About Agora MCP
Agora MCP connects AI assistants to SearchAgora product search for finding and filtering products across the web. It is for shopping through clients such as Claude or Cursor with price, pagination, and sorting options; cart and purchasing features are not yet available.
Key features
- 01Search products across the web
- 02Filter by minimum and maximum price
- 03Paginate through results
- 04Choose custom sorting
Use cases
- 01Find products within a price range
- 02Compare search results sorted by rating
MCP support
The MCP server exposes SearchAgora product search to compatible clients, including query, pagination, price filters, and custom sorting.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEAgora 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.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.