amazon-sp-mcp vs fetch
Side-by-side comparison to help you pick between these two MCP servers.
amazon-sp-mcp by mansournorouzi | fetch by modelcontextprotocol | |
|---|---|---|
| Stars | ★ 29 | ★ 85,748 |
| 30d uses | — | — |
| Score | 44 | 76 |
| Official | — | ✓ |
| Categories | E-commerceFinanceProductivity | Web ScrapingAI / LLM ToolsProductivity |
| Language | TypeScript | TypeScript |
| Last commit | 1 mo ago | this month |
amazon-sp-mcp · Summary
Amazon SP-API MCP server connects Claude to Seller Central for sales, inventory, orders, and financial data using LWA OAuth authentication.
fetch · Summary
An MCP server that fetches web content and converts HTML to markdown, allowing LLMs to read web pages.
amazon-sp-mcp · Use cases
- Automate sales and inventory analysis through natural language queries
- Track reimbursements, settlements, and fees without logging into Seller Central
- Generate performance reports for specific products or time periods
fetch · Use cases
- LLMs reading news articles and blogs
- Content analysis of web pages
- Retrieving information from public websites
- Chunked reading of large web documents
amazon-sp-mcp · Install
# Clone and install
git clone https://github.com/mansournorouzi/amazon-sp-mcp.git
cd amazon-sp-mcp
npm install
npm run build
# Configure credentials
cp .env.example .env
# Edit .env with your LWA credentials, Seller ID, Marketplace ID
# For Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
```json
{
"mcpServers": {
"amazon-seller": {
"command": "node",
"args": ["/path/to/amazon-sp-mcp/build/index.js"],
"env": {
"LWA_CLIENT_ID": "amzn1.application-oa2-client.xxxxx",
"LWA_CLIENT_SECRET": "your_secret",
"LWA_REFRESH_TOKEN": "Atzr|your_token",
"SELLER_ID": "your_seller_id",
"MARKETPLACE_ID": "ATVPDKIKX0DER",
"SP_API_ENDPOINT": "https://sellingpartnerapi-na.amazon.com"
}
}
}
}fetch · Install
Installation
**Using uv (recommended)** No specific installation needed. Use uvx to run the server directly:
uvx mcp-server-fetch**Using PIP** Install via pip:
pip install mcp-server-fetchThen run as:
python -m mcp_server_fetchClaude Desktop Configuration
{
"mcpServers": {
"fetch": {
"command": "uvx",
"args": ["mcp-server-fetch"]
}
}
}