extract
Extract specific values from a page as JSON instead of markdown prose — for when you need particular data, not the whole page. Honors per-domain auth and proxies.
How to use it
extract is exposed by the Intercept MCP MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the extract tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.
Install Intercept MCP
claude mcp add intercept -s user -- npx -y intercept-mcpOther tools in Intercept MCP (17)
(number, optional, 1-5, default 3) — Results to fetch
Fetch a URL and return its content as clean markdown.
Fetch up to 10 URLs in parallel, each through the same handler/fallback chain.
(string, optional) — day, week, month, or year
(number, optional, default 50000) — Maximum characters to return
(number, optional, 1-5) — Stop at this tier for speed-sensitive cases
(boolean, optional) — Skip session and shared caches and fetch live
(number, optional, 1-10) — Results page for pagination
(string, required) — Search query
Search the web and fetch the top results in one call — replaces a search followed by several fetches.
Search the web and return results.
(object, optional) — Map of field name → CSS selector. Each value is either a selector string (returns the first match's text) or { selector, attr?, all? } — attr extracts an attribute (e.g. href), all: true returns every match as an array.
(string, optional) — Restrict to a domain
(number, optional, default 0) — Character offset for paginating long content
(boolean, optional) — Convert every HTML table to an array of row objects (defaults to true when no selectors are given).
(string, required) — URL to fetch
(string[], required, 1-10) — URLs to fetch