Skip to main content
Glama
fegizii

Semantic Scholar MCP Server

by fegizii

get_paper_references

Retrieve papers referenced by a specific academic paper using its ID, with options to limit results and select fields.

Instructions

Get papers referenced by a specific paper.

Args:
    paper_id: Paper ID to get references for
    limit: Maximum number of results (default: 10, max: 1000)
    offset: Number of results to skip (default: 0)
    fields: Comma-separated list of fields to return

Returns:
    List of referenced papers

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
paper_idYes
limitNo
offsetNo
fieldsNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Implementation Reference

  • The handler function for the 'get_paper_references' tool. It is decorated with @mcp.tool() for registration and implements the logic to fetch references for a given paper ID from the Semantic Scholar API, format them using format_paper helper, and return a formatted string.
    @mcp.tool()
    async def get_paper_references(
        paper_id: str, limit: int = 10, offset: int = 0, fields: Optional[str] = None
    ) -> str:
        """
        Get papers referenced by a specific paper.
    
        Args:
            paper_id: Paper ID to get references for
            limit: Maximum number of results (default: 10, max: 1000)
            offset: Number of results to skip (default: 0)
            fields: Comma-separated list of fields to return
    
        Returns:
            List of referenced papers
        """
        params: Dict[str, Any] = {"limit": min(limit, 1000), "offset": offset}
    
        if fields:
            params["fields"] = fields
        else:
            params["fields"] = "paperId,title,authors,year,venue,citationCount"
    
        encoded_id = quote(paper_id, safe="")
        result = await make_api_request(f"paper/{encoded_id}/references", params)
    
        if result is None:
            return "Error: Failed to fetch references"
    
        if "error" in result:
            return f"Error: {result['error']}"
    
        references = result.get("data", [])
        total = result.get("total", 0)
    
        if not references:
            return "No references found for this paper."
    
        formatted_references = []
        for i, reference in enumerate(references, 1):
            cited_paper = reference.get("citedPaper", {})
            if cited_paper:
                formatted_references.append(f"{i}. {format_paper(cited_paper)}")
    
        result_text = (
            f"Found {total} total references (showing {len(formatted_references)}):\n\n"
        )
        result_text += "\n\n".join(formatted_references)
    
        return result_text
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden but offers minimal behavioral disclosure. It mentions default values and limits (max: 1000), which is helpful, but doesn't cover important aspects like authentication requirements, rate limits, error conditions, pagination behavior beyond offset/limit, or what happens with invalid paper_id. For a read operation with zero annotation coverage, this leaves significant gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is efficiently structured with a clear purpose statement followed by organized parameter explanations and return value. Every sentence adds value: the first states the tool's function, the Args section documents all parameters, and the Returns section clarifies output. No wasted words or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's moderate complexity (4 parameters, 1 required) and the presence of an output schema (which handles return value documentation), the description is reasonably complete. It covers all parameters with semantics and mentions the return type. However, without annotations and with sibling tools present, it could better address usage context and behavioral constraints.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description adds substantial value beyond the schema, which has 0% description coverage. It explains what each parameter means: paper_id identifies the source paper, limit controls result count with defaults and maximum, offset enables skipping results, and fields controls returned data. This compensates well for the schema's lack of descriptions, though it doesn't specify field format or examples.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific action ('Get papers referenced by') and resource ('a specific paper'), distinguishing it from siblings like get_paper_citations (which likely gets papers citing this paper) or get_paper (which gets paper details). The verb 'get' combined with 'referenced by' precisely defines the tool's function.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives like get_paper_citations or get_paper_batch. It doesn't mention prerequisites (e.g., needing a valid paper_id) or contextual factors that would help an agent choose between this and sibling tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/fegizii/SemanticScholarMCP'

If you have feedback or need assistance with the MCP directory API, please join our Discord server