Erodenn/fetch-guard

Overview

Fetch URLs and return clean, LLM-ready markdown with metadata and layered prompt injection defense. Configurable timeouts, word limits, JS rendering, and link extraction. All-in-one MCP server + CLI.

Best for

Best for
Developers needing a secure, configurable web-to-markdown pipeline for LLM workflows

Use cases

• Convert web pages to markdown for LLM context ingestion
• Scrape content with configurable word limits and timeouts
• Extract links and metadata from URLs with JS rendering

Notes

Fetch URLs and return clean, LLM-ready markdown with metadata and layered prompt injection defense. Configurable timeouts, word limits, JS rendering, and link extraction. All-in-one MCP server + CLI.

0 stars on GitHub. Last updated 2026-03-23. Licensed MIT.

Use cases

• Convert web pages to markdown for LLM context ingestion
• Scrape content with configurable word limits and timeouts
• Extract links and metadata from URLs with JS rendering

Pros

• Built-in prompt injection defense layers
• Supports JavaScript rendering for dynamic content
• Works as both MCP server and CLI tool

Cons

• Zero stars and no community traction yet
• Python-only, limiting integration options
• No mention of caching or rate limiting

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.