About Agentmagnet
Agentmagnet is a product-search MCP server for AI agents, covering marketplaces, affiliate merchants, B2B programs, and SaaS across 52 languages. It supports local stdio and HTTP deployment, with optional USDC micropayments per search.
Key features
- 01Search across 40+ stores
- 0222 Amazon and 22 eBay stores
- 03Awin network with 15,000+ merchants
- 04AliExpress, B2B, and SaaS offers
- 0552-language detection
- 06USDC micropayments and HTTP or stdio
Use cases
- 01Find products across international marketplaces
- 02Search affiliate and SaaS offers
- 03Discover B2B industrial programs
MCP support
Exposes product-search capabilities to MCP clients, including searches across marketplaces, affiliate networks, and other listed offer sources.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEAgentMagnet
Universal Agent Commerce Layer — AI agents search products across 40+ stores, 52 languages, 30+ countries.
Quick Start
pip install -r requirements.txt
python -m agentmagnet
Features
- 52 languages — auto-detects agent language
- 22 Amazon stores (US, UK, DE, FR, IT, ES, JP, CA, AU, IN, MX, BR, NL, SE, PL, AE, SA, SG, TR, BE, EG, CN)
- 22 eBay stores
- Awin Network — 15,000+ merchants globally
- AliExpress — global
- B2B Industrial — hidden high-ticket programs ($120-$600/sale)
- SaaS affiliates — GoHighLevel 40%, HubSpot 30%, Kajabi 30% lifetime recurring
- x402 micropayments — $0.001/search in USDC, machine-to-machine
- Agent referral system — viral propagation built-in
- HTTP + stdio — deploy locally or on VPS
Deploy
# Local (stdio)
python -m agentmagnet
# VPS (HTTP)
python -m agentmagnet.http_server
License
MIT
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.