tooluniverse 1.0.4__py3-none-any.whl → 1.0.6__py3-none-any.whl

tooluniverse/data/pmc_tools.json

@@ -0,0 +1,109 @@
+[
+    {
+        "type": "PMCTool",
+        "name": "PMC_search_papers",
+        "description": "Search for full-text biomedical literature using PMC (PubMed Central) API. PMC is the free full-text archive of biomedical and life sciences journal literature at the U.S. National Institutes of Health's National Library of Medicine.",
+        "parameter": {
+            "type": "object",
+            "properties": {
+                "query": {
+                    "type": "string",
+                    "description": "Search query for PMC papers. Use keywords separated by spaces to refine your search."
+                },
+                "limit": {
+                    "type": "integer",
+                    "description": "Maximum number of papers to return. This sets the maximum number of papers retrieved from PMC.",
+                    "default": 10,
+                    "minimum": 1,
+                    "maximum": 100
+                },
+                "date_from": {
+                    "type": "string",
+                    "description": "Start date for publication date filter (YYYY/MM/DD format). Optional parameter to limit search to papers published from this date onwards."
+                },
+                "date_to": {
+                    "type": "string",
+                    "description": "End date for publication date filter (YYYY/MM/DD format). Optional parameter to limit search to papers published up to this date."
+                },
+                "article_type": {
+                    "type": "string",
+                    "description": "Article type filter (e.g., 'research-article', 'review', 'case-report'). Optional parameter to limit search to specific article types."
+                }
+            },
+            "required": ["query"]
+        },
+        "return_schema": {
+            "type": "array",
+            "description": "List of full-text biomedical papers from PMC matching the search query",
+            "items": {
+                "type": "object",
+                "properties": {
+                    "title": {
+                        "type": "string",
+                        "description": "Title of the paper"
+                    },
+                    "abstract": {
+                        "type": "string",
+                        "description": "Abstract of the paper"
+                    },
+                    "authors": {
+                        "type": "array",
+                        "items": {"type": "string"},
+                        "description": "List of author names"
+                    },
+                    "year": {
+                        "type": "string",
+                        "description": "Publication year"
+                    },
+                    "pmc_id": {
+                        "type": "string",
+                        "description": "PMC identifier"
+                    },
+                    "pmid": {
+                        "type": "string",
+                        "description": "PubMed identifier"
+                    },
+                    "doi": {
+                        "type": "string",
+                        "description": "Digital Object Identifier (DOI) of the paper"
+                    },
+                    "url": {
+                        "type": "string",
+                        "description": "URL to access the paper on PMC"
+                    },
+                    "venue": {
+                        "type": "string",
+                        "description": "Journal or venue name"
+                    },
+                    "open_access": {
+                        "type": "boolean",
+                        "description": "Open access status (always true for PMC)"
+                    },
+                    "source": {
+                        "type": "string",
+                        "description": "Source identifier (always 'PMC')"
+                    },
+                    "article_type": {
+                        "type": "string",
+                        "description": "Type of article (e.g., research-article, review)"
+                    },
+                    "citations": {
+                        "type": "integer",
+                        "description": "Number of citations"
+                    }
+                }
+            }
+        },
+        "test_examples": [
+            {
+                "query": "cancer research",
+                "limit": 2
+            },
+            {
+                "query": "COVID-19",
+                "limit": 1,
+                "date_from": "2020/01/01"
+            }
+        ]
+    }
+]

