exa-mcp-server vs fetch
Side-by-side comparison to help you pick between these two MCP servers.
exa-mcp-server by exa-labs | fetch by modelcontextprotocol | |
|---|---|---|
| Stars | ★ 4,436 | ★ 85,748 |
| 30d uses | — | — |
| Score | 59 | 76 |
| Official | — | ✓ |
| Categories | SearchWeb ScrapingDeveloper Tools | Web ScrapingAI / LLM ToolsProductivity |
| Language | TypeScript | TypeScript |
| Last commit | this month | this month |
exa-mcp-server · Summary
MCP server for Exa web search and web crawling capabilities with support for multiple AI clients.
fetch · Summary
An MCP server that fetches web content and converts HTML to markdown, allowing LLMs to read web pages.
exa-mcp-server · Use cases
- Enhancing AI assistants with real-time web search capabilities
- Conducting company research and competitive analysis
- Searching for code examples and technical documentation
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
exa-mcp-server · Install
Installation
- **Hosted MCP Server (Recommended)**:
Connect to Exa's hosted MCP server: https://mcp.exa.ai/mcp
- **Via npm Package**:
``json { "mcpServers": { "exa": { "command": "npx", "args": ["-y", "exa-mcp-server"], "env": { "EXA_API_KEY": "your_api_key" } } } } ``
- **Claude Desktop**:
Add to your config file: ``json { "mcpServers": { "exa": { "command": "npx", "args": ["-y", "mcp-remote", "https://mcp.exa.ai/mcp"] } } } ``
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"]
}
}
}