No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by abhiemj · MCP Server · ★ 644
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is manim-mcp-server safe to install? View the security audit →
Manim MCP Server Overview This is an MCP (Model Context Protocol) server that executes Manim animation code and returns the generated video. It allows users to send Manim scripts and receive the rendered animation. Features Executes Manim Python scripts. Saves animation output in a visible media folder. Allows users to clean up temporary files after execution. Portable and configurable via environment variables. Installation Prerequisites Ensure you have the following installed: Python 3.8+ Manim (Community Version) MCP Install Manim Install MCP Clone the Repository Integration with Claude To integrate the Manim MCP server with Claude, add the following to your file: Finding Your Python Path To find your Python executable path, use the following command: Windows (PowerShell): Windows (Command Prompt/Terminal): Lin
| Stars | 644 |
| Forks | 90 |
| Language | Python |
| Category | MCP Server |
| License | MIT |
| Quality Score | 64.7919803719086/100 |
| Open Issues | 13 |
| Last Updated | 2025-05-19 |
| Created | 2025-03-31 |
| Platforms | mcp, python |
| Est. Tokens | ~23k |
These tools work well together with manim-mcp-server for enhanced workflows:
Explore other popular mcp server tools:
manim-mcp-server is an open-source mcp server by abhiemj with 644 GitHub stars.
manim-mcp-server is primarily written in Python.
You can find installation instructions and usage details in the manim-mcp-server GitHub repository at github.com/abhiemj/manim-mcp-server. The project has 644 stars and 90 forks, indicating an active community.
manim-mcp-server is released under the MIT license, making it free to use and modify according to the license terms.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: