Add AgentFetch — token-budgeted web fetch for AI agents
bch1212 committed
Apr 28, 2026 at 08:42 UTC
d8b9716d32664da2690fe53fea4da4bef71977fa
1 file changed
+1
README.md
+1
@@ -296,6 +296,7 @@ Web content access and automation capabilities. Enables searching, scraping, and
296
- [apireno/DOMShell](https://github.com/apireno/DOMShell) [](https://glama.ai/mcp/servers/@apireno/domshell) 📇 🏠 - Browse the web using filesystem commands (ls, cd, grep, click). 38 MCP tools map Chrome's Accessibility Tree to a virtual filesystem via a Chrome Extension.
297
- [automatalabs/mcp-server-playwright](https://github.com/Automata-Labs-team/MCP-Server-Playwright) 🐍 - An MCP server for browser automation using Playwright
298
- [BB-fat/browser-use-rs](https://github.com/BB-fat/browser-use-rs) 🦀 Lightweight browser automation MCP server in Rust with zero dependencies.
299
+- [bch1212/agentfetch-mcp](https://github.com/bch1212/agentfetch-mcp) 🐍 ☁️ 🏠 🍎 🪟 🐧 - Token-budgeted web fetch for AI agents. Auto-routes between Trafilatura, Jina Reader, FireCrawl, and pypdf based on URL pattern. `estimate_tokens` before `fetch_url`, 6h Redis cache, server-side `max_tokens` truncation. Open source MCP server (MIT) plus hosted REST API at [agentfetch.dev](https://www.agentfetch.dev) — 500 free fetches/mo, no card.
300
- [bighippoman/intercept-mcp](https://github.com/bighippoman/intercept-mcp) [](https://glama.ai/mcp/servers/bighippoman/intercept-mcp) 📇 🏠 - Multi-tier fallback chain for fetching web content as clean markdown. Handles tweets, YouTube, arXiv, PDFs, and regular pages with 9 fallback strategies.
301
- [blackwhite084/playwright-plus-python-mcp](https://github.com/blackwhite084/playwright-plus-python-mcp) 🐍 - An MCP python server using Playwright for browser automation,more suitable for llm
302
- [browserbase/mcp-server-browserbase](https://github.com/browserbase/mcp-server-browserbase) 🎖️ 📇 - Automate browser interactions in the cloud (e.g. web navigation, data extraction, form filling, and more)