search_paperLABSCO SUMMARY
Field selection is what keeps a search from filling the context window.
Ask for paperId, title, year and citationCount and a twenty-result search stays small; ask for the default record and every abstract comes with it. get_citation then formats the reference in BibTeX, APA, MLA or Chicago, which is the step people otherwise do by hand.
What it is
A Python server over the Semantic Scholar API. Four tools, each taking a fields parameter so you request only the columns you need rather than the whole record.
What you get
- Paper search filtered by year, fields of study and open-access PDF availability — search_paper
- One paper by any of its identifiers — Semantic Scholar id, DOI, arXiv id, MAG, ACL, PubMed or Corpus id — get_paper
- A paper's authors with affiliations, citation counts and h-index — get_authors
- A citation formatted as BibTeX, APA, MLA or Chicago — get_citation
- Field selection on every tool, so a search can return just paperId, title, year and citationCount instead of abstracts and reference lists
Requirements
Runs with uv straight from the repository: uv run --with git+https://github.com/FujishigeTemma/semantic-scholar-mcp semantic-scholar-mcp serve. SEMANTIC_SCHOLAR_API_KEY is optional and raises the rate limit — 100 requests per 5 minutes without one, 1 request per second with.
Setup effort
One command — claude mcp add semantic-scholar-mcp -s project -e SEMANTIC_SCHOLAR_API_KEY="<YOUR_SEMANTIC_SCHOLAR_API_KEY>" -- uv run --with "git+https://github.com/FujishigeTemma/semantic-scholar-mcp" semantic-scholar-mcp serve
USE CASES
01
Finding recent work in a field
Search with a year range and a fields-of-study filter, asking only for title, year and citation count so the results stay readable.
02
Resolving a DOI or arXiv id you were handed
Any of the supported identifier formats fetches the same record, so you do not have to convert between them first.
03
Building a bibliography
Take the paper ids you settled on and get each citation back in the format your document needs, without retyping the metadata.
04
Checking who wrote it and how cited they are
Author records come with affiliations, total citation count, h-index and paper count, so provenance is one call rather than a search.
4 tools
Listed in project docs. Your client may show a different list.
get_paperget_authorsget_citationBEFORE YOU INSTALL
What to know first
Tools you get
4 tools named in the project's documentation.
Requires
uv on PATH
Where it runs
Both documented clients run the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
claude mcp add semantic-scholar-mcp -s project -e SEMANTIC_SCHOLAR_API_KEY="<YOUR_SEMANTIC_SCHOLAR_API_KEY>" -- uv run --with "git+https://github.com/FujishigeTemma/semantic-scholar-mcp" semantic-scholar-mcp serveSEMANTIC_SCHOLAR_API_KEY is optional and only raises the rate limit. Without a key, delete -e SEMANTIC_SCHOLAR_API_KEY="<YOUR_SEMANTIC_SCHOLAR_API_KEY>" from the command before you run it.
MCP Clients
Claude Code — project scope
CLAUDE CODE — PROJECT SCOPE · TERMINAL
claude mcp add semantic-scholar-mcp -s project -e SEMANTIC_SCHOLAR_API_KEY="<YOUR_SEMANTIC_SCHOLAR_API_KEY>" -- uv run --with "git+https://github.com/FujishigeTemma/semantic-scholar-mcp" semantic-scholar-mcp serveThe key is optional and only raises the rate limit. Without one, delete the -e SEMANTIC_SCHOLAR_API_KEY="<YOUR_SEMANTIC_SCHOLAR_API_KEY>" part.
Any MCP client
ANY MCP CLIENT · JSON
{
"mcpServers": {
"semantic-scholar-mcp": {
"type": "stdio",
"command": "uv",
"args": [
"run",
"--with",
"git+https://github.com/FujishigeTemma/semantic-scholar-mcp",
"semantic-scholar-mcp",
"serve"
],
"env": {
"SEMANTIC_SCHOLAR_API_KEY": "<YOUR_SEMANTIC_SCHOLAR_API_KEY>"
}
}
}
}The key is optional and only raises the rate limit. Without one, delete the env entry.
