sncro.net
oficialLive browser debugging for AI assistants — DOM, console, network via MCP.
sncro-relay
Open-source components of sncro — the MCP relay, the browser-side agent, and the framework plugins that let AI coding assistants inspect a live browser.
What this repo contains
| Path | What |
|---|---|
relay/ | FastAPI app that exposes an MCP server plus long-poll endpoints for agent.js |
relay/static/agent.js | Browser-side script injected by the middleware; pushes console + DOM data to the relay |
middleware/sncro_middleware.py | FastAPI / Starlette plugin — drop-in middleware for FastAPI apps |
middleware/sncro_flask.py | Flask plugin — drop-in middleware for Flask apps |
trysncro/ | try.sncro.net — a deliberately-broken demo app for exercising sncro end-to-end |
How it works
┌──────────────┐ MCP ┌──────────┐ long-poll ┌─────────────┐
│ Claude Code │──tools────▶│ relay │◀──────────────│ agent.js │
│ (or other │ │ (relay/) │ snapshots │ (injected │
│ MCP client) │◀──results──│ │──────────────▶│ by plugin) │
└──────────────┘ └──────────┘ └─────────────┘
▲
│ same-origin
│ cookies
┌─────────────┐
│ your app │
│ (plugin is │
│ installed) │
└─────────────┘
- Claude calls
create_session(MCP tool) → relay returns a 9-digit session key + URL - User visits the URL in the browser where their app is running → confirms via "Allow sncro debugging?"
- The plugin drops a cookie, agent.js is injected into subsequent HTML responses on that origin
- agent.js pushes baseline data (console, errors) and long-polls for on-demand queries (
query_element,get_page_snapshot, etc.)
Using sncro
Most users don't need to run the relay yourself — the hosted version at relay.sncro.net is free-tier friendly. Register your project at sncro.net and grab your project key.
FastAPI: drop middleware/sncro_middleware.py into your project, then:
from middleware.sncro_middleware import SncroMiddleware, sncro_routes
app = FastAPI(debug=True) # sncro only loads when debug=True
if app.debug:
app.include_router(sncro_routes)
app.add_middleware(SncroMiddleware, relay_url="https://relay.sncro.net")
Flask: drop middleware/sncro_flask.py into your project, then:
from sncro_flask import init_sncro
app = Flask(__name__)
if app.debug:
init_sncro(app, relay_url="https://relay.sncro.net")
Both middlewares only activate in debug mode — zero overhead in production.
Contributing
We love new framework plugins. CONTRIBUTING.md has the full spec for what a plugin must do — cookies, routes, security headers — plus the test template. Django, Rails, Express, Next.js, ASP.NET, Go — all welcome.
Bug reports and security issues: see SECURITY.md.
License
MIT. See LICENSE.
The dashboard at sncro.net (project management, billing, admin) lives in a separate proprietary repo.
Servidores relacionados
Scout Monitoring MCP
patrocinadorPut performance and error data directly in the hands of your AI assistant.
Alpha Vantage MCP Server
patrocinadorAccess financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
Mindpilot MCP
Visualize legacy code and inspect complex flows to understand your agent's operations.
iOS Simulator MCP Server
A Model Context Protocol (MCP) server for interacting with iOS simulators. This server allows you to interact with iOS simulators by getting information about them, controlling UI interactions, and inspecting UI elements.
Alpaca MCP Server
Interact with Alpaca's Trading API for stocks, options, portfolios, and real-time market data using LLMs.
Lighthouse MCP Server
Audit web performance, accessibility, and SEO using Google Lighthouse.
MCP Context Server
Server providing persistent multimodal context storage for LLM agents.
Remote MCP Server on Cloudflare
A customizable remote MCP server for deployment on Cloudflare Workers, operating without authentication.
302AI Custom MCP Server
A customizable MCP service with flexible tool selection and configuration. Requires a 302AI API key.
Geo Location Demo
Retrieves user geolocation information using EdgeOne Pages Functions and exposes it via the Model Context Protocol (MCP).
MCP-Allure
Reads Allure test reports and returns them in LLM-friendly formats for better test analysis and insights.
Root Signals
Equip AI agents with evaluation and self-improvement capabilities with Root Signals.