Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@vtkapi-mcp Validate VTK: vtkSphereSource()"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Post-generation validation of VTK Python code using Model Context Protocol (MCP).
This module provides automatic validation of generated VTK code to catch API hallucinations:
✅ Direct API lookups - No vector search overhead, exact class/method verification
✅ Method existence validation - Detects when LLM invents non-existent methods
✅ Import validation - Verifies VTK classes are imported from correct modules
✅ Fast in-memory index - Loads ~2,900 VTK classes at startup
✅ Structured error reporting - Clear error messages with suggestions
Related MCP server: mcp-server-analyzer
From PyPI (recommended once published):
pip install vtkapi-mcpFor local development we standardize on uv to manage the virtualenv and extras:
uv venv .venv
source .venv/bin/activate
uv sync --extra dev # runtime + pytest + ruffNote: The 64 MB
data/vtk-python-docs.jsonlfile is required at runtime but is not bundled in the wheel. Place it underdata/(or pass--api-docs /path/to/file) before launching the MCP server.
Prefer automation? ./setup.sh now wraps the same uv workflow and accepts --dev to include the testing toolchain.
uv run python demo_mcp_integration.pyThis runs a complete demo showing how to use vtkapi-mcp as an MCP server (not as standalone Python library). It demonstrates all 18 MCP tools and error detection.
Task | Command |
Run unit + integration tests |
|
Run tests with coverage report |
|
Run Ruff lint & format checks |
|
These commands automatically reuse the
.venvcreated viauv venv/uv sync. No manual activation is required.
Add to your MCP settings (e.g., Claude Desktop config):
{
"mcpServers": {
"vtk-api": {
"command": "python",
"args": [
"-m",
"vtkapi_mcp",
"--api-docs",
"/absolute/path/to/vtkapi-mcp/data/vtk-python-docs.jsonl"
]
}
}
}The MCP server provides 18 tools for VTK API validation and lookup. See MCP Tools below.
vtkapi_mcp/
├── core/ # API indexing and data loading
│ └── api_index.py
├── validation/ # Code validation logic
│ ├── models.py
│ ├── validator.py
│ ├── import_validator.py
│ ├── class_validator.py
│ └── method_validator.py
├── server/ # MCP server implementation
│ ├── mcp_server.py
│ └── tools.py
└── utils/ # Utilities for parsing and search
├── extraction.py
└── search.pyFile | Purpose |
| Demo showing proper MCP integration (not standalone) |
| Python package configuration and dependencies |
| This file |
File | Purpose | Size |
| VTK API documentation (~2,900 classes) | ~64 MB |
Fast in-memory index of all VTK classes and methods:
VTKAPIIndex
├── Classes Dict: {class_name → {module, methods, docs}}
├── Modules Dict: {module_name → [class_names]}
└── Load Time: <1 second for ~2,900 classesKey Methods:
get_class_info(class_name) - Get module and documentation
search_classes(query) - Search by name or keyword
get_module_classes(module) - List classes in module
class_exists(class_name) - Check if class exists
AST-based validation of generated Python code:
VTKCodeValidator
├── Parse Code: Uses Python's ast module
├── Extract VTK Usage:
│ ├── Import statements
│ ├── Class instantiations
│ └── Method calls
├── Validate Against Index:
│ ├── Check classes exist
│ ├── Check imports correct
│ └── Check methods exist
└── Generate Error ReportValidation Types:
Import Validation - Verifies module paths
Class Validation - Checks class existence
Method Validation - Detects hallucinated methods
When running as MCP server, provides these 18 tools:
vtk_get_class_infoGet complete information about a VTK class.
Input:
{
"class_name": "vtkPolyDataMapper"
}Output:
{
"class_name": "vtkPolyDataMapper",
"module": "vtkmodules.vtkRenderingCore",
"content_preview": "vtkPolyDataMapper - map vtkPolyData to graphics primitives..."
}vtk_search_classesSearch for VTK classes by name or keyword.
Input:
{
"query": "reader",
"limit": 5
}Output:
[
{
"class_name": "vtkSTLReader",
"module": "vtkmodules.vtkIOGeometry",
"description": "Read ASCII or binary stereo lithography files."
}
]vtk_validate_importValidate and correct VTK import statements.
Input:
{
"import_statement": "from vtkmodules.vtkCommonDataModel import vtkPolyDataMapper"
}Output:
{
"valid": false,
"message": "Incorrect module. 'vtkPolyDataMapper' is in 'vtkmodules.vtkRenderingCore'",
"suggested": "from vtkmodules.vtkRenderingCore import vtkPolyDataMapper"
}vtk_get_method_infoGet full information about a specific method including section context.
