MCP-Slicer

Instructions

Implementation Reference

• src/mcp_slicer/mcp_server.py:46-115 (handler)

  The list_nodes tool handler, decorated with @mcp.tool() for automatic registration with the FastMCP server. It implements the core logic to list MRML nodes by querying the Slicer Web Server API based on filter_type ('names', 'ids', 'properties') and optional filters (class_name, name, id). Includes input/output schema in type hints and comprehensive docstring.
  @mcp.tool() def list_nodes(filter_type: str = "names", class_name: str = None, name: str = None, id: str = None) -> dict: """ List MRML nodes via the Slicer Web Server API. The filter_type parameter specifies the type of node information to retrieve. Possible values include "names" (node names), "ids" (node IDs), and "properties" (node properties). The default value is "names". The class_name, name, and id parameters are optional and can be used to further filter nodes. The class_name parameter allows filtering nodes by class name. The name parameter allows filtering nodes by name. The id parameter allows filtering nodes by ID. Examples: - List the names of all nodes: {"tool": "list_nodes", "arguments": {"filter_type": "names"}} - List the IDs of nodes of a specific class: {"tool": "list_nodes", "arguments": {"filter_type": "ids", "class_name": "vtkMRMLModelNode"}} - List the properties of nodes with a specific name: {"tool": "list_nodes", "arguments": {"filter_type": "properties", "name": "MyModel"}} - List nodes with a specific ID: {"tool": "list_nodes", "arguments": {"filter_type": "ids", "id": "vtkMRMLModelNode123"}} Returns a dictionary containing node information. If filter_type is "names" or "ids", the returned dictionary contains a "nodes" key, whose value is a list containing node names or IDs. Example: {"nodes": ["node1", "node2", ...]} or {"nodes": ["id1", "id2", ...]} If filter_type is "properties", the returned dictionary contains a "nodes" key, whose value is a dictionary containing node properties. Example: {"nodes": {"node1": {"property1": "value1", "property2": "value2"}, ...}} If an error occurs, a dictionary containing an "error" key is returned, whose value is a string describing the error. """ try: # Build API endpoint based on filter type endpoint_map = { "names": "/mrml/names", "ids": "/mrml/ids", "properties": "/mrml/properties" } if filter_type not in endpoint_map: return {"error": "Invalid filter_type specified"} api_url = f"{SLICER_WEB_SERVER_URL}{endpoint_map[filter_type]}" # Build query parameters params = {} if class_name: params["class"] = class_name if name: params["name"] = name if id: params["id"] = id # Send GET request to Slicer Web Server # Smart proxy handling: disable for localhost, use system default for others response = requests.get(api_url, params=params, proxies=get_proxy_config(api_url)) response.raise_for_status() # Process response based on filter type if filter_type == "properties": return {"nodes": response.json()} return {"nodes": response.json()} except requests.exceptions.HTTPError as e: return {"error": f"HTTP Error {e.response.status_code}: {str(e)}"} except json.JSONDecodeError: return {"error": f"Invalid JSON response: {response.text}"} except requests.exceptions.RequestException as e: return {"error": f"Connection error: {str(e)}"} except Exception as e: return {"error": f"Node listing failed: {str(e)}"}
• src/mcp_slicer/mcp_server.py:47-73 (schema)

  Type hints and docstring define the input schema (filter_type:str='names', class_name:str=None, name:str=None, id:str=None) and output schema (dict with 'nodes' list/dict or 'error' str), including usage examples.
  def list_nodes(filter_type: str = "names", class_name: str = None, name: str = None, id: str = None) -> dict: """ List MRML nodes via the Slicer Web Server API. The filter_type parameter specifies the type of node information to retrieve. Possible values include "names" (node names), "ids" (node IDs), and "properties" (node properties). The default value is "names". The class_name, name, and id parameters are optional and can be used to further filter nodes. The class_name parameter allows filtering nodes by class name. The name parameter allows filtering nodes by name. The id parameter allows filtering nodes by ID. Examples: - List the names of all nodes: {"tool": "list_nodes", "arguments": {"filter_type": "names"}} - List the IDs of nodes of a specific class: {"tool": "list_nodes", "arguments": {"filter_type": "ids", "class_name": "vtkMRMLModelNode"}} - List the properties of nodes with a specific name: {"tool": "list_nodes", "arguments": {"filter_type": "properties", "name": "MyModel"}} - List nodes with a specific ID: {"tool": "list_nodes", "arguments": {"filter_type": "ids", "id": "vtkMRMLModelNode123"}} Returns a dictionary containing node information. If filter_type is "names" or "ids", the returned dictionary contains a "nodes" key, whose value is a list containing node names or IDs. Example: {"nodes": ["node1", "node2", ...]} or {"nodes": ["id1", "id2", ...]} If filter_type is "properties", the returned dictionary contains a "nodes" key, whose value is a dictionary containing node properties. Example: {"nodes": {"node1": {"property1": "value1", "property2": "value2"}, ...}} If an error occurs, a dictionary containing an "error" key is returned, whose value is a string describing the error. """
• src/mcp_slicer/mcp_server.py:46-46 (registration)

  The @mcp.tool() decorator registers the list_nodes function as an MCP tool with the FastMCP server instance.
  @mcp.tool()