AI TOOL HUNTER

VishalsWorkspace4stars

AI tool discovery engine with live search agent, Google Auth, MCP server, and auto-updating HuggingFace dataset

1# AI TOOL HUNTER

README.mdMCP server

Transport: stdio
Status: Local

Power your agent

Add this server

Install from the publisher. Not a PlugMCP endpoint.

Run on PlugMCP

Host a copy with our keys and logs.

No packaged release in the registry yet. Follow the repository README.

RepositoryPublisher installStep-by-step: add this in Claude

Remote URL or a command on your machine? How the two installs differ

Run on PlugMCP

Host a copy with our keys and logs.

A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.

Launch

Server facts

Local

Transport: stdio
License: MIT
Last checked: 2026-10-28

Stars: 4
Tools: —
Uptime: —

Tools

No tool list yet. Remote servers get one after the first health check.

FAQ

Questions

How do I install AI TOOL HUNTER?

Copy the stdio config for Cursor, Claude Desktop, Claude Code, or VS Code on this page. It uses the publisher's install, not a PlugMCP proxy.

Does AI TOOL HUNTER need an API key?

No required environment variable is listed on this record.

What transport does AI TOOL HUNTER use?

AI TOOL HUNTER runs locally over stdio.

When was AI TOOL HUNTER last checked?

Last checked 2026-10-28. AI tool discovery engine with live search agent, Google Auth, MCP server, and auto-updating HuggingFace dataset

From the publisher

Documentation

🏹 AI Tool Hunter

An intelligent search engine for AI software.

Don't just search. Hunt.

AI Tool Hunter - Find Top 1% of AI Tools

What it is

AI Tool Hunter is a full-stack search engine purpose-built for discovering AI software — not a generic directory. It combines a curated, daily-refreshed database with a live search agent that scans the web in real time for tools that aren't in the database yet, verifying them with an LLM before they're shown. The same underlying dataset is exposed as an open-source Hugging Face dataset and as an MCP server, so the data is usable both by end users in a browser and by AI agents/IDEs directly.

✨ Key Features

🔍 Use-case based AI search
🤖 Live search agent (Tavily + Llama 3.3-70B)
🔐 Google OAuth + personalized experience
📚 My Stack — build and share your AI toolkit
⚖️ Side-by-side tool comparison
⭐ Community ratings and reviews
🔌 MCP server for IDE integration
📊 Open-source dataset on Hugging Face (auto-updating daily)
🚀 Deployed on Vercel with CI/CD via GitHub Actions

🛠️ Tech Stack

Layer	Technology
Framework	Next.js 16 (App Router), React 19, TypeScript
Styling	Tailwind CSS 4, Lucide Icons
Database & Auth	Supabase (PostgreSQL, Row Level Security, Google OAuth)
Search Agent	Tavily Search API
LLM Inference	Groq (Llama 3.3-70B, Llama 3.1-8B)
Analytics	PostHog
Automation	Python (GitHub Actions cron), Hugging Face Hub
Deployment	Vercel
Integration	MCP (Model Context Protocol) server

🏗️ Architecture

                          ┌────────────────────┐
                          │      Browser        │
                          └──────────┬──────────┘
                                     │
                          ┌──────────▼──────────┐
                          │   Next.js App        │
                          │  (Vercel, App Router) │
                          └──────────┬──────────┘
                                     │
                 ┌───────────────────┼───────────────────┐
                 │                   │                   │
        ┌────────▼───────┐ ┌─────────▼────────┐ ┌────────▼────────┐
        │    Supabase     │ │  Live Search Agent│ │   MCP Server     │
        │ Postgres + Auth │ │ Tavily → Groq LLM │ │ (separate repo)  │
        └────────▲────────┘ └────────────────────┘ └─────────────────┘
                 │
        ┌────────┴────────┐
        │ GitHub Actions   │   daily cron
        │ harvest → verify │──────────────► scripts/process_tools.py
        │ → export to HF   │──────────────► scripts/export_to_hf.py
        └──────────────────┘                        │
                                                      ▼
                                     Hugging Face Dataset (public)

🚀 Getting Started

# 1. Clone the repo
git clone https://github.com/VishalsWorkspace/AI-TOOL-HUNTER.git
cd AI-TOOL-HUNTER

# 2. Install dependencies
npm install

# 3. Set up environment variables
cp .env.example .env.local   # then fill in values, see table below

# 4. Run the dev server
npm run dev

The app will be available at http://localhost:3000.

