DeepFetch
Verified IntegrationClient Configuration
— Connect DeepFetch to Claude Desktop or Cursor in seconds{
"mcpServers": {
"deepfetch": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-deepfetch"
],
"env": {}
}
}
}~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows).System Overview
Provides a semantic web search and PDF extraction server for Model Context Protocol clients, leveraging Kagi, Scrapfly, and local ONNX reranking.
7/23/2026
Open Source
stdio / SSE RPC
Frequently Asked Questions
Architecture and operational details for DeepFetch
Deployment is simplified with Docker. Users only need Docker installed along with API keys for Kagi and Scrapfly. This allows for quick setup and enables local `stdio` transport, with options for managed deployments via `streamable-http`.
Related MCP Servers
Browse all servers →Empower AI assistants to generate and convert documents, manage templates, and automate document workflows efficiently.
Provides a multi-tenant, AI-native Content Delivery Network deployable on Cloudflare, featuring sub-100ms TTFB, AI agent controllability, and comprehensive accessibility.
Deploy a Model Context Protocol server on Cloudflare Workers without requiring authentication.