diff --git a/README.md b/README.md
index 10fda3dc6..73bb0401f 100644
--- a/README.md
+++ b/README.md
@@ -501,6 +501,7 @@ Web content access and automation capabilities. Enables searching, scraping, and
 - [LeonTing1010/tap](https://github.com/LeonTing1010/tap) [![LeonTing1010/tap MCP server](https://glama.ai/mcp/servers/LeonTing1010/tap/badges/score.svg)](https://glama.ai/mcp/servers/LeonTing1010/tap) 📇 🏠 🍎 🪟 🐧 - MCP server that compiles AI browser automation into deterministic `.tap.json` plans (25-op closed union, zero runtime LLM), runs on your logged-in Chrome, and detects drift via semantic fingerprint diff when sites change. 65+ open community taps on 40+ sites.
 - [lespaceman/agent-web-interface](https://github.com/lespaceman/agent-web-interface) [![lespaceman/agent-web-interface MCP server](https://glama.ai/mcp/servers/lespaceman/agent-web-interface/badges/score.svg)](https://glama.ai/mcp/servers/lespaceman/agent-web-interface) 📇 🏠 🍎 🪟 🐧 - Token-efficient browser automation for LLM agents: semantic page snapshots and stable element IDs instead of raw DOM or screenshots, driving Chrome over CDP.
 - [markmircea/Selenix-MCP-Server](https://github.com/markmircea/Selenix-MCP-Server) [![markmircea/Selenix-MCP-Server MCP server](https://glama.ai/mcp/servers/markmircea/Selenix-MCP-Server/badges/score.svg)](https://glama.ai/mcp/servers/markmircea/Selenix-MCP-Server) 📇 🏠 🍎 🪟 🐧 - MCP server bridging Claude Desktop with Selenix for browser automation and testing. Create, run, debug, and manage browser tests through natural language.
+- [ilien-dev/svipall](https://github.com/ilien-dev/svipall) [![ilien-dev/svipall MCP server](https://glama.ai/mcp/servers/ilien-dev/svipall/badges/score.svg)](https://glama.ai/mcp/servers/ilien-dev/svipall) 🦀 🏠 🍎 🪟 🐧 - Local-first web reading with a tier ladder that escalates from plain HTTP to a real browser when a page pushes back. Pages as clean Markdown, whole-site crawls, keyless search, repeated page structure induced into rows, and a REST API. Attempts supported captchas on your own machine with optional local ONNX models, and parks the rest in a human dashboard. Labels blocked and low-quality pages instead of handing back a challenge screen as content. No API keys, no paid solvers, no telemetry.
 - [imprvhub/mcp-browser-agent](https://github.com/imprvhub/mcp-browser-agent) 📇 🏠 - A Model Context Protocol (MCP) integration that provides Claude Desktop with autonomous browser automation capabilities.
 - [kimtaeyoon83/mcp-server-youtube-transcript](https://github.com/kimtaeyoon83/mcp-server-youtube-transcript) 📇 ☁️ - Fetch YouTube subtitles and transcripts for AI analysis
 - [samson-art/transcriptor-mcp](https://github.com/samson-art/transcriptor-mcp) [![transcriptor-mcp MCP server](https://glama.ai/mcp/servers/samson-art/transcriptor-mcp/badges/score.svg)](https://glama.ai/mcp/servers/samson-art/transcriptor-mcp) 📇 ☁️ - Transcriptor MCP is your choice when you need transcripts and metadata for AI, summarization, or content analysis