Kagi-Session2API-MCP vs fetch
Side-by-side comparison to help you pick between these two MCP servers.
Kagi-Session2API-MCP by KSroido | fetch by modelcontextprotocol | |
|---|---|---|
| Stars | ★ 134 | ★ 85,748 |
| 30d uses | — | — |
| Score | 48 | 76 |
| Official | — | ✓ |
| Categories | SearchWeb ScrapingAI / LLM Tools | Web ScrapingAI / LLM ToolsProductivity |
| Language | Python | TypeScript |
| Last commit | 1 mo ago | this month |
Kagi-Session2API-MCP · Summary
Free Kagi Search MCP server using session tokens instead of paid API, works with multiple MCP clients.
fetch · Summary
An MCP server that fetches web content and converts HTML to markdown, allowing LLMs to read web pages.
Kagi-Session2API-MCP · Use cases
- Integrate free Kagi search capabilities into AI agents like Claude Desktop and Cursor
- Build applications requiring web search without paying for Kagi's API
- Create summarization tools for web content using Kagi's internal summarizer
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
Kagi-Session2API-MCP · Install
Install via pip:
pip install kagi-session2api-mcpFor Claude Desktop, add to your claude_desktop_config.json:
{
"mcpServers": {
"kagi-session": {
"command": "uvx",
"args": ["kagi-session2api-mcp"],
"env": {
"KAGI_SESSION_TOKEN": "YOUR_SESSION_TOKEN_HERE"
}
}
}
}Or with config file for multiple tokens:
{
"mcpServers": {
"kagi-session": {
"command": "uvx",
"args": ["kagi-session2api-mcp"],
"env": {
"KAGI_SESSION_CONFIG": "/path/to/config.toml"
}
}
}
}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"]
}
}
}