Skip to main content
Glama
oktaycosar
by oktaycosar

ο»Ώ# Manim MCP β€” DeepSeek Only

Altin Kural: Sadece DeepSeek. Baska hicbir LLM provider YOK. OpenAI SDK β†’ DeepSeek endpoint. Google Gemini, OpenAI, Claude import edilmez.

Manim ile matematik animasyonlari ureten MCP sunucusu. DeepSeek LLM + ChromaDB tabanli RAG ile ilgili Manim kod orneklerini getirip, kullanici istedigi animasyonu uretir ve render eder.

Ozellikler

  • 🎬 Manim Community animasyon uretimi (DeepSeek deepseek-chat / deepseek-reasoner)

  • 🧠 ChromaDB tabanli RAG β€” vektor arama ile ilgili kod orneklerini getirir

  • πŸ“š Coklu kaynak indexleme β€” 3Blue1Brown videolari, animg kutuphanesi, Manim Kindergarten verisi, Pisagor ve ozel sahneler

  • πŸ“– Storyboard katmani β€” sahne planini JSON olarak uretir (storyboard.json)

  • πŸ”„ Geri besleme dongusu β€” basarili render'lar RAG'e geri beslenir (feed_rag.py)

  • πŸ–₯️ CLI + MCP β€” hem terminal hem VS Code MCP uzerinden kullanilabilir

Related MCP server: Manim MCP Server

Hizli Baslangic

# 1. Kur
pip install -r requirements.txt

# 2. .env dosyasini duzenle (DEEPSEEK_API_KEY zorunlu)
#    .env.example dosyasini .env olarak kopyala, API keyini yaz

# 3. (Istege bagli) RAG indexlerini olustur
python index_animg.py
python index_3b1b_videos.py
python index_pisagor.py

# 4. Sunucuyu baslat (1. terminal)
python server.py

# 5. CLI'yi baslat (2. terminal)
python cli.py

# 6. Test et
>>> Bir daire ciz ve kaydir
>>> /doc How to animate a square transforming into a circle
>>> /health

Mimarisi

                      β”Œβ”€β”€ index_*.py ──▢ ChromaDB (chroma_data/)
                      β”‚
storyboard.json ◀── generate_storyboard.py
                      β”‚
cli.py ──HTTP──▢ server.py ──OpenAI SDK──▢ api.deepseek.com
                      β”‚                          β”‚
                      β”œβ”€β”€ manim_mcp (manim-mcp-original)
                      β”‚     β”œβ”€β”€ core/rag.py        (ChromaDBService - RAG)
                      β”‚     β”œβ”€β”€ core/tracker.py    (RenderTracker)
                      β”‚     β”œβ”€β”€ prompts/           (system prompt sablonlari)
                      β”‚     └── config.py          (ManimMCPConfig)
                      β”‚
render_with_rag.py ◀── RAG retrieval (5 koleksiyon: patterns, components, helpers, scenes, 3b1b)
                      β”‚
                      └── feed_rag.py ──▢ basarili render'lar RAG'e geri beslenir

Dosyalar

Dosya

Gorevi

server.py

Flask MCP sunucusu (JSON-RPC)

cli.py

Terminal arayuzu

deepseek_client.py

OpenAI SDK ile DeepSeek API

manim_tools.py

MCP tool tanimlari (DeepSeek/OpenAI format)

config.py

.env tabanli yapilandirma (DeepSeek + MCP + Manim + RAG)

render_with_rag.py

RAG destekli animasyon uretim pipeline'i

generate_storyboard.py

Storyboard JSON uretici (ornek: Pisagor)

feed_rag.py

Basarili render'lari ChromaDB'ye besler

index_animg.py

animg kutuphanesi β†’ ChromaDB

index_3b1b_videos.py

3Blue1Brown videolari β†’ ChromaDB

index_pisagor.py

Pisagor ozel verisi β†’ ChromaDB

index_manim_kindergarten.py

Manim Kindergarten verisi β†’ ChromaDB

index_custom_scene.py

Ozel sahneler β†’ ChromaDB

manim-mcp-original/manim_mcp/

Cekirdek paket (RAG, tracker, promptlar)

storyboard.json

Ornek storyboard tanimi

mcp.template.json

VS Code MCP yapilandirmasi

.env.example

Sablon .env dosyasi

RAG (ChromaDB)

  • Embedding ve vektor arama ChromaDB uzerinden yapilir (TF-IDF degil)

  • Veri yolu: MANIM_MCP_CHROMADB_PATH (varsayilan: ./chroma_data)

  • render_with_rag.py 5 koleksiyondan paralel ceker: patterns, components, helpers, scenes, 3b1b

  • RAG protokolu icin: RAG_PROTOCOL.md

Testler

python test_code_generation.py   # kod uretim testi
python test_critical.py          # kritik akis testleri
python test_precision.py         # hassasiyet testleri
python test_production.py        # uretim testleri

Neden DeepSeek?

Orijinal paulnegz/manim-mcp reposu google.generativeai kullanir. Bu su demek:

  • Kod Gemini SDK import eder ama DEEPSEEK_API_KEY ayarlanmistir

  • Google SDK GOOGLE_API_KEY arar, DeepSeek keyini yok sayar

  • Ya crash olur ya da sessizce Geminiye gider

Bizim cozumumuz: from openai import OpenAI + base_url="https://api.deepseek.com" DeepSeek, OpenAI API uyumlu oldugu icin baska hicbir SDKya gerek yok.

MCP Olarak Kullan

mcp.template.json dosyasini VS Code MCP ayarlarina kopyala, DEEPSEEK_API_KEYi yaz.

F
license - not found
-
quality - not tested
B
maintenance

Maintenance

–Maintainers
–Response time
–Release cycle
–Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

View all related MCP servers

Related MCP Connectors

  • Create and manage AI agents that collaborate and solve problems through natural language interacti…

  • Persistent memory and knowledge management for AI agents with semantic search and 50+ tools.

  • Generate images, video, and audio with Glif's media-generation agent

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/oktaycosar/manim-mcp-rag'

If you have feedback or need assistance with the MCP directory API, please join our Discord server