广告合作
MCP.so
登录
A

Agentmagnet MCP Server

@egri-creator

代码仓库

基本信息

分类

其他

传输方式

stdio

作者

egri-creator

提交者

Edgaras Grigaliunas

关于 Agentmagnet MCP Server

Universal product search across 40+ stores (Amazon 22 countries, eBay 22 countries, Awin 15k merchants, AliExpress, SaaS, B2B) — 52 languages, x402 micropayments.

#amazon#ebay#awin#shopping#global#x402

Agentmagnet MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "agentmagnet": {
      "command": "python",
      "args": [
        "-m",
        "agentmagnet"
      ]
    }
  }
}

Agentmagnet MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is AgentMagnet?

AgentMagnet is a universal commerce layer that enables AI agents to search products across 40+ stores, 52 languages, and 30+ countries. It is designed for developers integrating affiliate commerce directly into agent workflows.

How to use AgentMagnet?

Install dependencies with pip install -r requirements.txt then run python -m agentmagnet for local stdio mode, or python -m agentmagnet.http_server for HTTP mode on a VPS.

Key features of AgentMagnet

  • 52 languages with auto-detection of the agent’s language
  • 22 Amazon stores and 22 eBay stores worldwide
  • Awin Network access to 15,000+ merchants
  • AliExpress global store coverage
  • B2B Industrial high-ticket affiliate programs ($120–$600/sale)
  • SaaS affiliate commissions (GoHighLevel 40%, HubSpot 30%, Kajabi 30% lifetime recurring)
  • x402 micropayments: $0.001/search in USDC for machine-to-machine payments
  • Built-in agent referral system for viral propagation
  • HTTP and stdio transports for local or VPS deployment

Use cases of AgentMagnet

  • An AI shopping assistant that searches product availability and prices across 22 Amazon stores
  • An agent recommending SaaS tools while earning recurring affiliate commissions from platforms like HubSpot
  • A B2B procurement agent finding high-ticket industrial parts with hidden affiliate programs
  • A multilingual chatbot that auto‑detects user language and queries local e‑commerce stores
  • Agent‑to‑agent micropayment flows using USDC for each product search

常见问题

1

Which e‑commerce platforms does AgentMagnet support?

AgentMagnet covers 22 Amazon stores, 22 eBay stores, the Awin Network (15,000+ merchants), and AliExpress globally.

2

How does AgentMagnet handle language and region?

It auto‑detects the agent’s language and supports 52 languages across 30+ countries, so searches return local store results.

3

Can I deploy AgentMagnet on a VPS?

Yes. Use `python -m agentmagnet.http_server` to run in HTTP mode on a VPS, or `python -m agentmagnet` locally via stdio.

4

What payment system does AgentMagnet use for agent interactions?

It uses x402 micropayments with USDC, charging $0.001 per search for machine‑to‑machine payments.

5

Are there any runtime dependencies?

The README requires Python and lists dependencies in a `requirements.txt` file to be installed via `pip install -r requirements.txt`.

评论

其他 分类下的更多 MCP 服务器

Handl

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.

FastMCP v2 🚀

jlowin

🚀 The fast, Pythonic way to build MCP servers and clients.

26.0K

Health by Dr Brad

Dr Brad Stanfield

Health by Dr Brad works out a health plan from your own results: which screening is due at your age, and evidence-based suggestions, each with the reason and the published guideline or study behind it. Your record is one

Screenpipe

screenpipe

YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context

22.0K

Figs, Relationship Expert

Figs O'Sullivan, LMFT

Couples therapist Figs O'Sullivan (LMFT, 17 years, endorsed by Sue Johnson, creator of EFT) inside your AI. Ask relationship questions answered from his clinical writing, name the pattern in a fight, get a three-step rep

广告合作