Skip to main content
Glama
openags

Paper Search MCP

by openags

search_papers

Search academic papers across multiple platforms simultaneously to find research publications. This tool aggregates results from sources like arXiv, PubMed, and Google Scholar in a single query.

Instructions

Unified top-level search across all configured academic platforms.

Args: query: Search query string. max_results_per_source: Max results to fetch from each selected source. sources: Comma-separated source names or 'all'. Available: arxiv,pubmed,biorxiv,medrxiv,google_scholar,iacr,semantic,crossref,openalex,pmc,core,europepmc,dblp,openaire,citeseerx,doaj,base,zenodo,hal,ssrn,unpaywall year: Optional year filter for Semantic Scholar only. Returns: Aggregated dictionary with per-source stats, errors, and deduplicated papers.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYes
max_results_per_sourceNo
sourcesNoall
yearNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Implementation Reference

  • The 'search_papers' tool handler, which orchestrates searches across various academic platforms based on the user-provided 'sources' parameter.
    async def search_papers(
        query: str,
        max_results_per_source: int = 5,
        sources: str = "all",
        year: Optional[str] = None,
    ) -> Dict[str, Any]:
        """Unified top-level search across all configured academic platforms.
    
        Args:
            query: Search query string.
            max_results_per_source: Max results to fetch from each selected source.
            sources: Comma-separated source names or 'all'.
                Available: arxiv,pubmed,biorxiv,medrxiv,google_scholar,iacr,semantic,crossref,openalex,pmc,core,europepmc,dblp,openaire,citeseerx,doaj,base,zenodo,hal,ssrn,unpaywall
            year: Optional year filter for Semantic Scholar only.
        Returns:
            Aggregated dictionary with per-source stats, errors, and deduplicated papers.
        """
        selected_sources = _parse_sources(sources)
    
        if not selected_sources:
            return {
                "query": query,
                "sources_requested": sources,
                "sources_used": [],
                "source_results": {},
                "errors": {"sources": "No valid sources selected."},
                "papers": [],
                "total": 0,
            }
    
        task_map = {}
        for source in selected_sources:
            if source == "arxiv":
                task_map[source] = search_arxiv(query, max_results_per_source)
            elif source == "pubmed":
                task_map[source] = search_pubmed(query, max_results_per_source)
            elif source == "biorxiv":
                task_map[source] = search_biorxiv(query, max_results_per_source)
            elif source == "medrxiv":
                task_map[source] = search_medrxiv(query, max_results_per_source)
            elif source == "google_scholar":
                task_map[source] = search_google_scholar(query, max_results_per_source)
            elif source == "iacr":
                task_map[source] = search_iacr(query, max_results_per_source, fetch_details=False)
            elif source == "semantic":
                task_map[source] = search_semantic(query, year=year, max_results=max_results_per_source)
            elif source == "crossref":
                task_map[source] = search_crossref(query, max_results=max_results_per_source)
            elif source == "openalex":
                task_map[source] = search_openalex(query, max_results_per_source)
            elif source == "pmc":
                task_map[source] = search_pmc(query, max_results_per_source)
            elif source == "core":
                task_map[source] = search_core(query, max_results_per_source)
            elif source == "europepmc":
                task_map[source] = search_europepmc(query, max_results_per_source)
            elif source == "dblp":
                task_map[source] = search_dblp(query, max_results_per_source)
            elif source == "openaire":
                task_map[source] = search_openaire(query, max_results_per_source)
            elif source == "citeseerx":
                task_map[source] = search_citeseerx(query, max_results_per_source)
            elif source == "doaj":
                task_map[source] = search_doaj(query, max_results_per_source)
            elif source == "base":
                task_map[source] = search_base(query, max_results_per_source)
            elif source == "zenodo":
                task_map[source] = search_zenodo(query, max_results_per_source)
            elif source == "hal":
                task_map[source] = search_hal(query, max_results_per_source)
            elif source == "ssrn":
                task_map[source] = search_ssrn(query, max_results_per_source)
            elif source == "unpaywall":
                task_map[source] = search_unpaywall(query, max_results_per_source)
            elif source == "ieee":
                if ieee_searcher is not None:
                    task_map[source] = async_search(ieee_searcher, query, max_results_per_source)
            elif source == "acm":
                if acm_searcher is not None:
                    task_map[source] = async_search(acm_searcher, query, max_results_per_source)
    
        source_names = list(task_map.keys())
        source_outputs = await asyncio.gather(*task_map.values(), return_exceptions=True)
Behavior3/5

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

With no annotations provided, the description carries the full burden. It discloses that the tool aggregates results, provides per-source stats and errors, and deduplicates papers, which are valuable behavioral details. However, it doesn't mention rate limits, authentication needs, timeout behavior, or what happens when sources fail, leaving some gaps in behavioral understanding.

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 well-organized sections for Args and Returns. Every sentence earns its place by providing essential information without redundancy. The formatting with bullet-like sections makes it easy to parse while remaining concise.

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 complexity (4 parameters, 0% schema coverage, no annotations, but with output schema), the description is quite complete. It explains all parameters thoroughly and describes the return structure. The only minor gap is that with an output schema present, the return description is somewhat redundant, but it still adds useful semantic context about aggregation and deduplication.

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

Parameters5/5

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

With 0% schema description coverage, the description fully compensates by providing detailed parameter explanations. It clarifies that 'sources' accepts comma-separated names or 'all', lists all 21 available sources, explains that 'year' only works for Semantic Scholar, and describes defaults and formats for all parameters, adding significant value beyond the bare schema.

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 tool's purpose: 'Unified top-level search across all configured academic platforms.' It specifies the verb ('search') and resource ('papers'), and distinguishes itself from sibling tools by emphasizing its unified nature across multiple sources rather than searching individual platforms like the many 'search_*' siblings.

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

Usage Guidelines4/5

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

The description implies when to use this tool through its 'unified top-level search' phrasing, suggesting it's for broad searches across multiple sources. However, it doesn't explicitly state when NOT to use it or name specific alternatives among the many sibling search tools, though the context makes clear this is for aggregated searching versus single-source searches.

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/openags/paper-search-mcp'

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