litreview-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OPENALEX_API_KEY | No | A free OpenAlex API key. Optional; without it, requests share the anonymous rate limit. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Tools for literature reviews, backed by OpenAlex. A typical review: use search_papers sorted by citations to find seminal work, search again sorted by newest with a recent from_year for current research, use get_citations to follow the trail from key papers, then get_paper for abstracts and citations. Only cite papers these tools returned. Never invent a citation.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_papersA | Search scholarly papers by topic, matching titles and abstracts. Returns compact summaries without abstracts; use get_paper for details. Put exact phrases in double quotes for much better precision, e.g. "growth mindset" teachers. With sort "citations" or "newest", results are the top 200 most relevant papers re-ranked, so a famous paper that matches the query poorly can be missed. Each search uses some of the server's daily budget, so prefer a few well-chosen queries. |
| get_paperA | Get one paper's abstract, full author list, citation count and a draft APA citation. The citation is generated from metadata: check author names and title capitalization before using it. The abstract is null when OpenAlex doesn't have one. |
| get_citationsA | Follow the citation trail from a paper, most cited first. Direction "cited_by" finds later papers that cite it, which shows how the idea developed. Direction "references" finds the papers it cites, which shows its foundations. |
| find_open_pdfA | Find a free, legal copy of a paper. Returns a direct pdf_url when one is known, and otherwise a read_online_url. Both are null if no open copy is known, in which case the paper is probably paywalled. Check the version field: a preprint can differ from the published paper. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
Each tool targets a distinct action on the paper domain: retrieval by ID (get_paper), discovery by query (search_papers), citation traversal (get_citations), and open-access resolution (find_open_pdf). Descriptions explicitly cross-reference each other (search_papers says use get_paper for details), eliminating overlap.
All four tools follow a consistent verb_noun snake_case pattern: get_paper, search_papers, get_citations, find_open_pdf. The verbs are used meaningfully and consistently across the set.
Four tools is lean but fits a focused literature-review server where each tool has a clear role. It is on the thin side of well-scoped, so slightly below the ideal 5-15 range.
The surface covers the core research workflow end to end: search, retrieve details, follow citations forward and backward, and locate open full text. Minor gaps exist around author/venue-level queries and any save/export or batch-lookup capability, which agents would have to work around with repeated searches.