Single Google search via browser, SearchApi primary, or browser-to-SearchApi fallback. Returns title, URL, and snippet. Results are cached 24h. For latest/today/breaking queries set SURF_CACHE_TTL_SEARCH_MS=0 to bypass the cache. Browser is the default provider and requires no API key. Default limit 10, max 20.

Search Google Scholar via browser, SearchApi primary, or fallback. Returns title, authors, publication, year, snippet, citation count, related/version links, and an available full-text link. Results are cached with the same TTL as search. Max 10 papers per call.

Run 2-10 Google searches with the provider selected by SURF_SEARCH_PROVIDER. Browser mode uses a worker pool. SearchApi primary and fallback work in cloud mode. Per-query browser failures are isolated and replaced individually in fallback mode.

Fetch one public URL -> clean article text. HTML via Mozilla Readability; academic PDFs (arxiv/biorxiv/Nature/OpenReview/NeurIPS/JMLR/PMLR/Springer/PubMed-via-PMC) auto-detected via Content-Type, %PDF magic, citation_pdf_url meta, and per-domain URL rules. Tiered depth: mode="abstract" returns ~1500 chars (PDF page 1 or HTML meta description) -- cheap survey to triage relevance before paying for full body. mode="full" (default) returns the whole article. Best-effort: failures return an errorInfo instead of throwing.

One-shot Google search + parallel extract of the top results. Default mode="abstract" returns SERP enriched with ~1500-char abstracts per result -- a cheap survey of what the top results actually contain, far fewer tokens than fetching all bodies. Switch to mode="full" only when you need the actual article texts (slower, much more tokens). Per-page extract failures are isolated. Disabled in cloud mode.

MCP server status: cascade mode + transitions, rate-limiter usage, cache size, config. Call this if searches start failing or returning empty -- check cascade.totalCaptchas and rateLimiter.queueSize, and reduce search volume if they are high.