Connects Claude to manimgl's mathematical animation engine for programmatic video generation. Exposes tools for scene management, mobject creation (circles, LaTeX, function graphs, 3D primitives), animations (transforms, fades, rotations), and rendering. The audio toolkit handles TTS narration with gTTS, background music from audio or MIDI files, and automatic sidechain ducking so music volume drops during voiceovers. Render outputs composited MP4s with synchronized audio tracks. Useful when you need to generate animated math explainers, proofs, or algorithm visualizations without manually coding manimgl scenes. Requires ffmpeg and optional FluidSynth for MIDI rendering.
mcp-manimgl — MCP server exposing manimgl (Manim OpenGL) mathematical animation functionality as tools for LLMs.
mcp-name: io.github.daedalus/mcp-manimgl
pip install mcp-manimgl
Optional extras:
# For rendering (requires manimgl + system deps)
pip install "mcp-manimgl[render]"
# For audio narration + MIDI music support
pip install "mcp-manimgl[audio]"
| Dependency | Required for | Install |
|---|---|---|
ffmpeg + ffprobe | Audio mixing, narration sync, music ducking | apt install ffmpeg |
libfluidsynth3 | MIDI file rendering to audio | apt install libfluidsynth3 |
SoundFont (.sf2/.sf3) | MIDI instrument sounds | apt install fluidr3mono-gm-soundfont |
| pangocairo, OpenGL | Manim rendering engine | See manimgl docs |
The server checks for non-Python dependencies at startup and reports any missing ones to stderr and via the mcp-manimgl://info resource.
# Run with stdio transport (default for MCP)
mcp-manimgl
Add to your mcp.json:
{
"mcpServers": {
"mcp-manimgl": {
"command": "mcp-manimgl"
}
}
}
The server exposes these tool categories:
create_scene — Create/configure a new sceneclear_scene — Remove all elementsadd_wait — Add wait/pauseset_camera — Configure cameraset_config — Set global rendering configsave_state / restore_state — State managementgenerate_scene_script — Get the generated Python scriptadd_circle, add_square, add_rectangle, add_polygonadd_line, add_arrow, add_dotadd_text, add_tex (LaTeX)add_function_graph, add_parametric_curveadd_coordinate_system, add_vectoradd_labeled_point, add_brace, add_number_lineadd_decimal_number, add_matrixadd_3d_object (sphere, cube, torus, cone, cylinder)move_to, shift, scale, rotateset_color, set_opacitynext_to, align_toanimate_transform, animate_fade_in/out, animate_growanimate_rotate, animate_scale, animate_shiftanimate_indicate, animate_write, animate_set_coloranimate_move_along_path, animate_groupadd_narration — Generate TTS (gTTS) narration that plays at the current timeline positionadd_background_music — Add background music from audio files or MIDI files (auto-rendered via FluidSynth). Supports volume control, looping, and sidechain ducking during narration.render_scene — Render to video (auto-mixes background music + narration with ducking)save_frame — Save single frameget_render_status — Check environment# TTS narration at current timeline position
add_narration("Shor's algorithm factors large numbers in polynomial time.")
Accepts audio files (.mp3, .wav, .ogg) or MIDI files (.mid, .midi). MIDI files are rendered to audio using FluidSynth and the system SoundFont.
# From an audio file
add_background_music("/path/to/music.mp3", volume=0.3, loop=True)
# From a MIDI file (auto-rendered)
add_background_music("/path/to/classical.mid", volume=0.2)
# With ducking configuration
add_background_music(
"bach_chorale.mid",
volume=0.25,
loop=True,
duck_threshold="-20dB",
duck_ratio=6,
duck_attack=0.05,
duck_release=0.3,
)
When both background music and narration are present, render_scene automatically:
A narrated animation explaining Shor's algorithm with LaTeX, 5 TTS narration tracks, and classical MIDI background music.
MCP tool call sequence:
# 1. Configure scene
create_scene(background_color="#0a0a2e", resolution="1920x1080", fps=30)
# 2. Background music (auto-loops to fill video duration)
add_background_music("classical.mid", volume=0.25, loop=True)
# 3. Create mobjects + animate (5 sections)
add_tex("Shor's Algorithm", font_size=72, color="#FFD700")
add_tex("Integer Factorization on Quantum Computers", font_size=36, color="#88CCFF")
animate_fade_in("m_...", run_time=1.5)
# ... more shapes, LaTeX formulas, fade-ins, fade-outs ...
# 4. Narration at specific timeline positions
add_narration("Shor's algorithm factors large numbers...") # ~3.5s
add_narration("The factoring problem...") # ~18.5s
add_narration("Key insight: reduce factoring to period...") # ~36.1s
add_narration("Quantum period finding uses superposition...") # ~55.4s
add_narration("Summary of Shor's algorithm...") # ~76.3s
# 5. Render (auto-mixes video + narrations + ducked BGM)
render_scene(output_path="data/Shors_Algorithm.mp4")
See the full scene script at shor_mcp.py in the repository root.
MIDI files are rendered using pyfluidsynth with a system SoundFont. On Debian/Ubuntu:
sudo apt install fluidr3mono-gm-soundfont libfluidsynth3
pip install "mcp-manimgl[audio]"
Auto-discovered SoundFont paths:
/usr/share/sounds/sf3/ (.sf3)/usr/share/sounds/sf2/ (.sf2)/usr/share/fluidr3mono-gm-soundfont/git clone https://github.com/dclavijo/mcp-manimgl.git
cd mcp-manimgl
pip install -e ".[test]"
# run tests
pytest
# format
ruff format src/ tests/
# lint + type check
prospector --with-tool ruff --with-tool mypy src/
# security scan
semgrep --config=auto --severity=ERROR src/
# find unused code
vulture --min-confidence 90 src/
mcp-name: io.github.dclavijo/mcp-manimgl
miapre/html-to-figma-design-system
ie3jp/illustrator-mcp-server
coding-solo/godot-mcp
ivanmurzak/unity-mcp
yctimlin/mcp_excalidraw
figma/mcp-server-guide