mcp-scholaris
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SEMANTIC_SCHOLAR_API_KEY | No | Optional API key for higher rate limits on Semantic Scholar. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_papersA | Search for academic papers across arXiv, Semantic Scholar, and PubMed. Returns titles, authors, abstracts, DOIs, and links. Use this to find papers by topic, author, or keyword. |
| fetch_paperA | Fetch the full text of a paper given a DOI, arXiv ID, or PubMed ID. Tries open access sources in order: arXiv, PubMed Central, Unpaywall. Returns extracted text from the PDF. |
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 2 tools
The two tools have clearly separate roles: search_papers is for discovery, returning metadata about papers, while fetch_paper retrieves full text for a known identifier. There is no overlap in purpose or output.
Both tool names follow a consistent verb_noun snake_case pattern: search_papers and fetch_paper. The naming clearly communicates what each tool does and matches the same style.
With only two tools, the server is on the small side, but the two operations form a natural and sufficient pair for a focused scholarly search-and-retrieval tool. Each tool is essential and earns its place.
For the stated purpose of finding academic papers and retrieving their full text, the pipeline is complete: search returns identifiers and metadata, and fetch consumes those identifiers to return content. No obvious dead ends or missing core operations exist in this read-only domain.