semantic_scholar_get_paper

Retrieve academic paper details using identifiers like DOI, arXiv ID, or S2 ID, with options to include citations and references for comprehensive research analysis.

Instructions

Get paper details. Accepts: S2 ID, DOI:xxx, ARXIV:xxx, PMID:xxx, CorpusId:xxx

Input Schema

TableJSON Schema

Name	Required	Description	Default
`params`	Yes

Implementation Reference

src/semantic_scholar_mcp/server.py:299-328 (handler)

The main handler function `get_paper_details` for the `semantic_scholar_get_paper` tool. It fetches paper details from the Semantic Scholar API, optionally including citations and references, and formats the output in Markdown or JSON.

@mcp.tool(name="semantic_scholar_get_paper")
async def get_paper_details(params: PaperDetailsInput) -> str:
    """Get paper details. Accepts: S2 ID, DOI:xxx, ARXIV:xxx, PMID:xxx, CorpusId:xxx"""
    logger.info(f"Getting paper: {params.paper_id}")
    
    paper = await _make_request("GET", f"paper/{params.paper_id}", params={"fields": ",".join(PAPER_FIELDS)})
    result = {"paper": paper}
    
    if params.include_citations:
        cit = await _make_request("GET", f"paper/{params.paper_id}/citations", params={"fields": ",".join(PAPER_FIELDS), "limit": params.citations_limit})
        result["citations"] = cit.get("data", [])
    if params.include_references:
        ref = await _make_request("GET", f"paper/{params.paper_id}/references", params={"fields": ",".join(PAPER_FIELDS), "limit": params.references_limit})
        result["references"] = ref.get("data", [])
    
    if params.response_format == ResponseFormat.JSON:
        return json.dumps(result, indent=2)
    
    lines = ["## Paper Details", "", _format_paper_markdown(paper)]
    if result.get("citations"):
        lines.extend(["---", f"### Citing Papers ({len(result['citations'])} shown)", ""])
        for c in result["citations"]:
            p = c.get("citingPaper", {})
            if p: lines.append(f"- **{p.get('title', '?')}** ({p.get('year', '')}) - {p.get('citationCount', 0)} citations")
    if result.get("references"):
        lines.extend(["---", f"### References ({len(result['references'])} shown)", ""])
        for r in result["references"]:
            p = r.get("citedPaper", {})
            if p: lines.append(f"- **{p.get('title', '?')}** ({p.get('year', '')}) - {p.get('citationCount', 0)} citations")
    return "\n".join(lines)

src/semantic_scholar_mcp/server.py:113-121 (schema)

Pydantic input schema `PaperDetailsInput` used by the tool handler for input validation and type hints.

class PaperDetailsInput(BaseModel):
    model_config = ConfigDict(str_strip_whitespace=True, extra="forbid")
    paper_id: str = Field(..., description="Paper ID: S2 ID, DOI:xxx, ARXIV:xxx, PMID:xxx, CorpusId:xxx", min_length=1)
    include_citations: bool = Field(default=False, description="Include citing papers")
    include_references: bool = Field(default=False, description="Include referenced papers")
    citations_limit: int = Field(default=10, description="Max citations to return", ge=1, le=100)
    references_limit: int = Field(default=10, description="Max references to return", ge=1, le=100)
    response_format: ResponseFormat = Field(default=ResponseFormat.MARKDOWN, description="Output format")

src/semantic_scholar_mcp/server.py:299-299 (registration)
The `@mcp.tool` decorator registers the `get_paper_details` function as the 'semantic_scholar_get_paper' tool with FastMCP.
```
@mcp.tool(name="semantic_scholar_get_paper")
```

Semantic Scholar MCP Server