🔑 Environment Variables

Variable	Description
`NEXT_PUBLIC_SUPABASE_URL`	Supabase project URL
`NEXT_PUBLIC_SUPABASE_ANON_KEY`	Supabase anon/public key (client-side)
`SUPABASE_KEY`	Supabase service key (server-side scripts)
`GROQ_API_KEY`	Groq API key for LLM inference
`TAVILY_API_KEY`	Tavily API key for live web search

🔌 MCP Integration

AI Tool Hunter's dataset is exposed via a Model Context Protocol (MCP) server, so IDEs and AI agents (e.g. Claude Code, Cursor) can query the tool database directly instead of scraping the site.

Repo: ai-tool-hunter-mcp
Live server: https://ai-tool-hunter-mcp.onrender.com

📊 Dataset

The full tool corpus is published as an open-source dataset, refreshed daily by the same GitHub Actions job that powers the site's harvester.

Hugging Face: Vishalsworkspace/AI-Tools-Corpus-2026

🔗 Links

Live Site: https://ai-tool-hunter-eight.vercel.app
MCP Server: https://ai-tool-hunter-mcp.onrender.com
MCP Server Repo: https://github.com/VishalsWorkspace/ai-tool-hunter-mcp
Dataset: https://huggingface.co/datasets/Vishalsworkspace/AI-Tools-Corpus-2026

🤝 Contributing

Contributions are welcome. See CONTRIBUTING.md for the fork → branch → PR workflow, coding conventions, and how to get in touch.

📄 License

MIT © Vishal Singh

Built by Vishal Singh

AI TOOL HUNTER

VishalsWorkspace4stars

AI tool discovery engine with live search agent, Google Auth, MCP server, and auto-updating HuggingFace dataset

Databases

Install Run on PlugMCP

GitHub Website

Run on PlugMCP

1# AI TOOL HUNTER

README.mdMCP server

Transport: stdio
Status: Local

Power your agent

Add this server

Install from the publisher. Not a PlugMCP endpoint.

Run on PlugMCP

Host a copy with our keys and logs.

No packaged release in the registry yet. Follow the repository README.

RepositoryPublisher installStep-by-step: add this in Claude

Remote URL or a command on your machine? How the two installs differ

Run on PlugMCP

Host a copy with our keys and logs.

A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.

Launch

Server facts

Local

Transport: stdio
License: MIT
Last checked: 2026-10-28

Stars: 4
Tools: —
Uptime: —

Tools

No tool list yet. Remote servers get one after the first health check.

FAQ

Questions

How do I install AI TOOL HUNTER?

Copy the stdio config for Cursor, Claude Desktop, Claude Code, or VS Code on this page. It uses the publisher's install, not a PlugMCP proxy.

Does AI TOOL HUNTER need an API key?

No required environment variable is listed on this record.

What transport does AI TOOL HUNTER use?

AI TOOL HUNTER runs locally over stdio.

When was AI TOOL HUNTER last checked?

Last checked 2026-10-28. AI tool discovery engine with live search agent, Google Auth, MCP server, and auto-updating HuggingFace dataset

From the publisher

Documentation

🏹 AI Tool Hunter

An intelligent search engine for AI software.

Don't just search. Hunt.

