
Dazzle - Agentic Streaming
@dazzle-labs
About Dazzle - Agentic Streaming
Cloud streaming for AI agents — isolated browser environments that render and broadcast your content to Twitch, Kick, Restream, and custom RTMP.
Basic information
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"dazzle": {
"command": "npx",
"args": [
"@dazzle-labs/cli",
"mcp"
]
}
}
}Tools
8Run a dazzle CLI command. Use ["--help"] to discover available commands. Output is JSON.
Edit a file in the stage workspace by exact string replacement. The old_string must match exactly once in the file. Use read_file first to see the current content.
Get the complete Dazzle reference — getting started, CLI commands, content capabilities, and streaming setup. Read this before creating or modifying stage content.
List all files in the stage workspace (~/.dazzle/stages/{stage}/). Returns relative paths, one per line.
Read a file from the stage workspace (~/.dazzle/stages/{stage}/{path}).
Capture a screenshot of the stage's current browser output. Returns a PNG image.
Sync the stage workspace (~/.dazzle/stages/{stage}/) to the live stage. Run this after writing files to push content. Equivalent to 'dazzle stage sync {workspace-dir}'.
Write a file to the stage workspace (~/.dazzle/stages/{stage}/{path}). Creates parent directories as needed. Use this to build up content that can then be synced to the stage.
Overview
What is Dazzle - Agentic Streaming?
Dazzle is a CLI and MCP server for cloud browser stages that render and stream content for AI agents and live broadcasting. It provides one binary with two interfaces: a full CLI for coding agents and terminals, and an MCP server for sandboxed clients like Claude Desktop and VS Code.
How to use Dazzle - Agentic Streaming?
Install using the curl (macOS/Linux) or PowerShell (Windows) one-liners, or via go install. For CLI usage, authenticate with dazzle login, create a stage with dazzle stage create, sync content with dazzle stage sync, and add streaming destinations. For MCP integration, add the server to your client config with command "dazzle" and args ["mcp"].
Key features of Dazzle - Agentic Streaming
- Cloud browser stages for live streaming and AI agent output
- MCP tools for file editing, sync, and screenshots
- Workspace tools bridge sandboxed environments to host filesystem
- Supports streaming to Twitch, Kick, and custom RTMP destinations
- Real-time event injection via DOM CustomEvents without reload
- Content sync with auto-refresh for live development
Use cases of Dazzle - Agentic Streaming
- Coding agents (e.g., Claude Code, Cursor) sync and stream live web content
- Sandboxed clients (e.g., Claude Desktop, VS Code) build stages via MCP
- Stream pre-built HTML/CSS/JS to Twitch, Kick, or any RTMP endpoint
- Inject real-time data from external processes into running
More Developer Tools MCP servers
sentry-mcp
getsentryAn MCP server for interacting with Sentry via LLMs.
Test
x1xhlolFULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae, Traycer AI, VSCode Agent, Warp.dev, Windsurf, Xcode, Z.ai Code, Dia & v0. (And other Open Sou
Unity MCP (Server + Plugin)
IvanMurzakAI Skills, MCP Tools, and CLI for Unity Engine. Full AI develop and test loop. Use cli for quick setup. Efficient token usage, advanced tools. Any C# method may be turned into a tool by a single line. Works with Claude Code, Gemini, Copilot, Cursor and any other absolutely for fr
TalkToFigma
sonnylazuardiTalkToFigma: MCP integration between AI Agent (Cursor, Claude Code, Codex) and Figma, allowing Agentic AI to communicate with Figma for reading designs and modifying them programmatically.
MCP-Scan: An MCP Security Scanner
invariantlabs-aiSecurity scanner for AI agents, MCP servers and agent skills.
Comments