loading…
Search for a command to run...
loading…
Exposes WAVE streaming APIs as tools for AI assistants to manage live streams, studio productions, and real-time analytics. It enables users to control stream l
Exposes WAVE streaming APIs as tools for AI assistants to manage live streams, studio productions, and real-time analytics. It enables users to control stream lifecycles, monitor health metrics, and access billing usage through the Model Context Protocol.
npm version npm downloads license
MCP (Model Context Protocol) server that exposes WAVE streaming APIs as tools for AI coding assistants.
npx @wave-av/mcp-server
# Via CLI
wave auth login
# Or create at https://wave.online/settings/api-keys
Add to your .mcp.json (Claude Code, Cursor, Windsurf, etc.):
{
"mcpServers": {
"wave": {
"command": "npx",
"args": ["-y", "@wave-av/mcp-server"],
"env": {
"WAVE_API_KEY": "wave_live_..."
}
}
}
}
| Tool | Description |
|---|---|
wave_list_streams |
List all streams with pagination and status filtering |
wave_create_stream |
Create a new stream with protocol and privacy options |
wave_start_stream |
Start streaming on an existing stream |
wave_stop_stream |
Stop an active stream |
wave_get_stream_health |
Get real-time health metrics for a stream |
| Tool | Description |
|---|---|
wave_list_productions |
List studio production sessions |
wave_create_production |
Create a new multi-camera production |
| Tool | Description |
|---|---|
wave_get_viewers |
Get current viewer count and breakdown |
wave_get_stream_metrics |
Get detailed stream performance metrics |
| Tool | Description |
|---|---|
wave_get_subscription |
Get current subscription plan and status |
wave_get_usage |
Get current period usage and limits |
Access WAVE entities directly via the wave:// URI scheme:
wave://streams/{id} - Stream configuration and statuswave://productions/{id} - Studio production details| Variable | Required | Default | Description |
|---|---|---|---|
WAVE_API_KEY |
Yes | - | Your WAVE API key |
WAVE_BASE_URL |
No | https://wave.online |
API base URL |
For consumers already running inside a Claude Agent SDK
session, the same tools are available in-process — skipping the stdio subprocess
hop (~50 ms vs ~500 ms cold start). The tool list is shared with the stdio
server (src/tools/index.ts), so the two transports never drift.
@anthropic-ai/claude-agent-sdk is an optional peer dependency: stdio users
never need it. Install it only for this mode:
npm install @wave-av/mcp-server @anthropic-ai/claude-agent-sdk
import { query } from "@anthropic-ai/claude-agent-sdk";
import { createWaveSdkMcpServer } from "@wave-av/mcp-server/sdk-server";
const wave = await createWaveSdkMcpServer();
for await (const message of query({
prompt: "List my active streams",
options: { mcpServers: { wave }, env: { WAVE_API_KEY: process.env.WAVE_API_KEY } },
})) {
// handle messages
}
Add to .cursor/mcp.json:
{
"mcpServers": {
"wave": {
"command": "npx",
"args": ["-y", "@wave-av/mcp-server"],
"env": { "WAVE_API_KEY": "wave_live_..." }
}
}
}
Add to Windsurf MCP settings with the same configuration.
Verify your API key is set:
echo $WAVE_API_KEY
Restart your AI tool after adding the MCP configuration. Most tools require a restart to detect new MCP servers.
The MCP server uses stdio transport (no network listener). If you see connection errors, check that npx can run successfully:
npx @wave-av/mcp-server --version
Send a JSON-RPC initialize request to verify:
echo '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"test","version":"1.0.0"}}}' | npx @wave-av/mcp-server
cd packages/mcp-server
pnpm install
pnpm run build
pnpm run dev # Watch mode
pnpm run type-check
MIT
Выполни в терминале:
claude mcp add wave-mcp-server -- npx CSA PROJECT - FZCO © 2026 IFZA Business Park, DDP, Premises Number 31174 - 001
Безопасность
Низкий рискАвтоматическая эвристика по публичным данным — не гарантия безопасности.