AI Tool Hunter - Find Top 1% of AI Tools

What it is

✨ Key Features

🔍 Use-case based AI search
🤖 Live search agent (Tavily + Llama 3.3-70B)
🔐 Google OAuth + personalized experience
📚 My Stack — build and share your AI toolkit
⚖️ Side-by-side tool comparison
⭐ Community ratings and reviews
🔌 MCP server for IDE integration
📊 Open-source dataset on Hugging Face (auto-updating daily)
🚀 Deployed on Vercel with CI/CD via GitHub Actions

🛠️ Tech Stack

Layer	Technology
Framework	Next.js 16 (App Router), React 19, TypeScript
Styling	Tailwind CSS 4, Lucide Icons
Database & Auth	Supabase (PostgreSQL, Row Level Security, Google OAuth)
Search Agent	Tavily Search API
LLM Inference	Groq (Llama 3.3-70B, Llama 3.1-8B)
Analytics	PostHog
Automation	Python (GitHub Actions cron), Hugging Face Hub
Deployment	Vercel
Integration	MCP (Model Context Protocol) server

🏗️ Architecture

                          ┌────────────────────┐
                          │      Browser        │
                          └──────────┬──────────┘
                                     │
                          ┌──────────▼──────────┐
                          │   Next.js App        │
                          │  (Vercel, App Router) │
                          └──────────┬──────────┘
                                     │
                 ┌───────────────────┼───────────────────┐
                 │                   │                   │
        ┌────────▼───────┐ ┌─────────▼────────┐ ┌────────▼────────┐
        │    Supabase     │ │  Live Search Agent│ │   MCP Server     │
        │ Postgres + Auth │ │ Tavily → Groq LLM │ │ (separate repo)  │
        └────────▲────────┘ └────────────────────┘ └─────────────────┘
                 │
        ┌────────┴────────┐
        │ GitHub Actions   │   daily cron
        │ harvest → verify │──────────────► scripts/process_tools.py
        │ → export to HF   │──────────────► scripts/export_to_hf.py
        └──────────────────┘                        │
                                                      ▼
                                     Hugging Face Dataset (public)

🚀 Getting Started

# 1. Clone the repo
git clone https://github.com/VishalsWorkspace/AI-TOOL-HUNTER.git
cd AI-TOOL-HUNTER

# 2. Install dependencies
npm install

# 3. Set up environment variables
cp .env.example .env.local   # then fill in values, see table below

# 4. Run the dev server
npm run dev

The app will be available at http://localhost:3000.

🔑 Environment Variables

Variable	Description
`NEXT_PUBLIC_SUPABASE_URL`	Supabase project URL
`NEXT_PUBLIC_SUPABASE_ANON_KEY`	Supabase anon/public key (client-side)
`SUPABASE_KEY`	Supabase service key (server-side scripts)
`GROQ_API_KEY`	Groq API key for LLM inference
`TAVILY_API_KEY`	Tavily API key for live web search

🔌 MCP Integration

AI Tool Hunter's dataset is exposed via a Model Context Protocol (MCP) server, so IDEs and AI agents (e.g. Claude Code, Cursor) can query the tool database directly instead of scraping the site.

Repo: ai-tool-hunter-mcp
Live server: https://ai-tool-hunter-mcp.onrender.com

📊 Dataset

The full tool corpus is published as an open-source dataset, refreshed daily by the same GitHub Actions job that powers the site's harvester.

Hugging Face: Vishalsworkspace/AI-Tools-Corpus-2026

🔗 Links

Live Site: https://ai-tool-hunter-eight.vercel.app
MCP Server: https://ai-tool-hunter-mcp.onrender.com
MCP Server Repo: https://github.com/VishalsWorkspace/ai-tool-hunter-mcp
Dataset: https://huggingface.co/datasets/Vishalsworkspace/AI-Tools-Corpus-2026

🤝 Contributing

Contributions are welcome. See CONTRIBUTING.md for the fork → branch → PR workflow, coding conventions, and how to get in touch.

📄 License

Built by Vishal Singh