search_zenodo
Search academic papers from Zenodo open repository using query terms to find relevant research publications.
Instructions
Search academic papers from Zenodo open repository.
Args: query: Search query string (e.g., 'machine learning'). max_results: Maximum number of papers to return (default: 10). Returns: List of paper metadata in dictionary format.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | ||
| max_results | No |
Output Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Implementation Reference
- paper_search_mcp/server.py:989-999 (handler)The `search_zenodo` tool implementation, which serves as the MCP tool handler and orchestrates the search using the `ZenodoSearcher` class.
async def search_zenodo(query: str, max_results: int = 10) -> List[Dict]: """Search academic papers from Zenodo open repository. Args: query: Search query string (e.g., 'machine learning'). max_results: Maximum number of papers to return (default: 10). Returns: List of paper metadata in dictionary format. """ papers = await async_search(zenodo_searcher, query, max_results) return papers if papers else [] - The `ZenodoSearcher.search` method, which interacts with the Zenodo public REST API to perform the search operation.
def search(self, query: str, max_results: int = 10, **kwargs) -> List[Paper]: """Search Zenodo records. Args: query: Free-text or Elasticsearch query string. max_results: Maximum number of results (1–200; Zenodo page limit is 10k). **kwargs: Extra filters: - ``type``: Record type, e.g. ``"publication"`` (default), ``"dataset"``, ``"image"``, ``"video"``, ``"software"``, ``"poster"``, etc. - ``subtype``: Publication subtype, e.g. ``"article"``, ``"preprint"``. - ``year``: Filter by publication year (e.g. ``2023``). - ``access_right``: ``"open"``, ``"embargoed"``, ``"restricted"``, ``"closed"``. Returns: List of :class:`~paper_search_mcp.paper.Paper` objects. """ max_results = max(1, min(max_results, 200)) params: Dict[str, Any] = { "q": query, "size": max_results, "sort": "mostrecent", } record_type = kwargs.get("type", "publication") if record_type: params["type"] = record_type subtype = kwargs.get("subtype", "") if subtype: params["subtype"] = subtype access_right = kwargs.get("access_right", "") if access_right: params["access_right"] = access_right year = kwargs.get("year") if year: params["q"] = f"{query} AND publication_date:[{year}-01-01 TO {year}-12-31]" try: response = self.session.get( f"{self.BASE_URL}/records", params=params, timeout=20 ) response.raise_for_status() data = response.json() except Exception as exc: logger.error("Zenodo search failed: %s", exc) return [] papers: List[Paper] = [] for hit in data.get("hits", {}).get("hits", []): paper = self._parse_record(hit) if paper: papers.append(paper) return papers - paper_search_mcp/server.py:309-309 (registration)Registration of the Zenodo search functionality within the task mapping in the server.
task_map[source] = search_zenodo(query, max_results_per_source)