tooluniverse/data/pubmed_tools.json

@@ -0,0 +1,65 @@
+[
+    {
+        "type": "PubMedTool",
+        "name": "PubMed_search_articles",
+        "description": "Search PubMed using NCBI E-utilities (esearch + esummary) and return articles. Returns articles with title, journal, year, DOI, and PubMed URL.",
+        "parameter": {
+            "type": "object",
+            "properties": {
+                "query": {
+                    "type": "string",
+                    "description": "Search query for PubMed articles. Use keywords separated by spaces to refine your search."
+                },
+                "limit": {
+                    "type": "integer",
+                    "description": "Number of articles to return. This sets the maximum number of articles retrieved from PubMed.",
+                    "default": 10
+                },
+                "api_key": {
+                    "type": "string",
+                    "description": "Optional NCBI API key for higher rate limits. Get your free key at https://www.ncbi.nlm.nih.gov/account/"
+                }
+            },
+            "required": ["query"]
+        },
+        "return_schema": {
+            "type": "array",
+            "description": "List of PubMed articles matching the search query",
+            "items": {
+                "type": "object",
+                "properties": {
+                    "title": {
+                        "type": "string",
+                        "description": "Title of the article"
+                    },
+                    "journal": {
+                        "type": "string",
+                        "description": "Journal name where the article was published"
+                    },
+                    "year": {
+                        "type": "integer",
+                        "description": "Publication year"
+                    },
+                    "doi": {
+                        "type": "string",
+                        "description": "Digital Object Identifier (if available)"
+                    },
+                    "url": {
+                        "type": "string",
+                        "description": "URL to the article on PubMed"
+                    }
+                }
+            }
+        },
+        "test_examples": [
+            {
+                "query": "cancer research",
+                "limit": 2
+            },
+            {
+                "query": "COVID-19",
+                "limit": 1
+            }
+        ]
+    }
+]

tooluniverse/data/unpaywall_tools.json

@@ -0,0 +1,86 @@
+[
+    {
+        "type": "UnpaywallTool",
+        "name": "Unpaywall_check_oa_status",
+        "description": "Query Unpaywall by DOI to check open-access status and OA locations. Requires a contact email for API access.",
+        "parameter": {
+            "type": "object",
+            "properties": {
+                "doi": {
+                    "type": "string",
+                    "description": "DOI (Digital Object Identifier) of the article to check for open access status."
+                },
+                "email": {
+                    "type": "string",
+                    "description": "Contact email address required by Unpaywall API for polite usage tracking."
+                }
+            },
+            "required": ["doi", "email"]
+        },
+        "return_schema": {
+            "type": "object",
+            "description": "Open access status and location information for the given DOI",
+            "properties": {
+                "is_oa": {
+                    "type": "boolean",
+                    "description": "Whether the article is open access"
+                },
+                "oa_status": {
+                    "type": "string",
+                    "description": "Open access status (e.g., 'gold', 'green', 'hybrid', 'closed')"
+                },
+                "best_oa_location": {
+                    "type": "object",
+                    "description": "Best available open access location"
+                },
+                "oa_locations": {
+                    "type": "array",
+                    "description": "All available open access locations"
+                },
+                "journal_is_oa": {
+                    "type": "boolean",
+                    "description": "Whether the journal is open access"
+                },
+                "journal_issn_l": {
+                    "type": "string",
+                    "description": "Journal ISSN-L"
+                },
+                "journal_issns": {
+                    "type": "array",
+                    "items": {"type": "string"},
+                    "description": "Journal ISSNs"
+                },
+                "doi": {
+                    "type": "string",
+                    "description": "The DOI that was queried"
+                },
+                "title": {
+                    "type": "string",
+                    "description": "Article title"
+                },
+                "year": {
+                    "type": "integer",
+                    "description": "Publication year"
+                },
+                "publisher": {
+                    "type": "string",
+                    "description": "Publisher name"
+                },
+                "url": {
+                    "type": "string",
+                    "description": "URL to the article"
+                }
+            }
+        },
+        "test_examples": [
+            {
+                "doi": "10.1038/nature12373",
+                "email": "test@example.com"
+            },
+            {
+                "doi": "10.1126/science.1234567",
+                "email": "user@example.com"
+            }
+        ]
+    }
+]

tooluniverse/data/wikidata_sparql_tools.json

@@ -0,0 +1,42 @@
+[
+    {
+        "type": "WikidataSPARQLTool",
+        "name": "Wikidata_SPARQL_query",
+        "description": "Execute SPARQL queries against Wikidata to retrieve structured data. This tool powers Scholia-style visualizations and can query academic topics, authors, institutions, and research relationships.",
+        "parameter": {
+            "type": "object",
+            "properties": {
+                "sparql": {
+                    "type": "string",
+                    "description": "SPARQL query string to execute against Wikidata. Use SPARQL syntax to query academic entities, relationships, and properties."
+                },
+                "max_results": {
+                    "type": "integer",
+                    "description": "Optional result limit override. If not specified, uses the LIMIT clause in the SPARQL query or returns all results.",
+                    "minimum": 1
+                }
+            },
+            "required": ["sparql"]
+        },
+        "return_schema": {
+            "type": "array",
+            "description": "List of query results from Wikidata SPARQL endpoint",
+            "items": {
+                "type": "object",
+                "description": "Each result is a dictionary with variable names as keys and their values from the SPARQL query results"
+            }
+        },
+        "test_examples": [
+            {
+                "sparql": "SELECT ?item ?itemLabel WHERE { ?item wdt:P31 wd:Q11424 . ?item rdfs:label ?itemLabel . FILTER(LANG(?itemLabel) = 'en') } LIMIT 5",
+                "max_results": 5
+            },
+            {
+                "sparql": "SELECT ?author ?authorLabel WHERE { ?author wdt:P31 wd:Q5 . ?author wdt:P106 wd:Q188094 . ?author rdfs:label ?authorLabel . FILTER(LANG(?authorLabel) = 'en') } LIMIT 3"
+            },
+            {
+                "sparql": "SELECT ?university ?universityLabel WHERE { ?university wdt:P31 wd:Q3918 . ?university rdfs:label ?universityLabel . FILTER(LANG(?universityLabel) = 'en') } LIMIT 3"
+            }
+        ]
+    }
+]

tooluniverse/data/zenodo_tools.json

@@ -0,0 +1,82 @@
+[
+    {
+        "type": "ZenodoTool",
+        "name": "Zenodo_search_records",
+        "description": "Search Zenodo for research data, publications, and datasets. Zenodo is an open-access repository that hosts research outputs from all fields of science, including papers, datasets, software, and more.",
+        "parameter": {
+            "type": "object",
+            "properties": {
+                "query": {
+                    "type": "string",
+                    "description": "Free text search query for Zenodo records. Use keywords to search across titles, descriptions, authors, and other metadata."
+                },
+                "max_results": {
+                    "type": "integer",
+                    "description": "Maximum number of results to return. Must be between 1 and 200.",
+                    "default": 10,
+                    "minimum": 1,
+                    "maximum": 200
+                },
+                "community": {
+                    "type": "string",
+                    "description": "Optional community slug to filter results by specific research community (e.g., 'zenodo', 'ecfunded')."
+                }
+            },
+            "required": ["query"]
+        },
+        "return_schema": {
+            "type": "array",
+            "description": "List of Zenodo records matching the search query",
+            "items": {
+                "type": "object",
+                "properties": {
+                    "title": {
+                        "type": "string",
+                        "description": "Title of the record"
+                    },
+                    "authors": {
+                        "type": "array",
+                        "items": {"type": "string"},
+                        "description": "List of author/creator names"
+                    },
+                    "date": {
+                        "type": "string",
+                        "description": "Publication date"
+                    },
+                    "doi": {
+                        "type": "string",
+                        "description": "Digital Object Identifier (DOI)"
+                    },
+                    "url": {
+                        "type": "string",
+                        "description": "URL to the record on Zenodo"
+                    },
+                    "files": {
+                        "type": ["array", "string"],
+                        "description": "List of files or link to files associated with the record"
+                    },
+                    "source": {
+                        "type": "string",
+                        "description": "Source identifier (always 'Zenodo')"
+                    }
+                }
+            }
+        },
+        "test_examples": [
+            {
+                "query": "machine learning",
+                "max_results": 2
+            },
+            {
+                "query": "COVID-19",
+                "max_results": 1
+            },
+            {
+                "query": "climate change",
+                "max_results": 3,
+                "community": "zenodo"
+            }
+        ]
+    }
+]
+

