Enables fetching and converting web content to markdown with built-in prompt injection safeguards that detect and block malicious content attempting to manipulate the LLM.
Enables AI agents to perform web searches, fetch and extract page content, and crawl sites with caching, rate limiting, and robots.txt compliance, all without needing API keys.
Enables AI agents to fetch and extract clean, readable content from web pages, and search within pages for specific queries, without needing a full browser.
Enables LLMs to perform web search and fetch with a frozen cutoff date, enforcing server-side time-lock and usage budgets to prevent lookahead contamination.
Enables LibreChat assistants to browse and fetch web content only from an allowlisted set of domains, with the allowed origins made visible to the model. It runs as a streamable-HTTP Docker service that enforces domain restrictions and supports sites like GitHub, Wikipedia, and Google.