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.
npx agentmods add instructions/hansur94/matlab-mcp-server-python/claude-mdgit clone --depth 1 https://github.com/HanSur94/matlab-mcp-server-pythonWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.04228 | $0.04228 |
| Opus 5 | $0.02114 | $0.02114 |
| Sonnet 5 | $0.00846 | $0.00846 |
| Haiku 4.5 | $0.00423 | $0.00423 |
Grade A, and why
matlab-mcp-server-python CLAUDE.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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project
MATLAB MCP Server — v2.0 Milestone
A Python-based MCP server that lets AI coding agents (Claude Code, Codex CLI, etc.) execute MATLAB code, inspect workspaces, manage files, and monitor server health. It bridges the Model Context Protocol to MATLAB's Engine API with elastic pooling, session isolation, and async job orchestration.
Core Value: Any MCP-compatible coding agent can connect to MATLAB and run code securely — with minimal setup, proper authentication, and production-grade reliability.
Constraints
- Tech stack: Python 3.10+, must keep backward compat with existing config.yaml format
- Platform: Must work on Windows 10 without admin rights (no service installation, no elevated ports)
- Dependency: FastMCP 3.0 migration must not break existing stdio/SSE clients
- MATLAB: Requires MATLAB R2022b+ with Engine API — this is an external user dependency
Technology Stack
Languages
- Python 3.10+ - Core application language, enforced via
pyproject.toml - MATLAB R2022b+ - Target runtime for code execution (via MATLAB Engine API)
- JavaScript/TypeScript - Dashboard frontend (static HTML/CSS/JS in monitoring UI)
Runtime
- Python 3.10, 3.11, 3.12 - Supported versions per
pyproject.toml - MATLAB Engine API for Python - Bridge to MATLAB execution (imported at
src/matlab_mcp/pool/engine.py) - pip - Python dependency management
- Lockfile:
requirements-lock.txt(pinned versions) - Build backend: hatchling (via
[build-system]inpyproject.toml)
Frameworks
- FastMCP 3.4.4 - MCP server framework (
fastmcp>=3.4.4,<4.0.0in dependencies) - Starlette 0.52.1 - Web framework for HTTP monitoring dashboard (
src/matlab_mcp/monitoring/dashboard.py) - Uvicorn 0.42.0 - ASGI server for HTTP transport and dashboard
- Model Context Protocol (MCP 1.26.0) - Protocol implementation
- Pydantic 2.12.5 - Configuration validation and data models (
src/matlab_mcp/config.py) - PyYAML 6.0.3 - Configuration file parsing (YAML format)
- aiosqlite 0.22.1 - Async SQLite for metrics persistence (
src/matlab_mcp/monitoring/store.py) - Plotly 6.6.0 - Interactive plot generation and JSON export (
src/matlab_mcp/output/plotly_convert.py) - Pillow 12.1.1 - Image processing for thumbnails (
src/matlab_mcp/output/thumbnail.py) - sse-starlette 3.3.3 - Server-sent events for multi-user SSE transport
- websockets 16.0 - WebSocket support
- pytest 7.0+ - Test runner
- pytest-asyncio 0.21+ - Async test support
- pytest-cov 4.0+ - Coverage reporting
- ruff 0.1.0+ - Code linting and formatting
- pip-audit 2.6.0+ - Security vulnerability scanning
- build 1.0.0+ - Python package builder
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.
- 2d ago First seen · 296 lines · 4,228 tokens per session scan A 5142fb660891
matlab-mcp-server-python CLAUDE.md is an instructions file published in the GitHub repository HanSur94/matlab-mcp-server-python (5 stars, last pushed 1mo ago), licensed MIT. It adds 4,228 tokens to every session, about $0.0211 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.
Other instructions, from other repositories
ironcurtain CLAUDE.md
Instructions for provos/ironcurtain, covering claude.md, general workflow, git & worktrees, git workflow and platform considerations.
ironcurtain copilot-instructions.md
Instructions for provos/ironcurtain, covering ironcurtain copilot review instructions, platform support, security invariants, ai sdk v6 api (breaking changes) and code conventions.
ironcurtain security-boundary.instructions.md
Instructions for provos/ironcurtain, covering security boundary review rules, mandatory checks and structural invariant order.
ironcurtain sandbox.instructions.md
Instructions for provos/ironcurtain, covering sandbox review rules and mandatory checks.
ironcurtain types.instructions.md
Instructions for provos/ironcurtain, covering types review rules and mandatory checks.
ironcurtain pipeline.instructions.md
Instructions for provos/ironcurtain, covering pipeline review rules and mandatory checks.