tooluniverse/dblp_tool.py

@@ -0,0 +1,62 @@
+import requests
+from .base_tool import BaseTool
+from .tool_registry import register_tool
+
+
+@register_tool("DBLPTool")
+class DBLPTool(BaseTool):
+    """
+    Search DBLP Computer Science Bibliography for publications.
+    """
+
+    def __init__(
+        self,
+        tool_config,
+        base_url="https://dblp.org/search/publ/api",
+    ):
+        super().__init__(tool_config)
+        self.base_url = base_url
+
+    def run(self, arguments):
+        query = arguments.get("query")
+        limit = int(arguments.get("limit", 10))
+        if not query:
+            return {"error": "`query` parameter is required."}
+        return self._search(query, limit)
+
+    def _search(self, query, limit):
+        params = {
+            "q": query,
+            "h": max(1, min(limit, 100)),
+            "format": "json",
+        }
+        try:
+            response = requests.get(self.base_url, params=params, timeout=20)
+        except requests.RequestException as e:
+            return {
+                "error": "Network error calling DBLP API",
+                "reason": str(e),
+            }
+
+        if response.status_code != 200:
+            return {
+                "error": f"DBLP API error {response.status_code}",
+                "reason": response.reason,
+            }
+
+        hits = response.json().get("result", {}).get("hits", {}).get("hit", [])
+        results = []
+        for hit in hits:
+            info = hit.get("info", {})
+            results.append(
+                {
+                    "title": info.get("title"),
+                    "authors": info.get("authors", {}).get("author"),
+                    "year": info.get("year"),
+                    "venue": info.get("venue"),
+                    "url": info.get("url"),
+                    "ee": info.get("ee"),
+                }
+            )
+
+        return results

tooluniverse/default_config.py

@@ -33,6 +33,23 @@ default_tool_files = {
     "Enrichr": os.path.join(current_dir, "data", "enrichr_tools.json"),
     "HumanBase": os.path.join(current_dir, "data", "humanbase_tools.json"),
     "OpenAlex": os.path.join(current_dir, "data", "openalex_tools.json"),
+    # Literature search tools
+    "arxiv": os.path.join(current_dir, "data", "arxiv_tools.json"),
+    "crossref": os.path.join(current_dir, "data", "crossref_tools.json"),
+    "dblp": os.path.join(current_dir, "data", "dblp_tools.json"),
+    "pubmed": os.path.join(current_dir, "data", "pubmed_tools.json"),
+    "doaj": os.path.join(current_dir, "data", "doaj_tools.json"),
+    "unpaywall": os.path.join(current_dir, "data", "unpaywall_tools.json"),
+    "biorxiv": os.path.join(current_dir, "data", "biorxiv_tools.json"),
+    "medrxiv": os.path.join(current_dir, "data", "medrxiv_tools.json"),
+    "hal": os.path.join(current_dir, "data", "hal_tools.json"),
+    "core": os.path.join(current_dir, "data", "core_tools.json"),
+    "pmc": os.path.join(current_dir, "data", "pmc_tools.json"),
+    "zenodo": os.path.join(current_dir, "data", "zenodo_tools.json"),
+    "openaire": os.path.join(current_dir, "data", "openaire_tools.json"),
+    "osf_preprints": os.path.join(current_dir, "data", "osf_preprints_tools.json"),
+    "fatcat": os.path.join(current_dir, "data", "fatcat_tools.json"),
+    "wikidata_sparql": os.path.join(current_dir, "data", "wikidata_sparql_tools.json"),
     "agents": os.path.join(current_dir, "data", "agentic_tools.json"),
     "dataset": os.path.join(current_dir, "data", "dataset_tools.json"),
     # 'mcp_clients': os.path.join(current_dir, 'data', 'mcp_client_tools_example.json'),
@@ -113,6 +130,7 @@ default_tool_files = {
     "output_summarization": os.path.join(
         current_dir, "data", "output_summarization_tools.json"
     ),
+    "odphp": os.path.join(current_dir, "data", "odphp_tools.json"),
 }
 