Input:
{
"class_name": "vtkPolyDataMapper",
"method_name": "SetInputData"
}Output:
{
"class_name": "vtkPolyDataMapper",
"method_name": "SetInputData",
"content": "SetInputData(vtkDataObject) - Set the input data...",
"section": "Methods defined here"
}vtk_get_method_docGet just the docstring for a specific method.
Input:
{
"class_name": "vtkPolyDataMapper",
"method_name": "SetInputData"
}Output:
{
"class_name": "vtkPolyDataMapper",
"method_name": "SetInputData",
"docstring": "SetInputData(vtkDataObject) - Set the input data...",
"found": true
}vtk_get_class_docGet the class documentation string.
Input:
{
"class_name": "vtkPolyDataMapper"
}Output:
{
"class_name": "vtkPolyDataMapper",
"class_doc": "vtkPolyDataMapper - map vtkPolyData to graphics primitives. Superclass: vtkMapper",
"found": true
}vtk_get_class_synopsisGet a brief synopsis/summary of what a class does.
Input:
{
"class_name": "vtkPolyDataMapper"
}Output:
{
"class_name": "vtkPolyDataMapper",
"synopsis": "Maps polygonal data (vtkPolyData) to graphics primitives for rendering.",
"found": true
}vtk_get_class_action_phraseGet the action phrase describing what a class does.
Input:
{
"class_name": "vtkPolyDataMapper"
}Output:
{
"class_name": "vtkPolyDataMapper",
"action_phrase": "polygon mapping",
"found": true
}vtk_get_class_roleGet the functional role/category of a class.
Input:
{
"class_name": "vtkPolyDataMapper"
}Output:
{
"class_name": "vtkPolyDataMapper",
"role": "rendering",
"found": true
}vtk_get_class_visibilityGet the visibility/exposure level of a class.
Input:
{
"class_name": "vtkPolyDataMapper"
}Output:
{
"class_name": "vtkPolyDataMapper",
"visibility": "likely",
"found": true
}vtk_get_module_classesList all classes in a specific module.
Input:
{
"module": "vtkmodules.vtkRenderingCore"
}Output:
{
"module": "vtkmodules.vtkRenderingCore",
"classes": ["vtkActor", "vtkPolyDataMapper", ...],
"count": 42
}vtk_get_class_moduleReturn the vtkmodules.* import path for a given VTK class.
Input:
{
"class_name": "vtkPolyDataMapper"
}Output:
{
"class_name": "vtkPolyDataMapper",
"module": "vtkmodules.vtkRenderingCore",
"found": true
}vtk_get_class_input_datatypeGet the input data type for a VTK class.
Input:
{
"class_name": "vtkPolyDataMapper"
}Output:
{
"class_name": "vtkPolyDataMapper",
"input_datatype": "vtkPolyData",
"found": true
}vtk_get_class_output_datatypeGet the output data type for a VTK class.
Input:
{
"class_name": "vtkContourFilter"
}Output:
{
"class_name": "vtkContourFilter",
"output_datatype": "vtkPolyData",
"found": true
}vtk_get_class_semantic_methodsGet semantically tagged methods for a VTK class (input setters, output getters, configuration methods).
Input:
{
"class_name": "vtkContourFilter"
}Output:
{
"class_name": "vtkContourFilter",
"semantic_methods": {
"input_setters": ["SetInputData", "SetInputConnection"],
"output_getters": ["GetOutput", "GetOutputPort"],
"configuration": ["SetValue", "SetNumberOfContours"]
},
"found": true
}vtk_is_a_classCheck if a given name is a valid VTK class.
