Firecrawl Research Index Skill 安全审计

1718- MCP: **`firecrawl_research_search_papers(query, k?)`**19  CLI: **`firecrawl research search-papers <query> [--k <number>]`**20  Semantic (HyDE) search over **abstracts**. The natural first move for almost any query.21  If results look thin or all-alike, re-run with a different framing (sibling domain, rival method, dataset/benchmark name) rather than giving up.

2223- MCP: **`firecrawl_research_related_papers(seed_ids, intent, mode?, k?)`**24  CLI: **`firecrawl research related-papers <seedIds...> --intent <intent> [--mode <similar|citers|references>] [--k <number>]`**25  Semantic and structural expansion, ranked to your `intent`.26  This reaches papers semantic search _cannot_, and it's how you turn one good hit into the rest of a set.27  `mode=similar` → niche siblings; `citers` → who uses/builds on the seeds; `references` → what they build on / compare against.28

3435- MCP: **`firecrawl_research_read_paper(id, question)`**36  CLI: **`firecrawl research read-paper <id> --question <question>`**37  In-body passages of **one** paper, to verify a load-bearing constraint (a method actually used, a score actually reported, an affiliation, what a paper compares to).38  Use it to settle a specific doubt, not on everything.39

4546- MCP: **`firecrawl_search(query)` / `firecrawl_scrape(url)`**47  CLI: **`firecrawl search <query>` / `firecrawl scrape <url>`**48  General **web** search and page fetch, for facts that don't live in paper abstracts: benchmark **leaderboards**, rankings, "who scores best / is largest / is most used."49  Find the ranking on the web, then map the top entries back to papers with `search_papers`.50  Reach for these only when the corpus can't answer the question on its own.51

65- **Query shape and subject field are separate.** A clinical-trial question and a machine-learning question take the same shapes above; what differs is only which source the hits come from. Don't send a biomedical or life-science query to the open web on the assumption the corpus is arXiv-only — PubMed, bioRxiv, and medRxiv are the largest part of what `search_papers` reads.66- **When in doubt, include.** For any topic / method / comparison question, return the relevant _family_, not just the single best match — err toward keeping a plausibly-relevant paper rather than dropping it. The neighboring methods are part of a good answer; don't reason close work out just because one paper is the most exact match.67- **Follow the literature, and keep what you find.** The seminal source, the competing methods, the close neighbors are usually a hop away — use `related_papers`, and _include_ them, not just the first hit. Stopping at one good result is the most common way to leave the reader with half an answer.68- **Verify to exclude, not to gatekeep.** Use `read_paper` to rule a paper _out_ when a hard constraint clearly fails (wrong org/author, doesn't actually report the score). When a paper is plausibly relevant, lean toward keeping it rather than demanding proof.69- **Only drop the clearly off-topic.** Don't pad with papers you're confident are unrelated — but that's a high bar; most plausibly-relevant work should make the cut.70