Token-budgeted web fetching service for AI agents that intelligently routes requests between multiple extraction methods (Trafilatura, Jina, FireCrawl, pypdf) with built-in Redis caching and token estimation.
AgentFetch-MCP is an open-source Model Context Protocol (MCP) server that provides intelligent web content fetching for AI agents. It automatically routes requests to the most appropriate extraction method based on URL patterns, including Trafilatura for general web pages, Jina Reader for complex content, FireCrawl for dynamic sites, and pypdf for PDF documents. The tool implements token budgeting to estimate costs before fetching, preventing expensive token overages.
Deploy as an MCP server compatible with Claude, Claude Studio, or other MCP-compatible applications. The tool can be self-hosted using the open-source MIT-licensed code or accessed via the hosted REST API endpoint. Configuration involves setting API keys for preferred extraction services and Redis connection details for caching.
Monday.com MCP Server streamlines board management, item operations, and workflow automation for teams. I…
by NotionFlow
Sentry MCP Server provides comprehensive error tracking and performance monitoring, helping developers id…
by AnalyticsPro
Cloudflare MCP Server simplifies Cloudflare management by providing tools for DNS management, Workers dep…
by PricingBot