Sarakael78

Bridge Search — AI skill for Claude Code

AI community

Blazing-fast WSL2 to Windows file search bridge for AI Agents via MCP.

How to install Bridge Search

This entry records only its repository, not the path inside it, so there is no exact command to give. Open Sarakael78/Bridge-Search and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Bridge Search does

Blazing-fast WSL2 to Windows file search bridge for AI Agents via MCP.

Alternatives in AI

Fast Agent — Code, Build and Evaluate agents - excellent Model and Skills/MCP/ACP Support 3.7k ★
Open Science — Open Science Desktop — local-first, model-agnostic AI research workbench for macOS, Windows & Linux 1.5k ★
System One Connector — System One MCP connector to evaluate anything fast and cheap 340 ★

README

Bridge Search 🌉

![Diagram illustrating Bridge Search connecting WSL2 to Windows-native search tools Everything and AnyTXT.](docs/assets/bridge-search-hero.png)

[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT) [![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/) [![MCP Compatible](https://img.shields.io/badge/MCP-Ready-success.svg)](https://github.com/steipete/mcporter) [![CodeQL](https://github.com/Sarakael78/Bridge-Search/actions/workflows/github-code-scanning/codeql/badge.svg)](https://github.com/Sarakael78/Bridge-Search/actions/workflows/github-code-scanning/codeql)

[![CI: Lint, Typecheck, Test](https://github.com/Sarakael78/Bridge-Search/actions/workflows/test.yml/badge.svg)](https://github.com/Sarakael78/Bridge-Search/actions/workflows/test.yml) [![GitHub Release](https://img.shields.io/github/v/release/Sarakael78/Bridge-Search?color=blue)](https://github.com/Sarakael78/Bridge-Search/releases) [![Dependabot](https://badgen.net/github/dependabot/Sarakael78/Bridge-Search)](https://github.com/Sarakael78/Bridge-Search/pulls?q=is%3Apr+is%3Aopen+label%3Adependabot)

The Problem

The OS boundary is a massive bottleneck. When AI agents (like OpenClaw, Cursor, or Claude) try to search Windows files (`/mnt/c` etc.) from inside WSL2 using standard Linux commands, the results are disastrous. The search takes forever, the agent times out, loses its context window, or simply hallucinates file paths to move on.

The Solution

**Bridge Search** bypasses the file system bottleneck entirely. It uses Model Context Protocol (MCP) tools to connect your AI directly to the native, hyper-optimised search engines built for Windows.

It handles all the messy cross-OS path translations automatically, giving your agent two immediate superpowers: