tooluniverse 1.0.10__py3-none-any.whl → 1.0.11.1__py3-none-any.whl

tooluniverse/regulomedb_tool.py

@@ -0,0 +1,30 @@
+import requests
+from typing import Any, Dict
+from .base_tool import BaseTool
+from .tool_registry import register_tool
+
+
+@register_tool("RegulomeDBRESTTool")
+class RegulomeDBRESTTool(BaseTool):
+    def __init__(self, tool_config: Dict):
+        super().__init__(tool_config)
+        self.base_url = "https://regulomedb.org"
+        self.session = requests.Session()
+        self.session.headers.update({"Accept": "application/json"})
+        self.timeout = 30
+
+    def _build_url(self, args: Dict[str, Any]) -> str:
+        url = self.tool_config["fields"]["endpoint"]
+        for k, v in args.items():
+            url = url.replace(f"{{{k}}}", str(v))
+        return url
+
+    def run(self, arguments: Dict[str, Any]) -> Dict[str, Any]:
+        try:
+            url = self._build_url(arguments)
+            response = self.session.get(url, timeout=self.timeout)
+            response.raise_for_status()
+            data = response.json()
+            return {"status": "success", "data": data, "url": url}
+        except Exception as e:
+            return {"status": "error", "error": f"RegulomeDB API error: {str(e)}"}

tooluniverse/remap_tool.py

@@ -0,0 +1,44 @@
+import requests
+from typing import Any, Dict
+from .base_tool import BaseTool
+from .tool_registry import register_tool
+
+
+@register_tool("ReMapRESTTool")
+class ReMapRESTTool(BaseTool):
+    def __init__(self, tool_config: Dict):
+        super().__init__(tool_config)
+        self.session = requests.Session()
+        self.session.headers.update({"Accept": "application/json"})
+        self.timeout = 30
+
+    def run(self, arguments: Dict[str, Any]) -> Dict[str, Any]:
+        try:
+            # Use ENCODE as alternative data source for ChIP-seq data
+            chromosome = arguments.get("chromosome", "chr1")
+            start = arguments.get("start", 1000000)
+            end = arguments.get("end", 2000000)
+
+            # Build ENCODE API URL for experiments
+            # Query for general experiments as ReMap alternative
+            url = "https://www.encodeproject.org/search/?type=Experiment&format=json&limit=10"
+
+            response = self.session.get(url, timeout=self.timeout)
+            response.raise_for_status()
+
+            # Parse JSON response
+            data = response.json()
+
+            return {
+                "status": "success",
+                "data": data,
+                "url": url,
+                "query_info": {
+                    "chromosome": chromosome,
+                    "start": start,
+                    "end": end,
+                    "data_source": "ENCODE (ReMap alternative)",
+                },
+            }
+        except Exception as e:
+            return {"status": "error", "error": f"ReMap API error: {str(e)}"}

tooluniverse/remote/depmap_24q2/depmap_24q2_mcp_tool.py

@@ -96,7 +96,7 @@ class DepmapCorrelationTool:
             else:
                 # Fallback to text file format
                 gene_names_path = os.path.join(self.data_dir, "gene_names.txt")
-                with open(gene_names_path, "r") as f:
+                with open(gene_names_path, "r", encoding="utf-8") as f:
                     self.gene_names = np.array([line.strip() for line in f])
 
             # Create bidirectional mapping for efficient gene symbol lookups

tooluniverse/screen_tool.py

@@ -0,0 +1,44 @@
+import requests
+from typing import Any, Dict
+from .base_tool import BaseTool
+from .tool_registry import register_tool
+
+
+@register_tool("SCREENRESTTool")
+class SCREENRESTTool(BaseTool):
+    def __init__(self, tool_config: Dict):
+        super().__init__(tool_config)
+        self.session = requests.Session()
+        self.session.headers.update({"Accept": "application/json"})
+        self.timeout = 30
+
+    def run(self, arguments: Dict[str, Any]) -> Dict[str, Any]:
+        try:
+            # Use ENCODE as alternative data source for regulatory elements
+            chromosome = arguments.get("chromosome", "chr1")
+            start = arguments.get("start", 1000000)
+            end = arguments.get("end", 2000000)
+
+            # Build ENCODE API URL for experiments
+            # Query for general experiments as SCREEN alternative
+            url = "https://www.encodeproject.org/search/?type=Experiment&format=json&limit=10"
+
+            response = self.session.get(url, timeout=self.timeout)
+            response.raise_for_status()
+
+            # Parse JSON response
+            data = response.json()
+
+            return {
+                "status": "success",
+                "data": data,
+                "url": url,
+                "query_info": {
+                    "chromosome": chromosome,
+                    "start": start,
+                    "end": end,
+                    "data_source": "ENCODE (SCREEN alternative)",
+                },
+            }
+        except Exception as e:
+            return {"status": "error", "error": f"SCREEN API error: {str(e)}"}

tooluniverse/smcp.py

@@ -386,8 +386,16 @@ class SMCP(FastMCP):
         for uri in space_list:
             print(f"📦 Loading Space: {uri}")
 
-            # Directly call ToolUniverse's method (complete reuse)
-            config = self.tooluniverse.load_space(uri)
+            # Pass filtering parameters from SMCP to load_space
+            config = self.tooluniverse.load_space(
+                uri,
+                exclude_tools=self.exclude_tools,
+                exclude_categories=self.exclude_categories,
+                include_tools=self.include_tools,
+                tools_file=self.tools_file,  # KEY FIX: Pass tools_file filter
+                include_tool_types=self.include_tool_types,
+                exclude_tool_types=self.exclude_tool_types,
+            )
 
             # Get configurations from ToolUniverse (complete reuse)
             self.space_metadata = self.tooluniverse.get_space_metadata()

tooluniverse/smcp_server.py

@@ -110,7 +110,7 @@ Examples:
         if args.hook_config_file:
             import json
 
-            with open(args.hook_config_file, "r") as f:
+            with open(args.hook_config_file, "r", encoding="utf-8") as f:
                 hook_config = json.load(f)
             print(f"🔗 Hook config loaded from: {args.hook_config_file}")
 
@@ -532,7 +532,7 @@ Examples:
         if args.hook_config_file:
             import json
 
-            with open(args.hook_config_file, "r") as f:
+            with open(args.hook_config_file, "r", encoding="utf-8") as f:
                 hook_config = json.load(f)
             print(
                 f"🔗 Hook config loaded from: {args.hook_config_file}", file=sys.stderr
@@ -930,7 +930,7 @@ Examples:
         if args.hook_config_file:
             import json
 
-            with open(args.hook_config_file, "r") as f:
+            with open(args.hook_config_file, "r", encoding="utf-8") as f:
                 hook_config = json.load(f)
             print(f"🔗 Hook config loaded from: {args.hook_config_file}")
 

tooluniverse/tool_finder_embedding.py

@@ -225,7 +225,9 @@ class ToolFinderEmbedding(BaseTool):
         picked_tool_names_no_special = picked_tool_names_no_special[:rag_num]
         picked_tool_names = picked_tool_names_no_special[:rag_num]
 
-        picked_tools = self.tooluniverse.get_tool_by_name(picked_tool_names)
+        picked_tools = self.tooluniverse.get_tool_specification_by_names(
+            picked_tool_names
+        )
         picked_tools_prompt = self.tooluniverse.prepare_tool_prompts(picked_tools)
         if return_call_result:
             return picked_tools_prompt, picked_tool_names

tooluniverse/tool_finder_keyword.py

@@ -451,7 +451,9 @@ class ToolFinderKeyword(BaseTool):
         picked_tool_names = picked_tool_names_no_special[:rag_num]
 
         # Get tool objects and prepare prompts (matching original behavior)
-        picked_tools = self.tooluniverse.get_tool_by_name(picked_tool_names)
+        picked_tools = self.tooluniverse.get_tool_specification_by_names(
+            picked_tool_names
+        )
         picked_tools_prompt = self.tooluniverse.prepare_tool_prompts(picked_tools)
 
         if return_call_result:

tooluniverse/tool_finder_llm.py

@@ -387,7 +387,9 @@ Requirements:
 
             # Get actual tool objects
             if tool_names:
-                selected_tool_objects = self.tooluniverse.get_tool_by_name(tool_names)
+                selected_tool_objects = (
+                    self.tooluniverse.get_tool_specification_by_names(tool_names)
+                )
                 tool_prompts = self.tooluniverse.prepare_tool_prompts(
                     selected_tool_objects
                 )
@@ -495,7 +497,9 @@ Requirements:
         picked_tool_names = picked_tool_names_no_special[:rag_num]
 
