mcp-manimgl AGENTS.md

mcp-manimgl AGENTS.md is an instructions file for Codex, OpenCode from daedalus/mcp-manimgl. It costs 692 tokens per session, scanned A, original, MIT.

An instruction file for mcp-manimgl, an MCP server that lets AI agents create mathematical animations with Manim OpenGL. It documents development commands, tests, formatting, and code checks.

In plain words
What is it for?
Use it when developing or reviewing mcp-manimgl, including running its Python tests, formatting code, type checks, security scans, and unused-code checks.
Why use it?
It tells contributors how to validate changes across scene management, graphical objects, animations, and integration behavior.

Instructions file for CodexOpenCode

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/daedalus/mcp-manimgl/agents-md
Clone the repo
git clone --depth 1 https://github.com/daedalus/mcp-manimgl

Made for: Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for mcp-manimgl AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/daedalus/mcp-manimgl/agents-md.svg)](https://agentmods.dev/instructions/daedalus/mcp-manimgl/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/daedalus/mcp-manimgl/agents-md"><img src="https://agentmods.dev/badge/instructions/daedalus/mcp-manimgl/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 692 This file is loaded in full into every session.
When invoked 692 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00692 $0.00692
Opus 5 $0.00346 $0.00346
Sonnet 5 $0.00138 $0.00138
Haiku 4.5 $0.00069 $0.00069

Measured 4d ago against content hash e0ab40b63192, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-manimgl AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

AGENTS.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — mcp-manimgl

Overview

MCP server that exposes manimgl (Manim OpenGL) functionality as tools for LLMs. Enables AI agents to create mathematical animations programmatically through MCP tools.

Commands

Command Description
pytest Run test suite
ruff format Format code
prospector --with-tool ruff --with-tool mypy src/ Lint + type check
semgrep --config=auto src/ Security and pattern scanning (install separately: pip install semgrep)
vulture --min-confidence 90 src/ Dead/unused code detection

Development

pip install -e ".[test]"
pytest
ruff format src/ tests/
prospector --with-tool ruff --with-tool mypy src/
pip install semgrep && semgrep --config=auto --severity=ERROR src/  # semgrep not included in [lint] due to mcp version conflict
vulture --min-confidence 90 src/

Testing

Tests cover:

  • Scene manager: init, state, mobject/animation lifecycle, save/restore, script generation
  • Mobject builder: every mobject type, edge cases (unicode, custom positions, uniqueness)
  • Animation builder: every animation type, edge cases (zero time, negative scale, groups)
  • Integration: combined mobject + animation flows

Code Style

  • Format: ruff format
  • Lint + Type check: prospector (ruff check + mypy + pylint)
  • Docstrings: Google style

Release

bumpversion patch  # or minor/major
git tag v<version>
git push && git push --tags

MCP Server

pip install mcp-manimgl

Add to your mcp.json:

{
  "mcpServers": {
    "mcp-manimgl": {
      "command": "mcp-manimgl"
    }
  }
}

Development Server (with Auto-Reload)

During development, start the server with --reload to automatically pick up source changes:

mcp-manimgl --reload

This uses watchfiles to monitor the src/ directory and restarts the server whenever a .py file changes. Install with:

pip install watchfiles

Without --reload, you must restart the server manually after editing source files (e.g., audio_mixer.py, scene_manager.py).

Read the full file on GitHub · 89 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 89 lines · 692 tokens per session scan A e0ab40b63192

Subscribe to this mod's changes

mcp-manimgl AGENTS.md is an instructions file published in the GitHub repository daedalus/mcp-manimgl (0 stars, last pushed 3mo ago), licensed MIT. It adds 692 tokens to every session, about $0.0035 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.