Categories › Knowledge & Everyday › Research, papers & reference data
Search 8.5M scientific papers with LLM TLDRs, citations, linked entities, figures, and full text.
Remote server: your requests and data go to mcp.tomesphere.com. Claude Code: claude mcp add --transport http tomesphere https://mcp.tomesphere.com/api/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
search_papers — Search 8.5 million academic papers (arXiv + biomedical: PMC / bioRxiv / medRxiv, all disciplines) by topic, keyword, author, or linked entitget_paper — Fetch a paper's full metadata: title, authors, year, abstract, TLDR (LLM-generated), key findings, citation count, GitHub repos, HuggingFacesimilar_papers — Find papers semantically similar to a given paper using SPECTER2 embeddings (trained on scientific-citation triplets). Returns nearest neighcitations — Get papers that cite the given paper (who refers to this work). Use when the user asks 'who cites X', 'what's the impact', or wants follow-ureferences — Get the papers that this paper cites (its bibliography). Use when the user asks 'what does X cite' or 'show me the references'.get_full_text — Fetch a paper's full body text as Markdown (methods, results, protocols, inline tables) — use for deep questions the abstract can't answer. get_figures — Get a paper's real figure images — URLs, labels, and captions. Most biomedical papers have figures; arXiv papers often don't. Accepts an arXget_entities — Get the biomedical entities linked to a paper: genes, proteins, chemicals, diseases, species, mutations, cell lines, and clinical-trial (NCTget_structure — Resolve a gene/protein name (e.g. 'TP53', 'CD44') or UniProt accession to its 3D structure — returns the UniProt accession + AlphaFold modelNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.