mcp-testing

mcp-testing is a skill for Claude Code, Codex from adeze/raindrop-mcp. It costs 17 tokens per session (1,531 once invoked), scanned A, original, MIT.

A testing guide for Model Context Protocol servers using Vitest, the MCP Inspector, and integration tests. Model Context Protocol is a standard way for AI applications to connect to tools and data.

In plain words
What is it for?
Use it to test MCP server tools, connect a test client through an in-memory transport, list available tools, and write TypeScript tests with Vitest. TypeScript is a programming language commonly used for JavaScript applications.
Why use it?
It provides a way to check both individual pieces and the complete connection between an MCP client and server before relying on them.

Skill for Claude CodeCodex

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 skills/adeze/raindrop-mcp/mcp-testing
Any agent
npx skills add adeze/raindrop-mcp --skill mcp-testing
Clone the repo
git clone --depth 1 https://github.com/adeze/raindrop-mcp

Made for: Claude Code, Codex.

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-testing

README.md
[![agentmods](https://agentmods.dev/badge/skills/adeze/raindrop-mcp/mcp-testing.svg)](https://agentmods.dev/skills/adeze/raindrop-mcp/mcp-testing)
Your own site
<a href="https://agentmods.dev/skills/adeze/raindrop-mcp/mcp-testing"><img src="https://agentmods.dev/badge/skills/adeze/raindrop-mcp/mcp-testing.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,531 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00017 $0.01531
Opus 5 $0.00009 $0.00766
Sonnet 5 $0.00003 $0.00306
Haiku 4.5 $0.00002 $0.00153

Measured 5d ago against content hash 5c1fd6b0b4fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-testing 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 5d 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/skills/mcp-testing/SKILL.md · 245 lines

How it starts

The opening of the file, as written. The whole thing — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Testing Skill

Modern testing strategies for Model Context Protocol (MCP) servers developed in VS Code using TypeScript, Bun, and Vitest.

Unit Testing with Vitest & In-Memory Transport

Setup Minimal Test Environment

import { describe, it, expect, beforeEach } from "vitest";
import { Client } from "@modelcontextprotocol/sdk/client/index.js";
import { InMemoryTransport } from "@modelcontextprotocol/sdk/testing/inMemoryTransport.js";
import { RaindropMCPService } from "../src/services/raindropmcp.service.js";

describe("RaindropMCPService Tools", () => {
  let service: RaindropMCPService;
  let transport: InMemoryTransport;
  let client: Client;

  beforeEach(async () => {
    service = new RaindropMCPService();
    transport = new InMemoryTransport(service.getServer());
    client = new Client(
      {
        name: "test-client",
        version: "1.0.0",
      },
      { capabilities: {} },
    );
    await client.connect(transport);
  });

  it("should list available tools", async () => {
    const tools = await client.listTools();
    expect(tools.tools.length).toBeGreaterThan(0);
    expect(tools.tools.map((t) => t.name)).toContain("collection_list");
  });

  it("should call a tool with valid input", async () => {
    const result = await client.callTool({
      name: "collection_list",
      arguments: {},
    });
    expect(result).toBeDefined();
    expect(result.content).toBeDefined();
  });
});

Key Testing Patterns

  1. In-Memory Transport: Use for unit tests—no subprocess overhead, direct method invocation
  2. Server Capabilities: Verify manifest before running tool tests
  3. Mock Context: Provide mock RaindropService for isolated tool testing
  4. Error Handling: Test both success and error paths with Zod validation

Integration Testing with MCP Inspector

Launch Inspector in VS Code

  1. Terminal > Run Task > "Debug HTTP Server with Inspector" (or STDIO variant)
    • Opens Inspector at http://localhost:3000 (or via auto-opened browser)
    • Live tool/resource exploration with bidirectional message capture

Read the full file on GitHub · 245 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. 5d ago First seen · 245 lines · 17 tokens per session scan A 5c1fd6b0b4fd

Subscribe to this mod's changes

mcp-testing is a skill published in the GitHub repository adeze/raindrop-mcp (183 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 1,531 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

test-generator

Generate comprehensive unit, integration, and end-to-end tests. Use when adding test coverage, writing tests for new features, or improving existing test suites.

asgarovf/locusai · 33 tokens

testing-strategies

Use when writing tests, setting up test frameworks, implementing mocking strategies, or establishing testing best practices (unit, integration, E2E) across any technology stack.

MadAppGang/claude-code · 38 tokens

qa-use

E2E testing and browser automation with qa-use CLI. Use when the user needs to run tests, verify features, automate browser interactions, or debug test failures.

desplega-ai/qa-use · 36 tokens

testing-expert

Expert-level software testing with unit tests, integration tests, E2E tests, TDD/BDD, and testing best practices.

personamanagmentlayer/pcl · 29 tokens

harness-test-writer

Add regression test cases to the Bifrost provider harness (the Postman collection run via make run-provider-harness-test) based on a merged PR or a GitHub issue. Fetches the PR/issue, traces the affected wire path in the codebase, checks existing harness coverage, designs cases following harness conventions, inserts…

maximhq/bifrost · 133 tokens

setup-agent-replay

Set up a local agent replay server for Raindrop Workshop. Use when the user wants Workshop to replay a captured trace against their real local agent code and tools. Creates/updates .raindrop/agents.yaml, scaffolds a language-appropriate replay server, registers the project with raindrop replay register, and verifies…

raindrop-ai/workshop · 74 tokens