skernelx

skernelx / MySearch-Proxy

Public

Unified search MCP, proxy console, and skill for Tavily, Firecrawl, and Social / X.

ai-search claude-code codex firecrawl mcp
39
8
69% credibility
Found Mar 18, 2026 at 39 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

MySearch Proxy bundles search tools from multiple providers into a unified backend for AI assistants, with installable runtimes, skill guides, and a shared management console.

How It Works

1
🔍 Discover MySearch

You find MySearch, a helpful search toolkit that makes your AI companion smarter at finding web info, documents, and news.

2
📥 Grab the easy starter kit

Download the ready-to-go package and set it up on your computer in moments, no fuss needed.

3
🔗 Link your favorite search helpers

Connect everyday web search, page readers, and news finders so everything works together smoothly.

4
🚀 Start your search buddy

Hit go, and watch your new search helper come alive for personal use or team sharing.

5
✅ Quick check it works

Test a search or two, see fresh results pop up right away.

🎉 AI supercharged!

Now your AI friend fetches exactly what you need, fast and reliable, every time.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 39 to 39 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is MySearch-Proxy?

MySearch-Proxy is a Python-based unified search stack that aggregates Tavily, Firecrawl, Exa, and optional X/Social APIs into one installable MCP for AI assistants like Codex, Claude Code, and OpenClaw. It solves the hassle of juggling multiple search providers by offering a single proxy console for key management, quota syncing, and token generation, plus ready-to-deploy skills and Docker images for local or team use. Users get tools like search (with modes for web, docs, GitHub via Firecrawl, social), extract_url, research, and health checks over stdio, SSE, or streamableHTTP.

Why is it gaining traction?

It stands out as a true unified search engine—routing queries intelligently (Tavily for news/web, Firecrawl for docs/PDFs/GitHub, xAI for social) without forcing single-provider lock-in, and fallback gracefully if keys are missing. The proxy console centralizes ops like key pools and stats, while auto-install scripts and AI-friendly skills make it dead simple to plug into local agents or ClawHub. Developers hook it via two env vars for proxy mode, dodging scattered API keys.

Who should use this?

Local AI tinkerers running Codex or Claude Code who need reliable web/docs/social search without prompt hacks. OpenClaw/ClawHub skill builders wanting a publishable bundle with bundled runtime. Teams deploying shared backends for agent fleets, especially those already on Tavily/Firecrawl and eyeing unified GitHub searches or console dashboards.

Verdict

Grab it if you're building AI search workflows—docs are solid, Docker deploys fast, and proxy-first setup shines for reuse. At 39 stars and 0.7% credibility, it's early but stable for niches; monitor for broader adoption before production scale.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.