firecrawl_research_* MCP tools or the firecrawl research CLI subcommands. Calling firecrawl_search with its categories option set to [\"research\"] is a different feature — it filters ordinary web search to research-affiliated websites (the list includes PubMed, bioRxiv, medRxiv, arXiv, and publisher sites) and returns page results from them, without querying the paper records in this index.Find the research papers that answer a research query. Some questions have a single answer; many have several — and when in doubt, lean toward returning the fuller relevant set (most relevant first) rather than narrowing to one. A reader is better served seeing the neighboring methods and papers than having them silently dropped.
\nPaper abstracts, with full text reachable per paper. The largest share of the corpus is biomedical and life-science literature — PubMed journal articles plus bioRxiv and medRxiv preprints — so clinical, drug, gene, disease, epidemiology, and public-health questions are in scope. arXiv preprints cover computer science, physics, and mathematics. Coverage outside those sources is thinner: a paper that exists only behind a publisher paywall or in a niche venue may not be indexed, and the general web tools below are the fallback when it isn't.
\nThere is no fixed recipe. Read the query, decide what kind it is, and choose the approach below. Some queries need a single search; others need heavy structural/semantic expansion. Don't run machinery a query doesn't call for.
\nMCP: firecrawl_research_search_papers(query, k?)\nCLI: firecrawl research search-papers <query> [--k <number>]\nSemantic (HyDE) search over abstracts. The natural first move for almost any query.\nIf results look thin or all-alike, re-run with a different framing (sibling domain, rival method, dataset/benchmark name) rather than giving up.
MCP: firecrawl_research_related_papers(seed_ids, intent, mode?, k?)\nCLI: firecrawl research related-papers <seedIds...> --intent <intent> [--mode <similar|citers|references>] [--k <number>]\nSemantic and structural expansion, ranked to your intent.\nThis reaches papers semantic search cannot, and it's how you turn one good hit into the rest of a set.\nmode=similar → niche siblings; citers → who uses/builds on the seeds; references → what they build on / compare against.
MCP: firecrawl_research_inspect_paper(id)\nCLI: firecrawl research inspect-paper <id>\nCanonical metadata for one paper: title, abstract, authors, categories, source ids, and dates.\nUse it after search_papers or related_papers when you need the complete citation/metadata for a candidate, or when you have an id from elsewhere and need to confirm what paper it resolves to.\nThis does not read the paper body; use read_paper for specific full-text questions.
MCP: firecrawl_research_read_paper(id, question)\nCLI: firecrawl research read-paper <id> --question <question>\nIn-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).\nUse it to settle a specific doubt, not on everything.
MCP: firecrawl_search(query, categories: [\"research\"])\nCLI: firecrawl search <query> --categories research\nNot this index. This is a website filter: it restricts a normal web search to a short list of research-affiliated domains — the list does include pubmed.ncbi.nlm.nih.gov, biorxiv.org, medrxiv.org, and arxiv.org alongside publisher sites — and returns page results in a research group beside web, each with url, title, description (the matched passage), position, and category: \"research\" — web results carry no category, so that is the field to key on when merging.\nSo it reaches those sites' web pages; what it does not do is query their paper records in this index — no semantic search over abstracts, no citation-graph or related-paper expansion, no canonical paper metadata, and no in-body passages. The results are ordinary web results.\nUse it when you are already running a web search and want those sites weighed in the same call. For anything that is actually a paper-finding task, use firecrawl_research_search_papers and its siblings above.
MCP: firecrawl_search(query) / firecrawl_scrape(url)\nCLI: firecrawl search <query> / firecrawl scrape <url>\nGeneral 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.\"\nFind the ranking on the web, then map the top entries back to papers with search_papers.\nReach for these only when the corpus can't answer the question on its own.
search_papers, done. This is the only case that truly wants exactly one paper.related_papers and include the closely-related methods/papers too. Even when one paper is the exact literal match, surface and keep its neighbors — don't narrow to the single best hit and reason the rest out. Only treat it as one-answer if the query names a specific paper.related_papers earns its keep: expand several strong anchors with mode=similar, re-seed from new strong hits. One search is never enough here.citers/references, and use read_paper to confirm a candidate actually uses P.firecrawl_search / firecrawl_scrape to find the benchmark's leaderboard or rankings, read off the top models/papers, then search_papers each to get its paper. As a fallback, search the benchmark and read_paper candidates for reported numbers. The hardest kind — cast wide.read_paper) before keeping a paper.read_paper(X, ...) or related_papers([X], ..., mode=\"references\").firecrawl_research_* / firecrawl research. The categories: [\"research\"] option on firecrawl_search is a website filter — it does point web search at PubMed, bioRxiv, medRxiv, arXiv, and publisher sites, but what comes back is their web pages, not paper records. If a task is about finding papers, the tools in this skill are the ones that read the corpus; reaching for categories: [\"research\"] will quietly answer a different question.search_papers reads.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.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.