 

tooluniverse/doaj_tool.py

@@ -0,0 +1,124 @@
+import requests
+from .base_tool import BaseTool
+from .tool_registry import register_tool
+
+
+@register_tool("DOAJTool")
+class DOAJTool(BaseTool):
+    """
+    Search DOAJ (Directory of Open Access Journals) articles and journals.
+
+    Parameters (arguments):
+        query (str): Query string (Lucene syntax supported by DOAJ)
+        max_results (int): Max number of results (default 10, max 100)
+        type (str): "articles" or "journals" (default: "articles")
+    """
+
+    def __init__(self, tool_config):
+        super().__init__(tool_config)
+        self.base_url = "https://doaj.org/api/search"
+
+    def run(self, arguments=None):
+        arguments = arguments or {}
+        query = arguments.get("query")
+        search_type = arguments.get("type", "articles")
+        max_results = int(arguments.get("max_results", 10))
+
+        if not query:
+            return {"error": "`query` parameter is required."}
+
+        if search_type not in ["articles", "journals"]:
+            return {"error": "`type` must be 'articles' or 'journals'."}
+
+        endpoint = f"{self.base_url}/{search_type}/{query}"
+        params = {
+            "pageSize": max(1, min(max_results, 100)),
+        }
+        try:
+            resp = requests.get(endpoint, params=params, timeout=20)
+            resp.raise_for_status()
+            data = resp.json()
+        except requests.RequestException as e:
+            return {
+                "error": "Network/API error calling DOAJ",
+                "reason": str(e),
+            }
+        except ValueError:
+            return {"error": "Failed to decode DOAJ response as JSON"}
+
+        results = data.get("results", [])
+        items = []
+        if search_type == "articles":
+            for r in results:
+                b = r.get("bibjson", {})
+                title = b.get("title")
+                year = None
+                try:
+                    year = int((b.get("year") or 0))
+                except Exception:
+                    year = b.get("year")
+                authors = [
+                    a.get("name")
+                    for a in b.get("author", [])
+                    if a.get("name")
+                ]
+                doi = None
+                for i in b.get("identifier", []):
+                    if i.get("type") == "doi":
+                        doi = i.get("id")
+                        break
+                url = None
+                for link_item in b.get("link", []):
+                    if (
+                        link_item.get("type") == "fulltext"
+                        or link_item.get("url")
+                    ):
+                        url = link_item.get("url")
+                        break
+                journal = (b.get("journal") or {}).get("title")
+                items.append(
+                    {
+                        "title": title,
+                        "authors": authors,
+                        "year": year,
+                        "doi": doi,
+                        "venue": journal,
+                        "url": url,
+                        "source": "DOAJ",
+                    }
+                )
+        else:
+            for r in results:
+                b = r.get("bibjson", {})
+                title = b.get("title")
+                publisher = b.get("publisher")
+                eissn = None
+                pissn = None
+                for i in b.get("identifier", []):
+                    if i.get("type") == "eissn":
+                        eissn = i.get("id")
+                    if i.get("type") == "pissn":
+                        pissn = i.get("id")
+                homepage_url = None
+                for link_item in b.get("link", []):
+                    if link_item.get("url"):
+                        homepage_url = link_item.get("url")
+                        break
+                subjects = [
+                    s.get("term")
+                    for s in b.get("subject", [])
+                    if s.get("term")
+                ]
+                items.append(
+                    {
+                        "title": title,
+                        "publisher": publisher,
+                        "eissn": eissn,
+                        "pissn": pissn,
+                        "subjects": subjects,
+                        "url": homepage_url,
+                        "source": "DOAJ",
+                    }
+                )
+
+        return items