Architecture
FastMCP native integration
EGL/OSMesa headless · cinematic lighting · PBR
Vortex detection · stagnation points · BC parsing
Physics-driven · timeline · compositor · video
50+ input formats via VTK + meshio
One Pipeline, Every Domain
Every render is a single MCP tool call — no GUI, no post-processing, no ParaView. VTK-native annotations rendered inside the 3D scene.
CT skull volume rendering
Combustion streamlines
Heatsink gradient
Seismic wavefield
DrivAerML Cp · 8.8M cells
H₂O electron density
Cerebral aneurysm MRA
Bennu · 196K triangles
Cantilever FEA stress
Thermal threshold
Physics Insights, Not Just Pixels
Extract physics, render LaTeX equations, compose cinematic story layouts. One pipeline, one command.
inspect_physics → cinematic_render × 4 → LaTeX equations → compose_assets
Every Effect Has a Physical Reason
Not slideshows — real VTK frame-by-frame rendering with physics-driven presets.
Streamline Growth
Lagrangian advection
streamline_growth Clip Sweep
Pressure gradient cross-section
clip_sweep Layer Reveal
CT density classification
layer_reveal Iso Sweep
Orbital topology
iso_sweep Warp Oscillation
Structural mode shape
warp_oscillation Light Orbit
Oblique illumination
light_orbit Threshold Reveal
Feature hierarchy
threshold_reveal Get started in 3 steps
Install
One-line pip install
pip install mcp-server-viznoir Or with Claude Code:
claude install kimimgo/viznoir Configure
Add to your MCP config
{
"mcpServers": {
"viznoir": {
"command": "mcp-server-viznoir"
}
}
} Use
Prompt in natural language
"Analyze cavity.foam, then compose
a story with LaTeX equations"