeed/mcp"
]
}
}
}Add to `~/.gemini/settings.json`.
{
"mcpServers": {
"mcp": {
"type": "local",
"command": "npx",
"args": [
"-y",
"@wavespeed/mcp"
],
"tools": [
"*"
]
}
}
}Add to `~/.copilot/mcp-config.json`, or run `/mcp add` inside the CLI.
{
"context_servers": {
"mcp": {
"command": {
"path": "npx",
"args": [
"-y",
"@wavespeed/mcp"
]
}
}
}
}Add to your Zed `settings.json`.
npx -y @wavespeed/mcpRun `goose configure`, choose **Add Extension → Command-line Extension**, and paste this command.
7 个工具
wavespeed 向已连接的智能体提供 7 个工具。
- list_models
- Search the live catalog by text or modality type
- get_model_schema
- A model's real input schema (required, properties, defaults)
- run_model
- Submit + wait; `@path` inputs upload automatically; returns output URLs
- get_price
- Cost estimate with `unpriced_inputs` / `at_base_price` disclosure
- get_balance
- Account credit balance
- upload_file
- Local file → hosted URL (24h content-hash dedupe)
- get_prediction
- Recover status/outputs of any run by id
评分
81 / 100
优秀
- 文档22/25
- 维护25/25
- 可信度16/20
- 能力6/15
- 安装体验12/15
- Documents what it does and how to connect
- Has a resolvable package or endpoint
- Exposes at least one tool, prompt or resource
- README has substantive content
- Includes a code example
- Documents its configuration
- Mentions credentials or security posture
- Last commit 1 days ago
- Has a release history
- Repository is not archived
- Licensed MIT
- Namespace verified in the official MCP registry
- Claimed by its owner
- Published under an organisation
- 7 tool(s) documented
- Provides prompt templates
- Provides resources
- 12 documented install method(s)
- Published to a package registry
- Offers a hosted endpoint — no local install
版本历史
| 版本 | 发布于 |
|---|---|
| 1.0.7最新 | 2026年8月26日 |
| 1.0.6 | 2026年8月20日 |
| 1.0.5 | 2026年8月20日 |
| 1.0.4 | 2026年8月19日 |
| 1.0.2 | 2026年8月19日 |