MCP Server

tomesphere

com.tomesphere/tomesphere
Science & Engineering Search & Research Public & reachable MCP 2026-07-28

What this MCP does

Searches and retrieves scientific papers, full text, citations, figures, linked biomedical entities, related papers, and protein structure references.

citations
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-up work. Note: 2024+ citation coverage is sparse; indexing in progress.
Read only Open world
Input schema
{'type': 'object', 'required': ['id'], 'properties': {'k': {'type': 'integer', 'default': 25, 'description': 'Max citing papers (default 25, max 100).'}, 'id': {'type': 'string', 'description': 'arXiv ID or OpenAlex Work ID.'}}}
get_entities
Get the biomedical entities linked to a paper: genes, proteins, chemicals, diseases, species, mutations, cell lines, and clinical-trial (NCT) IDs. Accepts an arXiv ID, PMC ID, or bioRxiv/medRxiv DOI.
Read only Open world
Input schema
{'type': 'object', 'required': ['id'], 'properties': {'id': {'type': 'string', 'description': 'arXiv ID, PMC ID, or 10.1101/… DOI.'}}}
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 arXiv ID, PMC ID, or bioRxiv/medRxiv DOI.
Read only Open world
Input schema
{'type': 'object', 'required': ['id'], 'properties': {'id': {'type': 'string', 'description': 'arXiv ID, PMC ID, or 10.1101/… DOI.'}}}
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. Accepts an arXiv ID (2401.12345), a PMC ID (PMC5339222), or a bioRxiv/medRxiv DOI (10.1101/…).
Read only Open world
Input schema
{'type': 'object', 'required': ['id'], 'properties': {'id': {'type': 'string', 'description': 'arXiv ID, PMC ID, or 10.1101/… DOI.'}}}
get_paper
Fetch a paper's full metadata: title, authors, year, abstract, TLDR (LLM-generated), key findings, citation count, GitHub repos, HuggingFace models/datasets, videos, peer reviews, and links. Accepts an arXiv ID (e.g. '2401.12345' or '1706.03762v5') or an OpenAlex Work ID (e.g. 'W4390723197'). Use when the user names a specific paper or pastes an arXiv link.
Read only Open world
Input schema
{'type': 'object', 'required': ['id'], 'properties': {'id': {'type': 'string', 'description': "arXiv ID like '2401.12345' or OpenAlex Work ID like 'W4390723197'."}}}
get_structure
Resolve a gene/protein name (e.g. 'TP53', 'CD44') or UniProt accession to its 3D structure — returns the UniProt accession + AlphaFold model URL (and PDB when available). Great for a gene named in a paper's entities.
Read only Open world
Input schema
{'type': 'object', 'required': ['name'], 'properties': {'name': {'type': 'string', 'description': 'Gene/protein symbol (TP53, CD44) or UniProt accession (P04637).'}}}
references
Get the papers that this paper cites (its bibliography). Use when the user asks 'what does X cite' or 'show me the references'.
Read only Open world
Input schema
{'type': 'object', 'required': ['id'], 'properties': {'k': {'type': 'integer', 'default': 25, 'description': 'Max references (default 25, max 100).'}, 'id': {'type': 'string', 'description': 'arXiv ID or OpenAlex Work ID.'}}}
search_papers
Search 8.5 million academic papers (arXiv + biomedical: PMC / bioRxiv / medRxiv, all disciplines) by topic, keyword, author, or linked entity (gene / protein / disease). Each hit returns id, title, TLDR, type, and links. Use to find papers about a topic, e.g. 'transformer efficiency' or 'CRISPR base editing'.
Read only Open world
Input schema
{'type': 'object', 'required': ['query'], 'properties': {'k': {'type': 'integer', 'default': 10, 'description': 'Number of results (default 10, max 25).'}, 'query': {'type': 'string', 'description': "Natural-language search query. E.g. 'transformer attention efficiency', 'graph neural networks for molecular property prediction'."}, 'year_max': {'type': 'integer', 'description': 'Latest publication year.'}, 'year_min': {'type': 'integer', 'description': 'Earliest publication year, e.g. 2024.'}}}
similar_papers
Find papers semantically similar to a given paper using SPECTER2 embeddings (trained on scientific-citation triplets). Returns nearest neighbors with TLDR. Use when the user wants 'papers like X' or 'what's adjacent to this work'.
Read only Open world
Input schema
{'type': 'object', 'required': ['id'], 'properties': {'k': {'type': 'integer', 'default': 10, 'description': 'Number of neighbors (default 10, max 25).'}, 'id': {'type': 'string', 'description': 'arXiv ID or OpenAlex Work ID.'}}}
Added
get_structure
Sept. 17, 2026, 12:38 p.m.
Added
get_entities
Sept. 17, 2026, 12:38 p.m.
Added
get_figures
Sept. 17, 2026, 12:38 p.m.
Added
get_full_text
Sept. 17, 2026, 12:38 p.m.
Added
references
Sept. 17, 2026, 12:38 p.m.
Added
citations
Sept. 17, 2026, 12:38 p.m.
Added
similar_papers
Sept. 17, 2026, 12:38 p.m.
Added
get_paper
Sept. 17, 2026, 12:38 p.m.
Added
search_papers
Sept. 17, 2026, 12:38 p.m.