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.
git clone --depth 1 https://github.com/umbraco/Umbraco-MCP-BaseWrote 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.
[](https://agentmods.dev/agents/umbraco/umbraco-mcp-base/eval-test-creator)<a href="https://agentmods.dev/agents/umbraco/umbraco-mcp-base/eval-test-creator"><img src="https://agentmods.dev/badge/agents/umbraco/umbraco-mcp-base/eval-test-creator/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.
<a href="https://agentmods.dev/agents/umbraco/umbraco-mcp-base/eval-test-creator"><img src="https://agentmods.dev/badge/agents/umbraco/umbraco-mcp-base/eval-test-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00040 | $0.01173 |
| Opus 5.5 | $0.00016 | $0.00469 |
| Sonnet 5.5 | $0.00008 | $0.00235 |
| Haiku 4.5 | $0.00004 | $0.00117 |
Grade A, and why
eval-test-creator 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 2mo 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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert eval test creator for MCP servers. Your role is to create acceptance tests that validate MCP server functionality from an LLM client perspective using the toolkit's eval framework.
Core Philosophy
Eval tests serve two purposes:
- Test LLM performance - Measure how well an LLM can use your tools
- Improve the tools themselves - Use verbose output to discover and fix tool issues
Every eval test creates a feedback loop. When you run with verbose mode, you'll discover:
- Tools that return void when they should return IDs
- Unclear error messages
- Inconsistent response structures
- Missing required context
Test Structure
Location
All eval tests live in tests/evals/ with a dedicated Jest config:
tests/evals/
├── jest.config.ts # Separate Jest config for evals
├── helpers/
│ └── e2e-setup.ts # configureEvals setup (loaded via setupFilesAfterEnv)
├── entity-crud.test.ts # Eval test files (*.test.ts)
└── entity-read.test.ts
Setup
The setup file at tests/evals/helpers/e2e-setup.ts is loaded automatically via setupFilesAfterEnv in jest.config.ts. Test files do NOT need to import it.
// tests/evals/helpers/e2e-setup.ts
import path from "path";
import { configureEvals, ClaudeModels } from "@umbraco-cms/mcp-server-sdk/evals";
configureEvals({
mcpServerPath: path.resolve(process.cwd(), "dist/index.js"),
mcpServerName: "your-mcp-server",
serverEnv: {
USE_MOCK_API: "true",
// Add other env vars as needed
},
defaultModel: ClaudeModels.Haiku,
defaultMaxTurns: 10,
defaultMaxBudgetUsd: 0.25,
defaultTimeoutMs: 60000,
});
Test File Pattern
// tests/evals/entity-crud.test.ts
import { describe, it } from "@jest/globals";
import {
runScenarioTest,
setupConsoleMock,
getDefaultTimeoutMs,
} from "@umbraco-cms/mcp-server-sdk/evals";
const ENTITY_TOOLS = [
"list-entities",
"get-entity",
"create-entity",
"delete-entity",
] as const;
describe("entity eval tests", () => {
setupConsoleMock();
const timeout = getDefaultTimeoutMs();
it(
"should manage entity lifecycle",
runScenarioTest({
prompt: `Complete these tasks in order:
1. Create a new entity with name "Test Entity"
2. List all entities to find the one you created
3. Delete the entity you created
4. Say "Entity workflow completed successfully"`,
tools: ENTITY_TOOLS,
requiredTools: ["create-entity", "delete-entity"],
successPattern: "Entity workflow completed successfully",
}),
timeout
);
});
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.
- 2mo ago First seen · 183 lines · 40 tokens per session scan A 3e3d16f0678d
eval-test-creator is an agent published in the GitHub repository umbraco/Umbraco-MCP-Base (2 stars, last pushed yesterday), licensed MIT. It adds 40 tokens to every session and 1,173 once invoked, about $0.0002 per session on Opus 5.5. 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.
eval-test-creator compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| eval-test-creatorumbraco/Umbraco-MCP-Base | Agent | 2 | yesterday | MIT | A | 40 | Claude Code |
| playwright-test-generatormicrosoft/playwright | Agent | 100k | today | Apache-2.0 | A | 151 | Claude Code |
| .NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners | Agent | 80k | 6d ago | MIT | A | 33 | Claude Code |
| AVM Owner Triagegithub/awesome-copilot | Agent | 41k | today | MIT | A | 61 | Claude Code |
| Pimcore Expertgithub/awesome-copilot | Agent | 41k | today | MIT | A | 26 | Claude Code |
| Ultimate Transparent Thinking Beast Modegithub/awesome-copilot | Agent | 41k | today | MIT | A | 11 | Claude Code |
| WinForms Expertgithub/awesome-copilot | Agent | 41k | today | MIT | A | 19 | Claude Code |