MySearch-Proxy — security grade SAFE, quality 62/100

Security audit verdict: SAFE · quality 62/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by skernelx · MCP Server · ★ 147

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is MySearch-Proxy safe to install? View the security audit →

About MySearch-Proxy

MySearch Proxy English Guide 是一套给 AI 助手准备的统一搜索栈。 它把原本分散的 4 件事收成了同一个仓库: - 真正可安装的 MySearch MCP - 给 Codex / Claude Code 的 skill 与安装说明 - 给 OpenClaw / ClawHub 的独立 skill bundle - 给团队或公开部署使用的控制台与代理层 支持的搜索能力: Tavily Firecrawl Exa 可选 X / Social 目标很简单: 让本地 AI 助手先用起来 让 OpenClaw 直接装上去 让团队共享一套统一搜索后端 让调用方尽量少关心底层 provider 差异 项目入口: GitHub: skernelx/MySearch-Proxy Docker Hub: skernelx/mysearch-proxy ClawHub: clawhub.ai/skernelx/mysearch 为什么做这个项目 很多搜索类项目只解决其中一小段: 只给一个 只会搜,不会抓正文 只会调官方 API,不方便接自建网关 只给 prompt,不给真正能安装的运行时 只做 key 面板,不解决 AI 如何调用 选择直接把整条链补齐: 推荐架构 当前最推荐的是 : 这条路的好处很直接: 客户端只需要一组 Tavily / Firecrawl / Exa 不再散落到每台机器 可以统一管理 token、调用统计和额度同步 OpenClaw、本地 Codex、团队代理都能复用同一套配置 如果你暂时还没有 Proxy,也可以让 或 直接连官方 provider。 ##

ai-searchclaude-codecodexfirecrawlmcpmodel-context-protocolopenclawsearchsearch-proxysocial-search

Quick Facts

Stars147
Forks26
LanguagePython
CategoryMCP Server
Quality Score62.2524173329328/100
Open Issues4
Last Updated2026-03-23
Created2026-03-16
Platformsclaude-code, codex, mcp, python
Est. Tokens~118k

MySearch-Proxy alternative? Top 6 similar tools

Looking for a MySearch-Proxy alternative? If you're comparing MySearch-Proxy with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • mcp-omnisearch by spences10 · ⭐ 351

    🔍 A Model Context Protocol (MCP) server providing unified access to multiple search engines (Tavily, Brave, K

  • Overture by SixHq · ⭐ 630

    Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server

  • kindly-web-search-mcp-server by Shelpuk-AI-Technology-Consulting · ⭐ 388

    Kindly Web Search MCP Server: Web search + robust content retrieval for AI coding tools (Claude Code, Codex, C

  • deepcontext-mcp by Wildcard-Official · ⭐ 275

    DeepContext is an MCP server that adds symbol-aware semantic search to Claude Code, Codex CLI, and other agent

  • agent-skills by jdrhyne · ⭐ 241

    A collection of AI agent skills for Clawdbot, Claude Code, Codex

  • claude-historian-mcp by Vvkmnn · ⭐ 177

    📜 An MCP server for conversation history search and retrieval in Claude Code

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Python Agent Tools

Frequently Asked Questions

What is MySearch-Proxy?

MySearch-Proxy is Unified search MCP, proxy console, and skill for Tavily, Firecrawl, and Social / X.. It is categorized as a MCP Server with 147 GitHub stars.

What programming language is MySearch-Proxy written in?

MySearch-Proxy is primarily written in Python. It covers topics such as ai-search, claude-code, codex.

How do I install or use MySearch-Proxy?

You can find installation instructions and usage details in the MySearch-Proxy GitHub repository at github.com/skernelx/MySearch-Proxy. The project has 147 stars and 26 forks, indicating an active community.

What are the best alternatives to MySearch-Proxy?

The top alternatives to MySearch-Proxy on Agent Skills Hub include mcp-omnisearch, Overture, kindly-web-search-mcp-server. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse MCP Server tools