Terminal
Terminal/Skill
Reads the full text of a webpage from a specific URL as clean markdown, and can batch several URLs in one call.
By Exa
Works with
npx skills add exa-labs/exa-cursor-plugin --skill exa-fetchExtract content from: $ARGUMENTS
Use web_fetch_exa to get the full text of a webpage.
Trigger phrases: "read this page", "fetch this URL", "extract content from", "get the page at", "what does this link say", or when a user shares a URL.
Use web_search_exa instead when you don't have a URL and need to find pages first.
web_fetch_exa accepts:
urls (array of strings, required) — the URLs to extract content frommaxCharacters (number, optional) — max characters to return per page (default: 3000)maxCharacters: 1000-2000maxCharacters: 3000 (default)maxCharacters: 5000-10000You can fetch multiple URLs in a single call:
web_fetch_exa({
"urls": ["https://example.com/page1", "https://example.com/page2"],
"maxCharacters": 3000
})
Check if Exa MCP is installed by confirming web_fetch_exa is available in your tool list.
/exa-setup command in Cursor to add the Exa MCP server.