Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ckorhonen/claude-skillsnpx agentmods add skills/ckorhonen/claude-skills/mcp-testerWrote 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/skills/ckorhonen/claude-skills/mcp-tester)<a href="https://agentmods.dev/skills/ckorhonen/claude-skills/mcp-tester"><img src="https://agentmods.dev/badge/skills/ckorhonen/claude-skills/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.
<a href="https://agentmods.dev/skills/ckorhonen/claude-skills/mcp-tester"><img src="https://agentmods.dev/badge/skills/ckorhonen/claude-skills/mcp-tester.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 | $0.00080 | $0.05591 |
| Opus 5 | $0.00040 | $0.02795 |
| Sonnet 5 | $0.00016 | $0.01118 |
| Haiku 4.5 | $0.00008 | $0.00559 |
Grade A, and why
mcp-tester scanned grade A with 1 finding 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 12d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X POST http://localhost:3000/mcp \ How it starts
The opening of the file, as written. The whole thing — 768 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Tool Tester
A comprehensive skill for testing and evaluating MCP (Model Context Protocol) server tools available in the current Claude Code session.
When to Use
Use this skill when:
- Auditing MCP server configurations
- Validating tool quality and descriptions
- Generating test cases for MCP tools
- Checking tool naming conventions and parameter efficiency
- Analyzing tool redundancy across servers
- Evaluating response quality and format efficiency
- Debugging MCP integration issues
Prerequisites
MCP servers must be configured in your Claude Code settings. If the user asks to test tools that don't exist, guide them to add the MCP server to their configuration.
Workflow
Execute these phases in order for comprehensive testing:
Phase 1: Discovery
Identify all MCP tools available in the current session.
Steps:
- List all tools with
mcp__prefix - Group by server (namespace before second
__) - Generate inventory table
Output Format:
## Tool Inventory
| Server | Tool Name | Required Params | Optional Params | Description Preview |
|--------|-----------|-----------------|-----------------|---------------------|
| context7 | resolve-library-id | libraryName, query | - | Resolves package to Context7 ID... |
| context7 | query-docs | libraryId, query | - | Retrieves documentation... |
Metrics to Report:
- Total servers: [count]
- Total tools: [count]
- Tools per server breakdown
Phase 2: Quality Analysis
Evaluate each tool's design quality.
Naming Convention Analysis
Check for:
- Kebab-case consistency:
get-usernotgetUserorget_user - Verb-first naming:
create-item,list-users,delete-record - Clarity: Can purpose be understood from name alone?
- Namespace collisions: Similar names across servers
Description Quality Scoring
| Score | Criteria |
|---|---|
| Excellent | Clear purpose, usage context, examples, input/output expectations |
| Good | Clear purpose, some context, basic expectations |
| Fair | Purpose stated but lacking context or examples |
| Poor | Vague, missing, or misleading description |
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.
- 12d ago First seen · 768 lines · 80 tokens per session scan A e646203d8478
mcp-tester is a skill published in the GitHub repository ckorhonen/claude-skills (14 stars, last pushed 2mo ago), licensed MIT. It adds 80 tokens to every session and 5,591 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
llm-as-judge-evaluation
Evaluate LLM outputs using frontier models as judges. Use for pairwise model comparison, quality scoring with custom rubrics, and automated evaluation pipelines. Covers position bias mitigation, statistical significance, and generating preference data for DPO/RLHF.
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
impl-validator
Validate whether an implementation matches its stated goal. Use this skill when a skill or agent wants a second opinion on its own output, when the user says "check this implementation", "validate what you did", "is this correct?", "review the output", or "did you do this right?". Also spawned automatically as a…
setup
Set up or update TDD Guard for the current project. Detects the test framework, installs or updates the matching reporter, and configures or migrates its configuration to match the current specification.
qa
Browser-based QA verification. Launches a real browser, navigates the app, clicks buttons, fills forms, and tests user flows. Works as a standalone skill or as a phase end condition in campaigns. Requires Playwright (optional dependency, graceful skip if not installed).
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.