Connect tomesphere and your agent gets 9 tools, among them citations, get_entities, get_figures. It answers at https://mcp.tomesphere.com/api/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 10 of 10 times since 5 September 2026; the last check, on 18 October 2026, succeeded.
Search 8.5M scientific papers with LLM TLDRs, citations, linked entities, figures, and full text.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
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. Inputs: id, k |
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. Inputs: id |
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. Inputs: id |
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/…). Inputs: id |
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 '1706.0 Inputs: id |
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. Inputs: name |
references | Get the papers that this paper cites (its bibliography). Use when the user asks 'what does X cite' or 'show me the references'. Inputs: id, k |
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 Inputs: query, k, year_min, year_max |
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'. Inputs: id, k |
Every block below points at https://mcp.tomesphere.com/api/mcp. Pick your client and copy.
claude mcp add --transport http tomesphere https://mcp.tomesphere.com/api/mcp
{
"mcpServers": {
"tomesphere": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp.tomesphere.com/api/mcp"]
}
}
}{
"mcpServers": {
"tomesphere": {
"url": "https://mcp.tomesphere.com/api/mcp"
}
}
}{
"servers": {
"tomesphere": {
"type": "http",
"url": "https://mcp.tomesphere.com/api/mcp"
}
}
}{
"context_servers": {
"tomesphere": {
"url": "https://mcp.tomesphere.com/api/mcp"
}
}
}{
"mcpServers": {
"tomesphere": {
"serverUrl": "https://mcp.tomesphere.com/api/mcp"
}
}
}{
"mcpServers": {
"tomesphere": {
"url": "https://mcp.tomesphere.com/api/mcp"
}
}
}name: tomesphere
version: 0.0.1
schema: v1
mcpServers:
- name: tomesphere
type: streamable-http
url: https://mcp.tomesphere.com/api/mcp{
"mcpServers": {
"tomesphere": {
"httpUrl": "https://mcp.tomesphere.com/api/mcp"
}
}
}{
"mcpServers": {
"tomesphere": {
"type": "http",
"url": "https://mcp.tomesphere.com/api/mcp"
}
}
}{
"mcpServers": {
"tomesphere": {
"url": "https://mcp.tomesphere.com/api/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fmcp.tomesphere.com%2Fapi%2Fmcp&type=streamable_http&id=tomesphere&name=tomesphere
It answered our last check on 18 October 2026 in 360 ms. Over 10 checks since 5 September 2026 it answered 10. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by tomesphere.com and served from mcp.tomesphere.com, the vendor's own domain: https://mcp.tomesphere.com/api/mcp.
9, as returned by the server's own tools/list on 31 August 2026: citations, get_entities, get_figures, get_full_text, get_paper, get_structure, references, search_papers, and 1 more.
It answered our last check on 18 October 2026 in 360 ms. Over 10 checks since 5 September 2026 it answered 10.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://mcp.tomesphere.com/api/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: com.tomesphere. Endpoint host: mcp.tomesphere.com. ARD identifier: urn:air:com.tomesphere:mcp:tomesphere.
First indexed 31 August 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.