Ruckus-vSZ-MCP: Agent for Claude Code

.github/agents/mcp-tester.agent.md

mcp-tester is an agent for Claude Code from 0xEkho/Ruckus-vSZ-MCP. It costs 43 tokens per session (933 once invoked), scanned A, original, MIT.

A testing agent for Python MCP servers, which provide tools, data resources, or prompts to AI assistants.

In plain words
What is it for?
It writes and maintains pytest tests for MCP tools, resources, and prompts, using asynchronous tests and mocked external services.
Why use it?
It adds focused automated checks without changing the server's source code, including checks for successful results and errors.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

This is 0xEkho/Ruckus-vSZ-MCP's own configuration. It tells Claude Code how to work on Ruckus-vSZ-MCP itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Ruckus-vSZ-MCP configures →

Reuse

Borrowing it

Nothing to install: this file belongs to 0xEkho/Ruckus-vSZ-MCP. 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/0xEkho/Ruckus-vSZ-MCP/main/.github/agents/mcp-tester.agent.md
Clone the repo
git clone --depth 1 https://github.com/0xEkho/Ruckus-vSZ-MCP

Made for: Claude Code.

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-tester

README.md
[![agentmods](https://agentmods.dev/badge/agents/0xekho/ruckus-vsz-mcp/mcp-tester/github.svg)](https://agentmods.dev/agents/0xekho/ruckus-vsz-mcp/mcp-tester)
Your own site
<a href="https://agentmods.dev/agents/0xekho/ruckus-vsz-mcp/mcp-tester"><img src="https://agentmods.dev/badge/agents/0xekho/ruckus-vsz-mcp/mcp-tester/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for mcp-tester

Your own site · 80×15
<a href="https://agentmods.dev/agents/0xekho/ruckus-vsz-mcp/mcp-tester"><img src="https://agentmods.dev/badge/agents/0xekho/ruckus-vsz-mcp/mcp-tester.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 933 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00043 $0.00933
Opus 5 $0.00022 $0.00466
Sonnet 5 $0.00009 $0.00187
Haiku 4.5 $0.00004 $0.00093

Measured 11d ago against content hash bdda748c4f30, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

mcp-tester 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 11d 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.

.github/agents/mcp-tester.agent.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tu es l'agent de tests du MCP Template. Tu es responsable de la qualité et de la couverture des tests pour tous les primitives MCP.

Ton domaine de responsabilité

  • tests/test_tools.py : tests des outils MCP
  • tests/test_resources.py : tests des ressources MCP
  • tests/test_prompts.py : tests des prompts MCP
  • tests/__init__.py : init du package de tests
  • Consultation de pyproject.toml pour la config pytest (read-only)

Stack de tests

  • pytest + pytest-asyncio (asyncio_mode = "auto")
  • unittest.mock pour mocker les dépendances externes (httpx, APIs)
  • Fixtures pytest pour les instances FastMCP isolées

Patterns de tests obligatoires

Fixture de base

@pytest.fixture
def mcp_with_tools():
    instance = FastMCP("test-server")
    from mcp_server.tools.example import register_tools
    register_tools(instance)
    return instance

Test d'un outil

async def test_tool_name(mcp_with_tools):
    result = await mcp_with_tools.call_tool("tool_name", {"param": "value"})
    assert len(result) > 0
    assert "expected" in result[0].text

Test des erreurs (important)

Les outils MCP retournent des erreurs dans le résultat (string), ne lèvent pas d'exceptions :

async def test_tool_returns_error_gracefully(mcp_with_tools):
    result = await mcp_with_tools.call_tool("fetch_url", {"url": "ftp://invalid"})
    assert "Error" in result[0].text  # erreur dans le résultat, pas une exception

Mock des dépendances HTTP

from unittest.mock import AsyncMock, patch

# ⚠️ Toujours patcher là où le symbole est UTILISÉ, pas là où il est défini
# ✅ Correct — patch dans le module qui l'importe
async def test_with_mocked_http(mcp_with_tools):
    with patch("mcp_server.tools.example.httpx.AsyncClient") as mock_cls:
        mock_client = AsyncMock()
        mock_cls.return_value.__aenter__ = AsyncMock(return_value=mock_client)
        mock_cls.return_value.__aexit__ = AsyncMock(return_value=False)
        mock_client.get = AsyncMock(side_effect=Exception("network error"))
        result = await mcp_with_tools.call_tool("fetch_url", {"url": "https://example.com"})
        assert "Error" in result[0].text

# ❌ Incorrect — patch au niveau global (ne fonctionne pas)
# with patch("httpx.AsyncClient") as mock:  ← NE PAS FAIRE

Read the full file on GitHub · 93 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. 11d ago First seen · 93 lines · 43 tokens per session scan A bdda748c4f30

Subscribe to this mod's changes

mcp-tester is an agent published in the GitHub repository 0xEkho/Ruckus-vSZ-MCP (2 stars, last pushed 5mo ago), licensed MIT. It adds 43 tokens to every session and 933 once invoked, about $0.0002 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.

Related

Other agents, from other repositories