What is testzeus-mcp-server AGENTS.md?

Repository instructions for AI coding agents working on testzeus-mcp-server, a Python server that makes TestZeus software available to MCP clients such as Claude Desktop and Cursor.

Use it when changing testzeus-mcp-server, especially when installing dependencies, formatting code, running tests, checking lint, building the package, or starting the server.

It gives agents the project’s build, testing, formatting, linting, architecture, and coding conventions so changes fit the repository and pass its checks.

How test-zeus-ai/testzeus-mcp-server configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to test-zeus-ai/testzeus-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/test-zeus-ai/testzeus-mcp-server/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/test-zeus-ai/testzeus-mcp-server

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/test-zeus-ai/testzeus-mcp-server/agents-md.svg)](https://agentmods.dev/instructions/test-zeus-ai/testzeus-mcp-server/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/test-zeus-ai/testzeus-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/test-zeus-ai/testzeus-mcp-server/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 686 This file is loaded in full into every session.

When invoked 686 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00686	$0.00686
Opus 5	$0.00343	$0.00343
Sonnet 5	$0.00137	$0.00137
Haiku 4.5	$0.00069	$0.00069

Measured 7d ago against content hash 8df226a802ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

testzeus-mcp-server 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 7d 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 · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — testzeus-mcp-server

Guidance for AI coding agents working in this repository. Provider-agnostic: any agent (Claude Code, Cursor, etc.) should read this before making changes.

What this project is

testzeus-mcp-server is a FastMCP server that exposes TestZeus SDK functionality to MCP clients (Claude Desktop, Cursor, and other MCP hosts). It wraps testzeus-sdk and surfaces its capabilities as MCP tools. The console entry point is testzeus-mcp-server (testzeus_mcp_server.__main__:main).

Build, test, and lint

Uses uv (not Poetry). Python >=3.11,<4.0.

make dev-install   # uv sync --dev
make fmt           # uv run ruff format (testzeus_mcp_server/, tests/)
make lint          # uv run ruff check --fix
make test          # ruff + uv run pytest (--maxfail=1)
make run           # uv run testzeus-mcp-server

Formatter/linter is ruff, line length 100 (not 200 like the SDK/CLI). Run make fmt before committing.
CI (.github/workflows/ci.yml) has three blocking gates: ruff check, ruff format --check, and uv build ("Check build" — a broken build fails CI). pytest is non-blocking (|| echo).
make lint is not read-only and does not match CI: lint: fmt, so it runs ruff format then ruff check --fix — both mutate the tree, and the --fix auto-repairs lints. CI runs plain ruff check (no --fix), so an unfixable lint passes locally but fails CI. After make lint, double-check with a plain uv run ruff check before pushing. (make test chains test: lint, so it reformats too.)
Keep the testzeus-sdk dependency floor high enough that a stale SDK missing a needed capability can't satisfy the install.

Architecture

testzeus_mcp_server/ — the server package. Tools are registered on the FastMCP server; each tool prepares a TestZeus client, calls the SDK, and returns a JSON-serializable result.
Tools mirror SDK capabilities. When adding tools for a new SDK area, follow an existing group (e.g. the agent-harness / *_adversary_* tools) as the template, and keep long return payloads within the 100-char line limit (extract payload = json.dumps(...) into a variable rather than inlining).

Read the full file on GitHub · 56 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.

7d ago First seen · 56 lines · 686 tokens per session scan A 8df226a802ce

Subscribe to this mod's changes

testzeus-mcp-server AGENTS.md is an instructions file published in the GitHub repository test-zeus-ai/testzeus-mcp-server (2 stars, last pushed 6d ago), licensed MIT. It adds 686 tokens to every session, about $0.0034 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.

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

testzeus-mcp-server: Instructions file for Codex