fetch vs Custom-MCP-Server
Side-by-side comparison to help you pick between these two MCP servers.
fetch by modelcontextprotocol | Custom-MCP-Server by Sharan-Kumar-R | |
|---|---|---|
| Stars | ★ 85,748 | ★ 75 |
| 30d uses | — | — |
| Score | 76 | 40 |
| Official | ✓ | — |
| Categories | Web ScrapingAI / LLM ToolsProductivity | Web ScrapingDeveloper ToolsOther |
| Language | TypeScript | Python |
| Last commit | this month | 11 mo ago |
fetch · Summary
An MCP server that fetches web content and converts HTML to markdown, allowing LLMs to read web pages.
Custom-MCP-Server · Summary
An MCP server providing scraping tools for LinkedIn, Facebook, Instagram, and Google search.
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
Custom-MCP-Server · Use cases
- Researching professional backgrounds via LinkedIn profiles
- Gathering public information about individuals from social media
- Performing web searches and social media monitoring for intelligence gathering
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"]
}
}
}Custom-MCP-Server · Install
Installation
- Add MCP to your Python project using uv:
uv init custom-mcp-server
cd custom-mcp-server
uv add "mcp[cli]"- Install additional dependencies:
uv add httpx python-dotenv fastmcp- Add API keys to your
.envfile:
RAPIDAPI_KEY=your_rapidapi_key_here
SERPER_API_KEY=your_serper_api_key_here- Install the server:
uv run mcp install main.pyFor Claude Desktop, restart the app after installation to see the new tools.