SciWeave MCP Serverofficial
F
licenseNot graded
qualityD
maintenanceGround Claude, ChatGPT, Cursor, and Windsurf in 300M scientific works — every citation a verifiable DOI.
-
tomesphere
Server Details
Search 8.5M scientific papers with LLM TLDRs, citations, linked entities, figures, and full text.
If you are the author of this connector, you can claim ownership by verifying the domain or GitHub account it belongs to. Claimed connector authors can inspect health checks, view analytics, and manage their listing.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- OAuth
- Works in Glama
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-03-26
- URL
- ChatGPT
- –
- Claude
- –
TDQS
A4.1/5.0
Scored across 9 tools
Disambiguation5/5
Each tool targets a distinct resource: citations vs references cleanly split citing vs cited papers, get_paper/get_full_text/get_figures/get_entities each retrieve a different aspect of a paper, and search_papers vs similar_papers are clearly different retrieval modes. No two tools appear interchangeable.
Naming Consistency4/5
The majority follow a consistent 'get_' + noun pattern (get_paper, get_full_text, get_entities, get_figures, get_structure), with search_papers and similar_papers as verb/adjective+noun. However, 'citations' and 'references' are bare nouns, deviating slightly from the pattern, so naming is mostly but not fully uniform.
Tool Count5/5
Nine tools form a well-scoped set for a scholarly-paper server, covering discovery (search, similar), retrieval (paper, full text, figures), graph relations (references, citations), and extra metadata (entities, structures). Each tool serves a clear purpose with no redundancy.
Completeness4/5
The core workflows for finding, fetching, and exploring papers are well covered: search, metadata, full text, figures, references, citations, and entities. Minor gaps exist such as no direct author/profile lookup or batch retrieval, and some deep API-specific features are absent, but these do not block common tasks.
Available Tools
9 toolscitationsARead-onlyInspect
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.
| Name | Required | Description | Default |
|---|---|---|---|
| k | No | Max citing papers (default 25, max 100). | |
| id | Yes | arXiv ID or OpenAlex Work ID. |
get_entitiesARead-onlyInspect
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.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | arXiv ID, PMC ID, or 10.1101/… DOI. |
get_figuresARead-onlyInspect
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.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | arXiv ID, PMC ID, or 10.1101/… DOI. |
get_full_textARead-onlyInspect
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/…).
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | arXiv ID, PMC ID, or 10.1101/… DOI. |
get_paperARead-onlyInspect
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.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | arXiv ID like '2401.12345' or OpenAlex Work ID like 'W4390723197'. |
get_structureARead-onlyInspect
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.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Gene/protein symbol (TP53, CD44) or UniProt accession (P04637). |
referencesARead-onlyInspect
Get the papers that this paper cites (its bibliography). Use when the user asks 'what does X cite' or 'show me the references'.
| Name | Required | Description | Default |
|---|---|---|---|
| k | No | Max references (default 25, max 100). | |
| id | Yes | arXiv ID or OpenAlex Work ID. |
search_papersARead-onlyInspect
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'.
| Name | Required | Description | Default |
|---|---|---|---|
| k | No | Number of results (default 10, max 25). | |
| query | Yes | Natural-language search query. E.g. 'transformer attention efficiency', 'graph neural networks for molecular property prediction'. | |
| year_max | No | Latest publication year. | |
| year_min | No | Earliest publication year, e.g. 2024. |
similar_papersARead-onlyInspect
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'.
| Name | Required | Description | Default |
|---|---|---|---|
| k | No | Number of neighbors (default 10, max 25). | |
| id | Yes | arXiv ID or OpenAlex Work ID. |
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
9 tool updates
- First observed
citations - First observed
get_entities - First observed
get_figures - First observed
get_full_text - First observed
get_paper - First observed
get_structure - First observed
references - First observed
search_papers - First observed
similar_papers
Related MCP Connectors
Search 340M+ academic papers — citation graphs, semantic similarity, and AI literature reviews.
Search 220M+ scholarly papers with abstracts, DOIs, retraction flags and citation links.
Academic paper search, scientific literature, citation analysis, arXiv & semantic related-work.
Linked life-science search: 43M+ papers, 1.2M+ trials, drugs, genes, FDA/EMA approvals, patents.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables searching and exploring 340 million academic papers from 15+ databases with semantic search, citation graphs, and knowledge graph connections for biomedical entities.1MIT
Inciteful MCPofficial
AlicenseAqualityBmaintenanceEnables scholarly paper search, citation graph exploration, literature reviews, and full-text retrieval by combining OpenAlex metadata with Inciteful citation data.93MIT- AlicenseAqualityBmaintenanceMCP server for scientific grounding: search and discover open-access research papers across arXiv, OpenAlex, Crossref, PubMed, and Semantic Scholar, and retrieve references/citations from paywalled journals via public DOI/abstract metadata.3124 PyPI7MIT
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd
Glama MCP Gateway
Add one secure layer between your agents and this server.