         # Get tool objects and prepare prompts (needed for both list and other formats)
-        picked_tools = self.tooluniverse.get_tool_by_name(picked_tool_names)
+        picked_tools = self.tooluniverse.get_tool_specification_by_names(
+            picked_tool_names
+        )
         picked_tools_prompt = self.tooluniverse.prepare_tool_prompts(picked_tools)
 
         # If only list format is requested, return the tool specifications as a list

tooluniverse/tools/{UCSC_get_genes_by_region.py → BLAST_nucleotide_search.py}

@@ -1,39 +1,36 @@
 """
-UCSC_get_genes_by_region
+BLAST_nucleotide_search
 
-Query UCSC Genome Browser track API for knownGene features in a genomic window.
+Search nucleotide sequences using NCBI BLAST blastn against nucleotide databases
 """
 
 from typing import Any, Optional, Callable
 from ._shared_client import get_shared_client
 
 
-def UCSC_get_genes_by_region(
-    chrom: str,
-    start: int,
-    end: int,
-    genome: Optional[str] = "hg38",
-    track: Optional[str] = "knownGene",
+def BLAST_nucleotide_search(
+    sequence: str,
+    database: Optional[str] = "nt",
+    expect: Optional[float] = 10.0,
+    hitlist_size: Optional[int] = 50,
     *,
     stream_callback: Optional[Callable[[str], None]] = None,
     use_cache: bool = False,
     validate: bool = True,
 ) -> dict[str, Any]:
     """
-    Query UCSC Genome Browser track API for knownGene features in a genomic window.
+    Search nucleotide sequences using NCBI BLAST blastn against nucleotide databases
 
     Parameters
     ----------
-    genome : str
-        Genome assembly (e.g., hg38).
-    chrom : str
-        Chromosome (e.g., chr17).
-    start : int
-        Start position (0-based).
-    end : int
-        End position.
-    track : str
-        Track name.
+    sequence : str
+        DNA sequence to search
+    database : str
+        Database (nt, est, etc.)
+    expect : float
+        E-value threshold
+    hitlist_size : int
+        Max hits to return
     stream_callback : Callable, optional
         Callback for streaming output
     use_cache : bool, default False
@@ -49,13 +46,12 @@ def UCSC_get_genes_by_region(
 
     return get_shared_client().run_one_function(
         {
-            "name": "UCSC_get_genes_by_region",
+            "name": "BLAST_nucleotide_search",
             "arguments": {
-                "genome": genome,
-                "chrom": chrom,
-                "start": start,
-                "end": end,
-                "track": track,
+                "sequence": sequence,
+                "database": database,
+                "expect": expect,
+                "hitlist_size": hitlist_size,
             },
         },
         stream_callback=stream_callback,
@@ -64,4 +60,4 @@ def UCSC_get_genes_by_region(
     )
 
 
-__all__ = ["UCSC_get_genes_by_region"]
+__all__ = ["BLAST_nucleotide_search"]

tooluniverse/tools/BLAST_protein_search.py

@@ -0,0 +1,63 @@
+"""
+BLAST_protein_search
+
+Search protein sequences using NCBI BLAST blastp against protein databases
+"""
+
+from typing import Any, Optional, Callable
+from ._shared_client import get_shared_client
+
+
+def BLAST_protein_search(
+    sequence: str,
+    database: Optional[str] = "nr",
+    expect: Optional[float] = 10.0,
+    hitlist_size: Optional[int] = 50,
+    *,
+    stream_callback: Optional[Callable[[str], None]] = None,
+    use_cache: bool = False,
+    validate: bool = True,
+) -> dict[str, Any]:
+    """
+    Search protein sequences using NCBI BLAST blastp against protein databases
+
+    Parameters
+    ----------
+    sequence : str
+        Protein sequence to search
+    database : str
+        Database (nr, swissprot, etc.)
+    expect : float
+
+    hitlist_size : int
+
+    stream_callback : Callable, optional
+        Callback for streaming output
+    use_cache : bool, default False
+        Enable caching
+    validate : bool, default True
+        Validate parameters
+
+    Returns
+    -------
+    dict[str, Any]
+    """
+    # Handle mutable defaults to avoid B006 linting error
+
+    return get_shared_client().run_one_function(
+        {
+            "name": "BLAST_protein_search",
+            "arguments": {
+                "sequence": sequence,
+                "database": database,
+                "expect": expect,
+                "hitlist_size": hitlist_size,
+            },
+        },
+        stream_callback=stream_callback,
+        use_cache=use_cache,
+        validate=validate,
+    )
+
+
+__all__ = ["BLAST_protein_search"]

tooluniverse/tools/ClinVar_search_variants.py

@@ -1,30 +1,36 @@
 """
-ClinVar_search_variants
+clinvar_search_variants
 
-Search ClinVar via NCBI E-utilities (esearch→esummary) and return concise variant records for a q...
+Search for variants in ClinVar database by gene name, condition, or variant ID. Returns variant i...
 """
 
 from typing import Any, Optional, Callable
 from ._shared_client import get_shared_client
 