Input:
{
"class_name": "vtkPolyDataMapper"
}Output:
{
"class_name": "vtkPolyDataMapper",
"is_vtk_class": true
}Aspect | RAG Retrieval | MCP Validation |
Speed | Vector search + reranking | Direct hash lookup (instant) |
Accuracy | Semantic similarity (can drift) | Exact API match (100%) |
Coverage | Top-K only (~10 results) | All ~2,900 classes available |
Tokens | Consumes prompt tokens | Tool calls (minimal cost) |
Errors | Silent hallucinations | Explicit error messages |
Generated Code:
stencil = vtkImageStencilToImage()
stencil.SetOutputWholeExtent([0, 10, 0, 10, 0, 10]) # ❌ Doesn't exist!Validation Error:
UNKNOWN_METHOD: Method 'SetOutputWholeExtent' not found on class 'vtkImageStencilToImage'
Suggestion: Did you mean SetOutputOrigin or SetOutputSpacing?Generated Code:
from vtkmodules.vtkCommonDataModel import vtkPolyDataMapper # ❌ Wrong module!Validation Error:
IMPORT_ERROR: 'vtkPolyDataMapper' is not in module 'vtkmodules.vtkCommonDataModel'
Correct import: from vtkmodules.vtkRenderingCore import vtkPolyDataMapperGenerated Code:
converter = vtkImageDataToPolyDataConverter() # ❌ Class doesn't exist!Validation Error:
UNKNOWN_CLASS: Class 'vtkImageDataToPolyDataConverter' not found in VTK
Suggestion: Did you mean vtkImageDataGeometryFilter?Input: data/vtk-python-docs.jsonl
Each line is a VTK class documentation in JSON format:
{
"class_name": "vtkPolyDataMapper",
"module_name": "vtkmodules.vtkRenderingCore",
"class_doc": "vtkPolyDataMapper - map vtkPolyData to graphics primitives. Superclass: vtkMapper",
"synopsis": "Maps polygonal data (vtkPolyData) to graphics primitives for rendering.",
"action_phrase": "polygon mapping",
"role": "rendering",
"visibility_score": "likely",
"input_datatype": "vtkPolyData",
"output_datatype": "",
"semantic_methods": { "input_setters": [...], "output_getters": [...] },
"structured_docs": { "sections": { ... } }
}Coverage: ~2,900 VTK classes from VTK Python API
Method signature validation - Check parameter types and counts
Deprecation warnings - Flag deprecated VTK methods
Pipeline validation - Verify data flow compatibility
Auto-fix suggestions - Generate corrected code automatically
Performance profiling - Track validation overhead
Cache layer - Cache frequent lookups for speed
This is a standalone MCP server for VTK API validation. Extracted from the vtk-rag project.
Status: Production ready MCP server for VTK API validation.
Get the action phrase describing what a VTK class does (e.g., 'data reading', 'mesh filtering')
Inputs: class_name (required).
Get the class documentation string for a VTK class
Inputs: class_name (required).
Get complete information about a VTK class including module path, description, and methods
Inputs: class_name (required).
Get the input data type for a VTK class (e.g., 'vtkPolyData', 'vtkImageData')
Inputs: class_name (required).
List all methods (with signatures) for a VTK class and optionally verify a specific method
Inputs: class_name (required), method_name.
Return the vtkmodules.* import path for a given VTK class
Inputs: class_name (required).
Get the output data type for a VTK class (e.g., 'vtkPolyData', 'vtkImageData')
Inputs: class_name (required).
Get the pipeline role of a VTK class. Returns one of: input, filter, properties, renderer, scene, infrastructure, output, utility, color
Inputs: class_name (required).
Get non-boilerplate callable methods for a VTK class. Excludes dunder methods, private methods, and VTK infrastructure methods.
Inputs: class_name (required).
Get a brief synopsis/summary of what a VTK class does
Inputs: class_name (required).
Get the visibility score of a VTK class (0.0-1.0). Higher scores indicate classes more likely to be used directly.
Inputs: class_name (required).
Get just the docstring for a specific method of a VTK class
Inputs: class_name (required), method_name (required).
Get documentation for a specific method of a VTK class
Inputs: class_name (required), method_name (required).
Return only the canonical signature for a specific method of a VTK class (minimal payload)
Inputs: class_name (required), method_name (required).
List all VTK classes in a specific module
Inputs: module (required).
Check if a given name is a valid VTK class. Returns true if it exists in the VTK API, false otherwise.
Inputs: class_name (required).
Search for VTK classes by name or keyword
Inputs: query (required), limit.
Validate if a VTK import statement is correct and suggest corrections
Inputs: import_statement (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Scored across 18 tools
Each tool has a clearly distinct purpose, querying different aspects of VTK classes (e.g., action phrase, doc, methods, module). Overlaps are minimal and well-defined (e.g., three method-query tools differentiate by payload: doc only, doc+signature, signature only).
All tools follow a consistent snake_case pattern with 'vtk_' prefix, verb (mostly 'get', plus 'is_a', 'search', 'validate'), and specific resource. Naming is predictable and uniform.
With 18 tools, the set is well-scoped for a reference API server that provides detailed class metadata. Each tool serves a clear need without clutter.
The tool surface covers all key aspects of VTK class information: identification, documentation, methods, module path, input/output types, role, visibility, search, import validation, and per-module listing. No obvious gaps for the stated purpose.
MCP server providing access to the Scorecard API to evaluate and optimize LLM systems.
MCP Server for Slima - AI Writing IDE for Novel Authors with AI Beta Reader.
MCP server for building and testing AI agents with multi-model experimentation and insights.
MCP server for secureFlows: token-free URL builders and integration-linting tools for AI agents.
