Merge pull request #11306 from lbotinelly/agent/add-ghostlight

Add Ghostlight browser automation server 🤖🤖🤖

README.md

@@ -483,6 +483,7 @@ Web content access and automation capabilities. Enables searching, scraping, and
 - [softvoyagers/pageshot-api](https://github.com/softvoyagers/pageshot-api) 📇 ☁️ - Free webpage screenshot capture API with format, viewport, and dark mode options. No API key required.
 - [SolveGate/solvegate-mcp](https://github.com/SolveGate/solvegate-mcp) [![SolveGate/solvegate-mcp MCP server](https://glama.ai/mcp/servers/SolveGate/solvegate-mcp/badges/score.svg)](https://glama.ai/mcp/servers/SolveGate/solvegate-mcp) 🎖️ 📇 ☁️ - Deal with Cloudflare Turnstile from an agent. `inspect_page` reports whether a page actually uses Turnstile and what its sitekey is — free, no API key — so the agent can look before it acts, and it says plainly when a page carries reCAPTCHA or hCaptcha instead, or is a full-page Cloudflare interstitial rather than an embedded widget. `solve_turnstile` and `get_solve` clear the challenge and return a token when one is genuinely needed. `npx -y solvegate-mcp`
 - [swimmwatch/cloakbrowser-mcp](https://github.com/swimmwatch/cloakbrowser-mcp) [![swimmwatch/cloakbrowser-mcp MCP server](https://glama.ai/mcp/servers/swimmwatch/cloakbrowser-mcp/badges/score.svg)](https://glama.ai/mcp/servers/swimmwatch/cloakbrowser-mcp) 📇 🏠 🍎 🪟 🐧 - Playwright MCP-compatible browser automation using CloakBrowser Chromium, available as an npm package and Docker image.
+- [sylin-org/ghostlight](https://github.com/sylin-org/ghostlight) [![sylin-org/ghostlight MCP server](https://glama.ai/mcp/servers/sylin-org/ghostlight/badges/score.svg)](https://glama.ai/mcp/servers/sylin-org/ghostlight) 🦀 🏠 🪟 🐧 - Visible local browser automation in the signed-in Chromium profile you already use, with useful recovery and optional policy and audit.
 - [User0856/snaprender-mcp](https://github.com/User0856/snaprender-integrations/tree/main/mcp-server) [![snaprender-mcp MCP server](https://glama.ai/mcp/servers/@User0856/snaprender-mcp/badges/score.svg)](https://glama.ai/mcp/servers/@User0856/snaprender-mcp) 📇 ☁️ - Screenshot API for AI agents — capture any website as PNG, JPEG, WebP, or PDF with device emulation, dark mode, ad blocking, and cookie banner removal. Free tier included.
 - [copperline-labs/rendex-mcp](https://github.com/copperline-labs/rendex-mcp) [![rendex-mcp MCP server](https://glama.ai/mcp/servers/copperline-labs/rendex-mcp/badges/score.svg)](https://glama.ai/mcp/servers/copperline-labs/rendex-mcp) 📇 ☁️ - Screenshot, PDF, and HTML rendering API for AI agents. Capture any URL or raw HTML as PNG/JPEG/WebP/PDF with batch processing, geo-targeting, async webhooks, and MCP-native integration. Free tier included.
 - [vincentvella/devloop](https://github.com/vincentvella/devloop) [![vincentvella/devloop MCP server](https://glama.ai/mcp/servers/vincentvella/devloop/badges/score.svg)](https://glama.ai/mcp/servers/vincentvella/devloop) 📇 🏠 🍎 🪟 🐧 - Drives a browser (or a native Expo/React Native app on iOS/Android) and your dev server onto one correlated timeline, so a browser console error and the backend stack trace from the same moment line up. Includes `repro` action sequences, a unified log/network query API, and an Electron cockpit.