webrtc-mcp-server
Enables peer-to-peer WebRTC communication between AI agents, with room-based signaling, video stream bridging (RTSP/HLS/RTMP to WebRTC), and multi-agent coordination via MCP tools.
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., "@webrtc-mcp-serverJoin the 'alpha' room and broadcast a greeting to all peers."
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.
WebRTC MCP Server
Peer-to-peer WebRTC communication for AI agents. Connects autonomous coding agents over low-latency WebRTC DataChannels with room-based signaling, video stream bridging, and multi-agent coordination — all exposed as MCP tools.
TL;DR
npm install && npm run build
# As MCP server (stdio)
node dist/index.js
# As WebSocket signaling server (for external peers)
WEBRTC_SIGNALING_MODE=ws WEBRTC_WS_PORT=8765 node dist/index.jsFeature | Detail |
Protocol | MCP v2025-03-26 (over stdio), WebSocket signaling |
Tools | 16 MCP tools — peers, rooms, streams, signaling, health |
Concurrency | Worker Thread pool (default 8, max 16) |
Latency | 0.82ms avg signaling RTT (measured) |
Sources | RTSP, HLS, RTMP, WebRTC (auto-detect) |
Tests | 14/14 passing |
Related MCP server: slm-mesh
What It Does
Multi-Agent Communication
Connect AI agents (Claude Code, OpenCode, Cursor, and any MCP client) over WebRTC DataChannels. Each agent becomes a peer that can:
Join named rooms for group communication
Send structured messages (JSON) with ACK
Broadcast to all peers in a room
Relay SDP/ICE for WebRTC handshake
webrtc_connect creates a real RTCPeerConnection + DataChannel (SDP offer generated by @roamhq/wrtc, signaled automatically to the peer over the WebSocket channel). Once connected, webrtc_send delivers messages over the DataChannel (P2P), falling back to WS relay only if no WebRTC connection exists.
Note:
@roamhq/wrtc(libwebrtc native binding) is not thread-safe — creating anRTCPeerConnectioninside a worker_thread crashes V8 ("HandleScope Entering the V8 API without proper locking"). All WebRTC connections therefore live in the main process thread (WebRTCConnectionManager); the worker pool remains for CPU-bound tasks.
Video Streams
Bridge RTSP/HLS/RTMP video streams to WebRTC for real-time frame access:
webrtc_connect_stream(url)→ creates RTCPeerConnection + offer SDPwebrtc_frame_get(stream_id)→ returns latest frame as base64 JPEGwebrtc_stream_status(stream_id)→ health, FPS, throughput metricsFFmpeg-backed decoding with ring-buffer frame cache
Room-Based Signaling
WebSocket server (ws://host:port) for external peers:
join/leave/list_peers— room membershipsignal— SDP/ICE relay between peersbroadcast— fan-out messages to all room membersping/pong— health check
Quick Start
As a standalone server
# stdio mode (MCP transport)
WEBRTC_SIGNALING_MODE=stdio node dist/index.js
# WebSocket signaling mode (for external peers)
WEBRTC_SIGNALING_MODE=ws WEBRTC_WS_PORT=8765 node dist/index.js
# Both modes simultaneously
WEBRTC_SIGNALING_MODE=both node dist/index.jsAs an MCP server (Claude Desktop / Cursor / any MCP client)
{
"mcpServers": {
"webrtc": {
"command": "node",
"args": ["/path/to/dist/index.js"],
"env": {
"WEBRTC_SIGNALING_MODE": "stdio"
}
}
}
}External peer via WebSocket
// Node.js client
const ws = new WebSocket('ws://127.0.0.1:8765');
ws.on('open', () => {
ws.send(JSON.stringify({
type: 'join',
peerId: 'peer-a',
room: 'my-room'
}));
});MCP Tools
Peer Communication (6 tools)
Tool | Description |
| Create RTCPeerConnection + DataChannel with a peer |
| Close connection and release resources |
| Send structured message via DataChannel |
| Broadcast to all peers in a room |
| List all connected peers |
| Detailed status of a specific peer |
Rooms (4 tools)
Tool | Description |
| Create a new signaling room |
| Join a peer to a room |
| Leave a room |
| Relay SDP/ICE candidates between peers |
Video Streams (5 tools)
Tool | Description |
| Connect RTSP/HLS/RTMP source → WebRTC offer |
| Get latest frame as base64 (cached, no re-encode) |
| List all active streams with health metrics |
| Detailed streaming metrics (FPS, throughput) |
| Close a video stream |
Health (1 tool)
Tool | Description |
| Overall server health (peers, rooms, workers, uptime) |
Configuration
All config via environment variables or config.yaml:
Variable | Default | Description |
|
|
|
| 8 | Max concurrent worker threads (≤16) |
| 5 | Frames cached per stream (ring buffer) |
| 500000 | Max JPEG payload (~480KB @ 1920×1080) |
| 30 | Connection timeout in seconds |
| 8765 | WebSocket signaling port |
| 127.0.0.1 | WebSocket bind address |
| warn |
|
| stun:stun.l.google.com:19302 | STUN server |
| (auto) | Comma-separated URL allowlist |
See config.yaml for the full default configuration with TURN, rate limiting, and ICE restart settings.
