mcp for VS Code
ai.wavespeed/mcp
Run any model on the live WaveSpeed catalog: image, video, audio, 3D.
client:VS Code
transport:stdio
runtime:npm
Install mcp in VS Code
.vscode/mcp.json
{
"inputs": [
{
"type": "promptString",
"id": "wavespeed-api-key",
"description": "WAVESPEED_API_KEY",
"password": true
},
{
"type": "promptString",
"id": "wavespeed-base-url",
"description": "WAVESPEED_BASE_URL",
"password": true
},
{
"type": "promptString",
"id": "wavespeed-client-name",
"description": "WAVESPEED_CLIENT_NAME",
"password": true
}
],
"servers": {
"mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@wavespeed/mcp"
],
"env": {
"WAVESPEED_API_KEY": "${input:wavespeed-api-key}",
"WAVESPEED_BASE_URL": "${input:wavespeed-base-url}",
"WAVESPEED_CLIENT_NAME": "${input:wavespeed-client-name}"
}
}
}
}
VS Code prompts for each input the first time the server starts, so no secret is written to the file. VS Code docs