Skip to content
Back to search

SoSearch

🔎 One query. Three search engines. Self-hosted web search for AI agents via HTTP API or MCP. Aggregates DuckDuckGo, Brave & Yahoo. Built with Rust. No API keys required.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/netlops--sosearch/badge.svg)](/listings/netlops--sosearch)

HTML

<a href="/listings/netlops--sosearch"><img src="/api/listings/netlops--sosearch/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Linux / macOS

# Download pre-built binary or build from source
cargo run --release
curl "http://localhost:10080/search?q=hello+world"

Windows

**使用预编译二进制:**

从 [GitHub Releases](https://github.com/netlops/SoSearch/releases) 下载 `SoSearch-windows-amd64.zip`,解压后:

# 启动 HTTP 服务
.\SoSearch.exe

# 另开一个终端测试
Invoke-RestMethod "http://localhost:10080/search?q=hello+world" | ConvertTo-Json

# 或使用 curl
curl.exe "http://localhost:10080/search?q=hello+world"

**从源码编译(需要安装 [Rust](https://rustup.rs/)、CMake、NASM、LLVM/Clang):**

# 安装依赖 (使用 Chocolatey)
choco install cmake nasm llvm -y

# 编译运行
cargo run --release

**MCP 模式:**

.\SoSearch.exe --mcp

Refer to `QUICK_START.md` for full instructions.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 180 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # SoSearch API
  2. A lightning-fast pseudo Web Search Engine API written in **Rust** — also works as an **MCP server** for AI agents.
  3. This project emulates popular APIs like *SerpAPI* or *Tavily* without needing official and expensive API keys, by multiplexing requests to popular engines directly and scraping the results concurrently.
  4. ## Philosophy
  5. - **Performance**: Powered by `tokio` for async concurrent I/O.
  6. - **Bot Bypass**: Leverages `rquest` with TLS impersonation (e.g., simulating a Chrome 124 browser footprint at the TLS/HTTP2 layer) to minimize blocking vs standard HTTP clients (the Rust equivalent of `curl_cffi`).
  7. - **Standardized**: Normalizes `DuckDuckGo`, `Yahoo`, and `Brave` HTML results into a standardized `SearchResult` JSON array.
  8. ## Core Stack
  9. - [Axum](https://github.com/tokio-rs/axum)
  10. - [Tokio](https://tokio.rs/)
  11. - [rquest](https://github.com/0x676e67/rquest)
  12. - [scraper](https://github.com/causal-agent/scraper)
  13. ## 🔍 Supported Search Engines
  14. * **DuckDuckGo** (Primary standard search)
  15. * **Yahoo** (Powered by Bing)
  16. * **Brave Search** (Independent index)
  17. ## 📁 Project Structure
  18. ```
  19. src/
  20. ├── main.rs # Entry point: HTTP server or MCP mode (--mcp)
  21. ├── search.rs # Shared concurrent search logic
  22. ├── mcp.rs # MCP stdio server (JSON-RPC 2.0)
  23. ├── models.rs # SearchResultItem, SearchResponse structs
  24. └── engines/
  25. ├── mod.rs # SearchEngine enum + trait dispatch
  26. ├── duckduckgo.rs # DuckDuckGo scraper
  27. ├── yahoo.rs # Yahoo scraper (Bing-powered)
  28. └── brave.rs # Brave Search scraper
  29. examples/
  30. ├── fetch_html.rs # Download raw HTML for offline debugging
  31. └── test_parser.rs # Offline CSS selector iteration
  32. .gemini/ # Gemini CLI agent config
  33. ├── GEMINI.md # Project-level system prompt
  34. ├── settings.json # MCP server configuration
  35. └── skills/ # Project-level agent skills
  36. ├── sosearch-engine-dev/ # Scraper development workflow
