Slicer MCP

Capture a screenshot from 3D Slicer for visual inspection.

This MCP tool gives the model a "what you see is what you get" view of Slicer, so it can reason about the current GUI state (panels, slice views, 3D rendering, overlays, etc.) and take follow‑up actions.

Behavior by `view_type`:

• "application": Capture the full Slicer application window, including all dock widgets, slice views and 3D views, as a compressed JPEG.

• "slice": Capture a single slice view (Red/Yellow/Green) as it currently appears on screen. The screenshot includes whatever UI elements are visible in that view (crosshair, orientation markers, labels, segment overlays, etc.).

• "3d": Capture the 3D rendering view. Optionally, a camera axis can be specified to look from a standard anatomical direction.

Parameters: view_type (str): Type of screenshot to capture. Options:

• "application" (default): Full application window.
• "slice": One named slice view.
• "3d": The 3D rendering view.

view_name (str): For slice views, which slice to capture. Options: "red", "yellow", "green". Only used when `view_type="slice"`.

camera_axis (str): For 3D views, camera view direction. Options: "L" (Left), "R" (Right), "A" (Anterior), "P" (Posterior), "I" (Inferior), "S" (Superior). Only used when `view_type="3d"`.

image_size (Optional[int]): Target pixel size for the output image.

• For slice views, this is treated as a maximum for the longer side of the captured pixmap; the image is scaled with preserved aspect ratio up to this size.
• For application and 3D views, the screenshot is captured at the current window size and may be downscaled if its longest side exceeds an internal maximum (for size control). Callers should not rely on an exact pixel size, only that larger values produce higher‑resolution images within reasonable limits.

Returns: list[mcp.types.Content]:

• TextContent`: A short, human‑readable description of what was captured (e.g. which view and approximate size).
• ImageContent`: The screenshot image in base64‑encoded JPEG format when capture succeeds, or omitted if only an error message is returned.

Note: This tool is primarily intended for multimodal models. Callers should inspect the returned screenshot with their vision capabilities (rather than relying only on the text summary) when reasoning about Slicer's state, UI layout, overlays, or other visual details.

The internal capture mechanism (e.g. which Slicer APIs or endpoints are used) is considered an implementation detail and may evolve over time without breaking this public contract.

Execute Python code in 3D Slicer.

Parameters: code (str): The Python code to execute.

The code parameter is a string containing the Python code to be executed in 3D Slicer's Python environment. The code should be executable by Python's exec() function. To get return values, the code should assign the result to a variable named __execResult.

Examples:

• Create a sphere model: {"tool": "execute_python_code", "arguments": {"code": "sphere = slicer.vtkMRMLModelNode(); slicer.mrmlScene.AddNode(sphere); sphere.SetName('MySphere'); __execResult = sphere.GetID()"}}
• Get the number of nodes in the current scene: {"tool": "execute_python_code", "arguments": {"code": "__execResult = len(slicer.mrmlScene.GetNodes())"}}
• Calculate 1+1: {"tool": "execute_python_code", "arguments": {"code": "__execResult = 1 + 1"}}

Returns: dict: A dictionary containing the execution result.

If the code execution is successful, the dictionary will contain the following key-value pairs:

• "success": True
• "message": The result of the code execution. If the code assigns the result to __execResult, the value of __execResult is returned, otherwise it returns empty.

If the code execution fails, the dictionary will contain the following key-value pairs:

• "success": False
• "message": A string containing an error message indicating the cause of the failure. The error message may come from the Slicer Web Server or the Python interpreter.

Examples:

• Successful execution: {"success": True, "message": 2} # Assuming the result of 1+1 is 2
• Successful execution: {"success": True, "message": "vtkMRMLScene1"} # Assuming the created sphere id is vtkMRMLScene1
• Python execution error: {"success": False, "message": "Server error: name 'slicer' is not defined"}
• Connection error: {"success": False, "message": "Connection error: ..."}
• HTTP error: {"success": False, "message": "HTTP Error 404: Not Found"}

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.