Agora MCP
Search and buy products across thousands of online stores using the SearchAgora universal product search engine.
Agora MCP
An MCP server for searching, discovering, and purchasing products through AI assistants like Claude or Cursor.
What is Agora MCP?
Agora MCP connects AI assistants to SearchAgora - a universal product search engine that helps you discover and buy products from across the web. With this MCP, you can seamlessly search for products, compare options, manage your shopping cart, and complete purchases directly through your AI assistant.
Prerequisites
- MCP Client like Cursor or Claude Desktop
- UV installed
- A payment method through any L402-compatible client like Fewsats
Setting Up the MCP Server
For Cursor
- Open Cursor and go to Settings
- Navigate to MCP Server Configuration
- Add the following configuration:
{
"mcpServers": {
"Agora": {
"command": "uvx",
"args": [
"agora-mcp"
]
},
"Fewsats": {
"command": "env",
"args": [
"FEWSATS_API_KEY=YOUR_FEWSATS_API_KEY",
"uvx",
"fewsats-mcp"
]
}
}
}
Make sure to replace YOUR_FEWSATS_API_KEY
with your actual API key from Fewsats.
For Claude Desktop
-
Find the configuration file:
- On MacOS:
~/Library/Application\ Support/Claude/claude_desktop_config.json
- On Windows:
%APPDATA%/Claude/claude_desktop_config.json
- On MacOS:
-
Add the following configuration:
"mcpServers": {
"Agora": {
"command": "uvx",
"args": [
"agora-mcp"
]
},
"Fewsats": {
"command": "env",
"args": [
"FEWSATS_API_KEY=YOUR_FEWSATS_API_KEY",
"uvx",
"fewsats-mcp"
]
}
}
Running a Local Development Version
For development purposes, you can run a local version of the Agora MCP from your own repository:
"Agora": {
"command": "uv",
"args": [
"--directory",
"/path/to/your/agora-mcp",
"run",
"agora-mcp"
]
}
Replace /path/to/your/agora-mcp
with the actual path to your local Agora MCP repository.
Using Agora MCP With Your AI
Once configured, you can have natural conversations with your AI to search for and purchase products:
Searching for Products
Simply ask your AI to search for products:
Can you find a cool t-shirt for me?
Advanced Search Options
Refine your search with additional parameters:
Show me headphones under $100 sorted by highest rating
The search supports:
- Price ranges (min/max)
- Pagination
- Custom sorting
- Product filtering
Coming Soon: Shopping Cart & Purchasing
Soon you'll be able to:
Add that red t-shirt to my cart
Show me what's in my cart
Checkout and purchase my items
Supported Features
Currently, Agora MCP supports:
- Product search with customizable parameters:
- Search query
- Results per page
- Page navigation
- Price filtering (minimum and maximum)
- Custom sorting options
Coming soon:
- Add products to cart
- View and manage shopping cart
- Complete purchases
- Save favorite products
- Track order status
About SearchAgora
SearchAgora is a universal product search engine that helps you discover products from across the web. It offers a seamless shopping experience with comprehensive product information, price comparisons, and streamlined checkout processes.
Related Servers
Pollinations Think
Strategic thinking and real-time web search using the Pollinations AI API with DeepSeek and SearchGPT models.
MCP Web Search Server
A web search server powered by DuckDuckGo, no API key required.
YouTube MCP Server
Search YouTube videos, retrieve transcripts, and perform semantic search over video content.
Deep Research
A server for conducting deep research and generating reports.
Perigon MCP Server
Official MCP server for the Perigon API, providing access to real-time news and media data.
Searchcraft
Manage Searchcraft cluster's Documents, Indexes, Federations, Access Keys, and Analytics.
YouTube Music MCP
Search and play tracks on YouTube Music via AI assistants.
Plex MCP Server
Search your Plex media library. Supports OAuth and static token authentication.
Bing Search
Perform web, news, and image searches using the Microsoft Bing Search API.
avr-docs-mcp
This MCP (Model Context Protocol) server provides integration with Wiki.JS for searching and listing pages from Agent Voice Response Wiki.JS instance.