 
-def ClinVar_search_variants(
-    query: str,
-    retmax: Optional[int] = 5,
+def clinvar_search_variants(
+    gene: Optional[str] = None,
+    condition: Optional[str] = None,
+    variant_id: Optional[str] = None,
+    max_results: Optional[int] = 20,
     *,
     stream_callback: Optional[Callable[[str], None]] = None,
     use_cache: bool = False,
     validate: bool = True,
-) -> list[Any]:
+) -> dict[str, Any]:
     """
-    Search ClinVar via NCBI E-utilities (esearch→esummary) and return concise variant records for a q...
+    Search for variants in ClinVar database by gene name, condition, or variant ID. Returns variant i...
 
     Parameters
     ----------
-    query : str
-        ClinVar search term (e.g., BRCA1).
-    retmax : int
-        Max records.
+    gene : str
+        Gene name or symbol (e.g., 'BRCA1', 'BRCA2')
+    condition : str
+        Disease or condition name (e.g., 'breast cancer', 'diabetes')
+    variant_id : str
+        ClinVar variant ID (e.g., '12345')
+    max_results : int
+        Maximum number of results to return
     stream_callback : Callable, optional
         Callback for streaming output
     use_cache : bool, default False
@@ -34,14 +40,19 @@ def ClinVar_search_variants(
 
     Returns
     -------
-    list[Any]
+    dict[str, Any]
     """
     # Handle mutable defaults to avoid B006 linting error
 
     return get_shared_client().run_one_function(
         {
-            "name": "ClinVar_search_variants",
-            "arguments": {"query": query, "retmax": retmax},
+            "name": "clinvar_search_variants",
+            "arguments": {
+                "gene": gene,
+                "condition": condition,
+                "variant_id": variant_id,
+                "max_results": max_results,
+            },
         },
         stream_callback=stream_callback,
         use_cache=use_cache,
@@ -49,4 +60,4 @@ def ClinVar_search_variants(
     )
 
 
-__all__ = ["ClinVar_search_variants"]
+__all__ = ["clinvar_search_variants"]

tooluniverse/tools/CodeQualityAnalyzer.py

@@ -14,12 +14,12 @@ def CodeQualityAnalyzer(
     tool_parameters: str,
     implementation_code: str,
     test_cases: str,
-    test_execution_results: Optional[str] = None,
+    test_execution_results: str,
     *,
     stream_callback: Optional[Callable[[str], None]] = None,
     use_cache: bool = False,
     validate: bool = True,
-) -> Any:
+) -> dict[str, Any]:
     """
     Analyzes code quality from multiple dimensions including algorithmic correctness, functional impl...
 
@@ -46,7 +46,7 @@ def CodeQualityAnalyzer(
 
     Returns
     -------
-    Any
+    dict[str, Any]
     """
     # Handle mutable defaults to avoid B006 linting error
 

tooluniverse/tools/EMDB_get_structure.py

@@ -0,0 +1,46 @@
+"""
+EMDB_get_structure
+
+Get electron microscopy structure data from EMDB
+"""
+
+from typing import Any, Optional, Callable
+from ._shared_client import get_shared_client
+
+
+def EMDB_get_structure(
+    emdb_id: str,
+    *,
+    stream_callback: Optional[Callable[[str], None]] = None,
+    use_cache: bool = False,
+    validate: bool = True,
+) -> dict[str, Any]:
+    """
+    Get electron microscopy structure data from EMDB
+
+    Parameters
+    ----------
+    emdb_id : str
+        EMDB structure ID (e.g., EMD-1234)
+    stream_callback : Callable, optional
+        Callback for streaming output
+    use_cache : bool, default False
+        Enable caching
+    validate : bool, default True
+        Validate parameters
+
+    Returns
+    -------
+    dict[str, Any]
+    """
+    # Handle mutable defaults to avoid B006 linting error
+
+    return get_shared_client().run_one_function(
+        {"name": "EMDB_get_structure", "arguments": {"emdb_id": emdb_id}},
+        stream_callback=stream_callback,
+        use_cache=use_cache,
+        validate=validate,
+    )
+
+
+__all__ = ["EMDB_get_structure"]