  37. └── sosearch-api-ops/ # API operations & deployment
  38. .agents/ # Generic agent config (compatible with multiple AI tools)
  39. └── skills/ # Same skills, alternative discovery path
  40. ├── sosearch-engine-dev/
  41. └── sosearch-api-ops/
  42. ```
  43. ## 🤖 Agent Skills & MCP Support
  44. This project includes built-in AI agent support for both **Gemini CLI** and other tools that follow the `.agents/` convention.
  45. ### Available Skills
  46. | Skill | Description |
  47. |---|---|
  48. | `sosearch-engine-dev` | Full workflow for adding/debugging search engine scrapers: fetch HTML → test selectors offline → decode URLs → integrate |
  49. | `sosearch-api-ops` | Operations guide: build, run, test, deploy (local + Docker), troubleshoot |
  50. ### MCP Servers
  51. Configured in `.gemini/settings.json`:
  52. | Server | Package | Purpose |
  53. |---|---|---|
  54. | `filesystem` | `@modelcontextprotocol/server-filesystem` | Scoped file access to project directory |
  55. ### Usage with Gemini CLI
  56. ```bash
  57. cd /path/to/SoSearch
  58. gemini
  59. # Skills are auto-discovered. Ask: "How do I add a new search engine?"
  60. ```
  61. ## 🔌 MCP Server Mode
  62. Run SoSearch as an MCP server for AI agents (Claude, Gemini, Cursor, etc.):
  63. ```bash
  64. ./SoSearch --mcp
  65. ```
  66. ### Configuration
  67. **Claude Desktop** (`claude_desktop_config.json`):
  68. ```json
  69. {
  70. "mcpServers": {
  71. "sosearch": {
  72. "command": "/path/to/SoSearch",
  73. "args": ["--mcp"]
  74. }
  75. }
  76. }
  77. ```
  78. **Gemini CLI** (`.gemini/settings.json`):
  79. ```json
  80. {
  81. "mcpServers": {
  82. "sosearch": {
  83. "command": "/path/to/SoSearch",
  84. "args": ["--mcp"]
  85. }
  86. }
  87. }
  88. ```
  89. This exposes a `web_search` tool that AI agents can call to search the web.
  90. ### Windows Configuration
  91. **Claude Desktop** (`%APPDATA%\Claude\claude_desktop_config.json`):
  92. ```json
  93. {
  94. "mcpServers": {
  95. "sosearch": {
  96. "command": "C:\\path\\to\\SoSearch.exe",
  97. "args": ["--mcp"]
  98. }
  99. }
  100. }
  101. ```
  102. ## 🚀 Quick Start
  103. ### Linux / macOS
  104. ```bash
  105. # Download pre-built binary or build from source
  106. cargo run --release
  107. curl "http://localhost:10080/search?q=hello+world"
  108. ```
  109. ### Windows
  110. **使用预编译二进制:**
  111. 从 [GitHub Releases](https://github.com/netlops/SoSearch/releases) 下载 `SoSearch-windows-amd64.zip`,解压后:
  112. ```powershell
  113. # 启动 HTTP 服务
  114. .\SoSearch.exe
  115. # 另开一个终端测试
  116. Invoke-RestMethod "http://localhost:10080/search?q=hello+world" | ConvertTo-Json
  117. # 或使用 curl
  118. curl.exe "http://localhost:10080/search?q=hello+world"
  119. ```
  120. **从源码编译(需要安装 [Rust](https://rustup.rs/)、CMake、NASM、LLVM/Clang):**
  121. ```powershell
  122. # 安装依赖 (使用 Chocolatey)
  123. choco install cmake nasm llvm -y
  124. # 编译运行
  125. cargo run --release
  126. ```
  127. **MCP 模式:**
  128. ```powershell
  129. .\SoSearch.exe --mcp
  130. ```
  131. Refer to `QUICK_START.md` for full instructions.
  132. ## 📄 License
  133. [CC BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/) — 非商业用途可自由使用、修改和分发。
  134. ## 🏠 Community
  135. 首发于 [LINUX DO 社区](https://linux.do),欢迎 Star ⭐ 和 PR!

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.