Multi-Agent Workflow
1. Agent A: webrtc_create_room("team-sync") → A = principal (líder)
2. Agent B: {type:"join", peerId:"agent-b", room:"team-sync"} ← WebSocket
3. Agent A: webrtc_connect(peerId="agent-b") → RTCPeerConnection REAL + DataChannel
(offer SDP auto-relayeado a B por WS)
4. B: acceptOffer → {type:"signal", to:"host", sdp:answer} → ICE → connected
5. A → B: webrtc_send(peerId="agent-b", data={"task":"review","file":"src/index.ts"}) ← DataChannel P2P
6. B → A: webrtc_send(peerId="agent-a", data={"result":"✅ no issues"})
7. Broadcast: webrtc_broadcast(data={"type":"status","msg":"deploying"})Video Stream Workflow
1. webrtc_connect_stream(url="rtsp://camera.local:554/stream1")
→ {stream_id: "cam-123", offer_sdp: "...", ice_servers: [...]}
2. webrtc_frame_get(stream_id="cam-123")
→ {frame: "base64...", timestamp: 1753785600000, resolution: {width:1920, height:1080}}
3. vision_analyze(image="data:image/jpeg;base64,...", question="¿Hay personas?")
→ "Sí, 2 personas detectadas"Frames are cached in a thread-safe ring buffer — repeated frame_get calls return the same buffer without re-encoding.
Architecture
┌─────────────────────────────────────────────────────────┐
│ MCP CLIENT (Claude Desktop, Cursor, any MCP host) │
│ MCP stdio transport: node dist/index.js │
├─────────────────────────────────────────────────────────┤
│ MCP Protocol Handler (v2025-03-26) │
│ → tools/list, tools/call → dispatch │
├─────────────────────────────────────────────────────────┤
│ WebSocket Signaling Server (ws://127.0.0.1:8765) │
│ → join/leave/list_peers/ping/broadcast/signal │
├─────────────────────────────────────────────────────────┤
│ Worker Thread Pool (8 concurrent, round-robin) │
│ ├─ Worker 1: RTCPeerConnection + DataChannel │
│ ├─ Worker 2: RTSP/FFmpeg → WebRTC bridge │
│ └─ Worker N: isolated per peer/stream │
├─────────────────────────────────────────────────────────┤
│ FFmpeg Bridge │
│ RTSP/HLS/RTMP → raw frames → JPEG (via sharp) │
│ FrameCache: thread-safe ring buffer (5 frames) │
└─────────────────────────────────────────────────────────┘Development
npm install # install dependencies
npm run build # TypeScript → dist/
npm run dev # watch mode (tsx)
npm test # 14 tests (vitest)
npm run typecheck # tsc --noEmit
npm run lint # eslintTests
Test Files 2 passed (2)
Tests 14 passed (14)File | Tests |
| 9 tests — room join/leave, peer management, broadcast |
| 5 tests — SDP/ICE routing, health checks |
License
MIT — see LICENSE.
WebRTC is the industry standard for real-time P2P communication (used by Zoom, Google Meet, Discord). This server brings that capability to the MCP ecosystem for multi-agent collaboration.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
No tool schema history has been recorded yet.
This server cannot be installed
Maintenance
Related MCP Connectors
Real-time chat for AI agents. Claude Code, Cursor, Cline and Codex join channels over MCP.
Agent-native collaboration network: orchestrate a team of long-running agents from any MCP client.
End-to-end encrypted messaging and work coordination for autonomous AI agents.
271One MCP endpoint for Claude, GPT & Gemini: 100+ tools + no-code connectors + agent workers.
Related MCP Servers
- AlicenseBqualityAmaintenanceBuild production-grade multi-agent communication infrastructure in minutes. Real-time messaging, task scheduling, shared memory, and trust-based evolution — all via MCP + SSE.582675MIT
- AlicenseNot gradedqualityCmaintenanceEnables peer-to-peer communication, discovery, shared state, and file coordination between AI coding agents across machines and sessions.2819Elastic 2.0
- AlicenseNot gradedqualityBmaintenanceEnables AI assistants to have voice conversations and screen sharing capabilities via WebRTC, using Pipecat for speech-to-text and text-to-speech.BSD 2-Clause "Simplified"
- AlicenseNot gradedqualityBmaintenanceShared rooms for AI agents (AgentsChat): channels, DMs, proposals & voting, OKR trees, and human handoff. Existing MCP clients (Claude Code, Cursor, and others) join live rooms instead of building a crew from scratch.Apache 2.0
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/Stuko0/webrtc-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server