WAVE MCP Server
OfficialThe WAVE MCP server exposes WAVE streaming APIs as MCP tools for AI coding assistants, enabling management across 5 domains:
Stream Management
List, create, start, and stop streams (with status filtering and pagination)
Create streams with protocol (
webrtc,srt,rtmp,hls), region, recording, and description optionsMonitor real-time stream health: bitrate, frame rate, and latency
Studio / Productions
List and create multi-camera studio productions (with layout options:
single,split,pip,grid,custom)Switch live program output between camera sources with transition effects (
cut,mix,wipe,dve)Control PTZ cameras: pan, tilt, zoom, focus, and recall/store presets
Show, hide, or update HTML5 graphics overlays on a production
Analytics
Get current viewer counts and optional geographic/device demographics per stream or account-wide
Retrieve detailed stream performance metrics (bitrate, latency, quality scores, error rates) over configurable time periods and granularity
Billing & Usage
View current subscription plan, billing cycle, and feature entitlements
Check billing-period consumption (streaming minutes, storage, bandwidth) with summary or detailed breakdowns
Production Tools
Create clips from recorded streams by time range, with optional export to TikTok, YouTube Shorts, Instagram Reels, or Twitter
Mark highlights in a live stream for later clipping (with optional AI confidence score)
Moderate live chat messages: block, flag, or allow with an optional reason
Start real-time captions/transcription using Deepgram, AssemblyAI, or Cohere
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@WAVE MCP ServerCheck the health and viewer count of my active stream"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
@wave-av/mcp-server
MCP (Model Context Protocol) server that exposes WAVE streaming APIs as tools for AI coding assistants (Claude Code, Cursor, Windsurf).
Live → · docs · npm · repo · Docs · Status
This README is machine-generated from WAVE's grounded Single Source of Truth — every factual claim below traces to a resolver that
npm run verifychecks against the live repo and live endpoints. Nothing here is asserted without a receipt.
Quick start
npx @wave-av/mcp-server{
"mcpServers": {
"wave": {
"command": "npx",
"args": ["-y", "@wave-av/mcp-server"],
"env": {
"WAVE_API_KEY": "wave_live_..."
}
}
}
}Related MCP server: ASTRA MCP Server
Setup
1. Get an API key
# Via CLI
wave auth login
# Or create at https://wave.online/settings/api-keys2. Configure your AI tool
Add to your .mcp.json (Claude Code, Cursor, Windsurf, etc.) — see the Quick start config above.
Available tools — Streams
Tool | Description |
| List all streams with pagination and status filtering |
| Create a new stream with protocol and privacy options |
| Start streaming on an existing stream |
| Stop an active stream |
| Get real-time health metrics for a stream |
Available tools — Studio
Tool | Description |
| List studio production sessions |
| Create a new multi-camera production |
Available tools — Analytics
Tool | Description |
| Get current viewer count and breakdown |
| Get detailed stream performance metrics |
Available tools — Billing
Tool | Description |
| Get current subscription plan and status |
| Get current period usage and limits |
Resources
Access WAVE entities directly via the wave:// URI scheme:
wave://streams/{id}- Stream configuration and statuswave://productions/{id}- Studio production details
Environment variables
Variable | Required | Default | Description |
| Yes | - | Your WAVE API key |
| No |
| API base URL |
In-process (Claude Agent SDK) mode
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-sdkimport { 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
}Setup for other AI tools
Cursor
Add to .cursor/mcp.json:
{
"mcpServers": {
"wave": {
"command": "npx",
"args": ["-y", "@wave-av/mcp-server"],
"env": { "WAVE_API_KEY": "wave_live_..." }
}
}
}Windsurf
Add to Windsurf MCP settings with the same configuration.
Troubleshooting
Server not starting
Verify your API key is set:
echo $WAVE_API_KEYTools not appearing
Restart your AI tool after adding the MCP configuration. Most tools require a restart to detect new MCP servers.
