# Strands Agents Manim

> A minimal end-to-end tutorial to build an autonomous agent that generates mathematical animations using AWS Strands, Manim, and MCP.

- **Type:** MCP server
- **Install:** `agentstack add mcp-danielpuentee-strands-agents-manim`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [DanielPuentee](https://agentstack.voostack.com/s/danielpuentee)
- **Installs:** 0
- **Category:** [Cloud & Infrastructure](https://agentstack.voostack.com/c/cloud-infrastructure)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [DanielPuentee](https://github.com/DanielPuentee)
- **Source:** https://github.com/DanielPuentee/strands-agents-manim

## Install

```sh
agentstack add mcp-danielpuentee-strands-agents-manim
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# 🧶 Strands Agents + MCP Tutorial — Manim Visualizations

  

*A minimal end-to-end tutorial to build an autonomous agent that generates mathematical animations using AWS Strands, Manim, and MCP.*

[](https://github.com/psf/black)

> Author: [Daniel Puente Viejo](https://www.linkedin.com/in/danielpuenteviejo/)

---

## 🎯 Objective

This repository shows how to **combine AWS Strands Agents + Manim** to enable **model-driven visualization** using the **Model Context Protocol (MCP)**.
We will build an autonomous agent that accepts natural language math queries and orchestrates a local rendering engine to produce high-quality videos using **native AWS Bedrock models**.

---

## 🧠 Core Idea

We move away from hard-coded workflows to a fluid, 4-step autonomous process:

1.  **Query:** You provide a prompt (e.g., *"Create a grid and a unit square. Apply a shear transformation matrix [[1, 1], [0, 1]] to the grid to show how the space distorts."*).
2.  **Tool Use:** The **Strands Agent** uses the MCP tool to write the necessary Python/Manim code.
3.  **Execution:** The local MCP server receives the code and runs the rendering engine.
4.  **Generation:** A video file is generated and saved to your output folder.

---

## 🧩 Requirements

This project uses **uv** for dependency management.

- **Environment Variables:**
  Create a `.env` file with your AWS credentials:
  ```plaintext
  AWS_ACCESS_KEY_ID=
  AWS_SECRET_ACCESS_KEY=
  AWS_REGION=
  ```

---

## 🚀 How to Run

This project is set up with `pyproject.toml` and `uv.lock`. You will need two terminal windows to run the agent and the server simultaneously.

### 1. Start the MCP Server
In the first terminal, launch the server that handles the Manim engine:
```bash
uv run start_mcp_server.py
```

### 2. Run the Agent
In a second terminal, launch the client application to start chatting with the agent:

```bash
uv run app.py
```

---

## 📃 License
This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.

## Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [DanielPuentee](https://github.com/DanielPuentee)
- **Source:** [DanielPuentee/strands-agents-manim](https://github.com/DanielPuentee/strands-agents-manim)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** yes
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/mcp-danielpuentee-strands-agents-manim
- Seller: https://agentstack.voostack.com/s/danielpuentee
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.