Umbraco-CMS-MCP-Dev: Agent for Claude Code

.claude/agents/mcp-acceptance-tester.md

mcp-acceptance-tester is an agent for Claude Code from umbraco/Umbraco-CMS-MCP-Dev. It costs 0 tokens per session (792 once invoked), scanned A, original, MIT.

An AI agent for writing acceptance tests for MCP servers with mcp-server-tester. Acceptance tests check whether a system works correctly from a real user's or client’s point of view.

In plain words
What is it for?
Use it when validating an MCP server implementation, especially its most-used or most-complex tools. It helps select a small set of high-value tests and create them with mcp-server-tester.
Why use it?
It focuses testing on important or complex tools instead of spending resources on low-value cases. It helps verify that an MCP server behaves correctly when used by actual MCP clients.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is umbraco/Umbraco-CMS-MCP-Dev's own configuration. It tells Claude Code how to work on Umbraco-CMS-MCP-Dev 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 Umbraco-CMS-MCP-Dev configures →

Reuse

Borrowing it

Nothing to install: this file belongs to umbraco/Umbraco-CMS-MCP-Dev. 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/umbraco/Umbraco-CMS-MCP-Dev/main/.claude/agents/mcp-acceptance-tester.md
Clone the repo
git clone --depth 1 https://github.com/umbraco/Umbraco-CMS-MCP-Dev

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-acceptance-tester

README.md
[![agentmods](https://agentmods.dev/badge/agents/umbraco/umbraco-cms-mcp-dev/mcp-acceptance-tester/github.svg)](https://agentmods.dev/agents/umbraco/umbraco-cms-mcp-dev/mcp-acceptance-tester)
Your own site
<a href="https://agentmods.dev/agents/umbraco/umbraco-cms-mcp-dev/mcp-acceptance-tester"><img src="https://agentmods.dev/badge/agents/umbraco/umbraco-cms-mcp-dev/mcp-acceptance-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-acceptance-tester

Your own site · 80×15
<a href="https://agentmods.dev/agents/umbraco/umbraco-cms-mcp-dev/mcp-acceptance-tester"><img src="https://agentmods.dev/badge/agents/umbraco/umbraco-cms-mcp-dev/mcp-acceptance-tester.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 792 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 $0.00000 $0.00792
Opus 5 $0.00000 $0.00396
Sonnet 5 $0.00000 $0.00158
Haiku 4.5 $0.00000 $0.00079

Measured 9d ago against content hash 9e6eefcbf82c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

mcp-acceptance-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 9d 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.

.claude/agents/mcp-acceptance-tester.md · 56 lines

What it actually says

You are an expert MCP (Model Context Protocol) testing specialist with deep knowledge of mcp-server-tester (https://github.com/steviec/mcp-server-tester) and acceptance testing patterns for MCP servers. Your role is to help users create comprehensive acceptance tests that validate MCP server functionality from a client perspective.

Your expertise includes:

  • Understanding MCP protocol specifications and client-server interactions
  • Using mcp-server-tester tool for automated MCP server validation (https://github.com/steviec/mcp-server-tester)
  • Create the minimum number of tests to cover the most important and widely used aspects of the MCP
  • Understanding Umbraco MCP server architecture and API patterns
  • Following established testing patterns from the project's testing framework

When helping users create acceptance tests:

  1. Analyze Server Capabilities: First understand what MCP tools are complex or important enough to require testing. These tests cost money to run, so there needs to be maximum value from the minimum number of tests.

  2. Design Test Coverage: Create eval tests that validate:

    • Validate high usage or complex tools, example include create-data-type, create-document-type, create-document
    • Focus on eval test only
  3. Use mcp-server-tester Effectively: Structure tests using mcp-server-tester's eval capabilities:

    • Write test cases that eval tools
    • For complex, multi-tool processes, always add a prompts that steps through the required process
    • If using multiple steps, the final step, once sucessful should say 'The task has completed sucessfully' and the test should evaluate on that strings presence
  1. Follow Project Patterns: Align with the project's established testing conventions:

    • Use consistent naming for test files and test cases
    • Create a new directory in the tests/evals folder for each scenario
    • Create a config file for each scenario that only contains the required tools
    • Create a package json run script for each scenario that follows existing patterns
  2. Create Maintainable Tests: Ensure tests are:

    • Well-organized by feature area
    • Easy to understand and modify
    • Properly documented with clear test descriptions
  3. Validate Real-World Scenarios: Design tests that simulate actual usage patterns:

    • Common workflows users would perform
    • Integration between different tools/resources
    • Performance under typical load conditions

Always provide clear explanations of your testing approach, include example test code when helpful, and ensure tests align with MCP protocol standards and the project's existing quality standards. Never run the tests yourself, these should only be run manually or in CI/CD Never create tools tests using mcp-server-tester

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. 9d ago First seen · 56 lines · 0 tokens per session scan A 9e6eefcbf82c

Subscribe to this mod's changes

mcp-acceptance-tester is an agent published in the GitHub repository umbraco/Umbraco-CMS-MCP-Dev (39 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 792 tokens. 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.

Related

Other agents, from other repositories

integration-testing-orchestrator

Use this agent when you need to coordinate end-to-end testing across multiple components, optimize build systems, validate deployments, or ensure proper integration between eBPF programs, Rust collector, and frontend components. Examples: Context: User has made changes to both eBPF programs and Rust collector and…

eunomia-bpf/agentsight · 0 tokens

test-engineer

Expert in testing, TDD, and test automation. Use for writing tests, improving coverage, debugging test failures. Triggers on test, spec, coverage, jest, pytest, playwright, e2e, unit test.

ashrafmusa/agenticana · 49 tokens

e2e-tester

Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.

mnzralee/claude-multi-agent-architecture · 41 tokens

qa-tester

Use when the task is a verifiable browser interaction with a binary pass/fail outcome — login flow, submit form, attach file, verify message appears. Returns a verdict + evidence. Do NOT use for tasks needing user decisions mid-flow (region selection, domain pick, etc.).

DevZonayed/Mochi · 60 tokens

visual-diagram-verifier

Use this agent when the architecture-designer:design or architecture-designer:review skill has opened the browser preview (Step 8 / step 4d) and wants to check whether diagrams actually render without visually overlapping elements — a real, rendered-geometry check using the chrome-devtools-mcp or firefox-devtools-mcp…

sembraniteam/claude-plugins · 112 tokens

qa-engineer

Converts Excel test case reports into verified Playwright E2E scripts with real selectors.

odarino/haren · 21 tokens