Connection errors
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 --versionTesting the server
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-serverRelated packages
@wave-av/sdk — TypeScript SDK (34 API modules)
@wave-av/adk — Agent Developer Kit
@wave-av/cli — Command-line interface
@wave-av/create-app — Scaffold a new project
OpenAPI spec — Full API specification
Development
cd packages/mcp-server
pnpm install
pnpm run build
pnpm run dev # Watch mode
pnpm run type-checkLicense
MIT
Capabilities
Capability | Status |
Control a PTZ camera (pan, tilt, zoom, focus, preset recall/store). | |
Create a clip from a recorded stream, optionally exporting to social platforms. | |
Create a new multi-camera studio production. | |
Create a new stream (protocol, recording, region options). | |
Get real-time stream health metrics (bitrate, frame rate, latency). | |
Get detailed stream performance metrics (bitrate, latency, quality, error rates). | |
Get current subscription plan, billing cycle, and feature entitlements. | |
Get current billing-period usage (streaming minutes, storage, bandwidth). | |
Get current viewer count and viewer demographics for a stream or account-wide. | |
List all studio productions in the WAVE account. | |
List all streams in the WAVE account with pagination and status filtering. | |
Mark a moment in a stream as a highlight for later clipping. | |
Moderate a chat message in a live stream (block, flag, or allow). | |
Show, hide, or update an HTML5 graphics overlay on a production. | |
Start real-time captions/transcription on a stream. | |
Start a stream by ID, transitioning it to the active state. | |
Stop an active stream by ID. | |
Switch the live program output to a different camera/source in a Cloud Switcher session. |
For AI agents
Exposes the MCP tool wave-mcp-server over stdio.
The receipts
Every claim below is checked by npm run verify against the live repo or endpoint — a non-pass verdict fails the gate.
Claim | How it's verified |
Documentation surface is docs.wave.online/mcp | resolved by grepping |
Published npm package name is @wave-av/mcp-server | resolved by grepping |
wave_control_camera tool defined in src/tools/production.ts | resolved by grepping |
Exposes 18 MCP tools | resolved by grepping |
wave_create_clip tool defined in src/tools/production.ts | resolved by grepping |
wave_create_production tool defined in src/tools/studio.ts | resolved by grepping |
wave_create_stream tool defined in src/tools/streams.ts | resolved by grepping |
wave_get_viewers tool defined in src/tools/analytics.ts | resolved by grepping |
wave_list_productions tool defined in src/tools/studio.ts | resolved by grepping |
wave_list_streams tool defined in src/tools/streams.ts | resolved by grepping |
wave_mark_highlight tool defined in src/tools/production.ts | resolved by grepping |
wave_moderate_chat tool defined in src/tools/production.ts | resolved by grepping |
wave_show_graphic tool defined in src/tools/production.ts | resolved by grepping |
wave_start_captions tool defined in src/tools/production.ts | resolved by grepping |
wave_start_stream tool defined in src/tools/streams.ts | resolved by grepping |
wave_stop_stream tool defined in src/tools/streams.ts | resolved by grepping |
wave_get_stream_health tool defined in src/tools/streams.ts | resolved by grepping |
wave_get_stream_metrics tool defined in src/tools/analytics.ts | resolved by grepping |
wave_get_subscription tool defined in src/tools/billing.ts | resolved by grepping |
wave_switch_camera tool defined in src/tools/production.ts | resolved by grepping |
wave_get_usage tool defined in src/tools/billing.ts | resolved by grepping |
Server connects via stdio transport (no network listener) | resolved by grepping |
Topics
wave · mcp · model-context-protocol · ai · streaming · tools
Built by WAVE Online, LLC · wave.online · Docs · LinkedIn
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseAqualityFmaintenanceEnables management of multi-platform streaming through the Restream API, allowing control of streaming channels, stream settings, and access to analytics across platforms like YouTube, Twitch, and Facebook through natural language.Last updated9171MIT
- AlicenseCqualityCmaintenanceEnables AI assistants to query and control a bio-hybrid neuromorphic simulation pipeline, including SNN engine, consciousness proxies, and neuroplatform telemetry, via the Model Context Protocol.Last updated50MIT

APIVerve MCP Serverofficial
Alicense-qualityBmaintenanceProvides access to 249+ production-ready APIs through the Model Context Protocol, enabling AI assistants to fetch weather, news, geocoding, validation, and more data.Last updated22MIT- Alicense-qualityCmaintenanceEnables AI assistants to control YouTube Live Streaming, including creating broadcasts, managing chat, and monitoring stream health via MCP tools.Last updated30MIT
Related MCP Connectors
16 AI-native tools with dual SSE + streamable-http transport. Free tier available.
AI Reasoning Cache & Consensus Layer with 11 MCP tools via Streamable HTTP.
Manage SRG+ hubs, channels, content, assets, users, and workspaces from any MCP-aware AI agent.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/wave-av/mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server