tooluniverse/tools/GtoPdb_get_targets.py

@@ -0,0 +1,52 @@
+"""
+GtoPdb_get_targets
+
+Get pharmacological targets from Guide to Pharmacology database
+"""
+
+from typing import Any, Optional, Callable
+from ._shared_client import get_shared_client
+
+
+def GtoPdb_get_targets(
+    target_type: Optional[str] = "protein",
+    limit: Optional[int] = 20,
+    *,
+    stream_callback: Optional[Callable[[str], None]] = None,
+    use_cache: bool = False,
+    validate: bool = True,
+) -> list[Any]:
+    """
+    Get pharmacological targets from Guide to Pharmacology database
+
+    Parameters
+    ----------
+    target_type : str
+        Target type
+    limit : int
+        Number of results
+    stream_callback : Callable, optional
+        Callback for streaming output
+    use_cache : bool, default False
+        Enable caching
+    validate : bool, default True
+        Validate parameters
+
+    Returns
+    -------
+    list[Any]
+    """
+    # Handle mutable defaults to avoid B006 linting error
+
+    return get_shared_client().run_one_function(
+        {
+            "name": "GtoPdb_get_targets",
+            "arguments": {"target_type": target_type, "limit": limit},
+        },
+        stream_callback=stream_callback,
+        use_cache=use_cache,
+        validate=validate,
+    )
+
+
+__all__ = ["GtoPdb_get_targets"]

tooluniverse/tools/InterPro_get_domain_details.py

@@ -0,0 +1,46 @@
+"""
+InterPro_get_domain_details
+
+Get detailed information about a specific InterPro domain entry including description, hierarchy,...
+"""
+
+from typing import Any, Optional, Callable
+from ._shared_client import get_shared_client
+
+
+def InterPro_get_domain_details(
+    accession: str,
+    *,
+    stream_callback: Optional[Callable[[str], None]] = None,
+    use_cache: bool = False,
+    validate: bool = True,
+) -> dict[str, Any]:
+    """
+    Get detailed information about a specific InterPro domain entry including description, hierarchy,...
+
+    Parameters
+    ----------
+    accession : str
+        InterPro accession ID (e.g., IPR000719, IPR000719)
+    stream_callback : Callable, optional
+        Callback for streaming output
+    use_cache : bool, default False
+        Enable caching
+    validate : bool, default True
+        Validate parameters
+
+    Returns
+    -------
+    dict[str, Any]
+    """
+    # Handle mutable defaults to avoid B006 linting error
+
+    return get_shared_client().run_one_function(
+        {"name": "InterPro_get_domain_details", "arguments": {"accession": accession}},
+        stream_callback=stream_callback,
+        use_cache=use_cache,
+        validate=validate,
+    )
+
+
+__all__ = ["InterPro_get_domain_details"]

tooluniverse/tools/InterPro_get_protein_domains.py

@@ -0,0 +1,49 @@
+"""
+InterPro_get_protein_domains
+
+Get protein domain annotations from InterPro database using UniProt protein ID. Returns domain fa...
+"""
+
+from typing import Any, Optional, Callable
+from ._shared_client import get_shared_client
+
+
+def InterPro_get_protein_domains(
+    protein_id: str,
+    *,
+    stream_callback: Optional[Callable[[str], None]] = None,
+    use_cache: bool = False,
+    validate: bool = True,
+) -> list[Any]:
+    """
+    Get protein domain annotations from InterPro database using UniProt protein ID. Returns domain fa...
+
+    Parameters
+    ----------
+    protein_id : str
+        UniProt protein ID (e.g., P05067, Q9Y6K9)
+    stream_callback : Callable, optional
+        Callback for streaming output
+    use_cache : bool, default False
+        Enable caching
+    validate : bool, default True
+        Validate parameters
+
+    Returns
+    -------
+    list[Any]
+    """
+    # Handle mutable defaults to avoid B006 linting error
+
+    return get_shared_client().run_one_function(
+        {
+            "name": "InterPro_get_protein_domains",
+            "arguments": {"protein_id": protein_id},
+        },
+        stream_callback=stream_callback,
+        use_cache=use_cache,
+        validate=validate,
+    )
+
+
+__all__ = ["InterPro_get_protein_domains"]