agentmods.dev

mcp-zenml AGENTS.md

mcp-zenml AGENTS.md is an instructions file for Codex, OpenCode from zenml-io/mcp-zenml. It costs 694 tokens per session, scanned A, original, MIT.

A repository instruction document for the mcp-zenml project, covering its Python structure, development commands, coding style, and tests.

In plain words
What is it for?
Use it when working on the ZenML MCP server, especially to find entry points, run it locally, format code, and execute smoke or unit tests.
Why use it?
It gives contributors the project-specific rules needed to make compatible changes and run the right checks.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

not rated 49 11d ago A scan 694 tokens original MIT
View the source file zenml-io/mcp-zenml zenml.io
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/zenml-io/mcp-zenml/agents-md
Clone the repo
git clone --depth 1 https://github.com/zenml-io/mcp-zenml

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-zenml AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/zenml-io/mcp-zenml/agents-md.svg)](https://agentmods.dev/instructions/zenml-io/mcp-zenml/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/zenml-io/mcp-zenml/agents-md"><img src="https://agentmods.dev/badge/instructions/zenml-io/mcp-zenml/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 694 This file is loaded in full into every session.
When invoked 694 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 5.1 $0.00694 $0.00694
Opus 5 $0.00347 $0.00347
Sonnet 5 $0.00139 $0.00139
Haiku 4.5 $0.00069 $0.00069

Measured 6d ago against content hash 24cd032567b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

mcp-zenml 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 6d 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 · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Project Structure & Module Organization

  • server/ – MCP server implementation. Main entry: server/zenml_server.py; analytics: server/zenml_mcp_analytics.py; treat server/lib/ as vendored support code (avoid edits unless necessary).
  • scripts/ – Developer utilities: format.sh (ruff), test_mcp_server.py (smoke test), test_analytics.py (analytics diagnostics), test_datetime_normalization.py (unit tests).
  • assets/ – Images and static assets.
  • Root files – README.md, manifest.json, mcp-zenml.mcpb (MCP bundle), CI in .github/workflows/.

Build, Test, and Development Commands

  • Run server locally: uv run server/zenml_server.py
  • Smoke test (local): uv run scripts/test_mcp_server.py server/zenml_server.py
  • Unit tests (local): uv run scripts/test_datetime_normalization.py
  • Format & lint: bash scripts/format.sh (ruff check + import sort + format)
  • CI mirrors the smoke test via GitHub Actions and requires Python 3.12.

Coding Style & Naming Conventions

  • Language: Python 3.12+. Indentation: 4 spaces.
  • Use snake_case for functions/variables, PascalCase for classes, UPPER_SNAKE_CASE for constants.
  • Keep imports tidy; scripts/format.sh enforces ruff rules and import sorting.
  • Logging: prefer logging to stderr; avoid printing from MCP tool functions except returning strings/JSON. Keep logs minimal to avoid MCP JSON protocol interference.

Testing Guidelines

  • Primary test: scripts/test_mcp_server.py exercises MCP connection, initialization, and basic tools.
  • Unit tests: scripts/test_datetime_normalization.py tests datetime filter normalization and exception classification (no credentials needed).
  • Analytics tests: scripts/test_analytics.py tests the analytics pipeline.
  • Run locally with uv run scripts/<test_script>.py; CI runs on PRs and a scheduled workflow.
  • When adding new test scripts, always wire them into .github/workflows/pr-test.yml so they run in CI. Tests that don't need ZenML credentials should run unconditionally.
  • Follow descriptive names (e.g., test_<area>_behavior.py) and place under scripts/. Keep tests fast and network-light; mock ZenML calls when feasible.

Read the full file on GitHub · 40 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. 6d ago First seen · 40 lines · 694 tokens per session scan A 24cd032567b2

Subscribe to this mod's changes

mcp-zenml AGENTS.md is an instructions file published in the GitHub repository zenml-io/mcp-zenml (49 stars, last pushed 11d ago), licensed MIT. It adds 694 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 2026-08-30.

MLOpsllmopsmcpmcp-server
Related

Other instructions, from other repositories

unified-ai-system AGENTS.md

AGENTS.md instructions for happy520ai/unified-ai-system, covering repository guidance, ownership, language and module policy, public repository rules and safety.

happy520ai/unified-ai-system · 602 tokens

mcp-router CLAUDE.md

Claude Code instructions for mcp-router/mcp-router, a project described as: A Unified MCP Server Management App (MCP Manager).

mcp-router/mcp-router · 515 tokens

portkey-admin-mcp AGENTS.md

AGENTS.md instructions for CodesWhat/portkey-admin-mcp, covering agent instructions and code review.

CodesWhat/portkey-admin-mcp · 71 tokens

clearml-mcp CLAUDE.md

Instructions for prassanna-ravishankar/clearml-mcp, covering clearml mcp server, project overview, available tools, task operations and model operations.

prassanna-ravishankar/clearml-mcp · 780 tokens

blockrun-mcp AGENTS.md

AGENTS.md instructions for BlockRunAI/blockrun-mcp, covering blockrun mcp, commands, project structure, key dependencies and install in codex.

BlockRunAI/blockrun-mcp · 282 tokens

openrouter-mcp-multimodal AGENTS.md

AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).

stabgan/openrouter-mcp-multimodal · 793 tokens