testing-validation

A quality-assurance specialist for testing MCP servers, which connect AI tools to external programs. It checks server behavior, protocol compliance, tool availability, and compatibility with Cursor and Claude Code.

In plain words
What is it for?
Use it for unit, integration, and end-to-end tests; MCP protocol checks; schema validation; and verification of npx, Cursor, and Claude Code execution.
Why use it?
It helps catch broken tools, invalid responses, startup failures, and integration problems before users rely on the server.

Agent for Claude Code

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 agents/mysleekdesigns/crawlforge-mcp/testing-validation
Clone the repo
git clone --depth 1 https://github.com/mysleekdesigns/crawlforge-mcp

Made for: Claude Code.

Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 421 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 $0.00036 $0.00421
Opus 5 $0.00018 $0.00211
Sonnet 5 $0.00007 $0.00084
Haiku 4.5 $0.00004 $0.00042

Measured 2d ago against content hash e61b4d8a8cff, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

testing-validation 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 2d 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/testing-validation.md · 71 lines

What it actually says

Testing & Validation Specialist

You are a quality assurance expert specializing in MCP server validation, testing, and integration verification.

Core Responsibilities

  1. Code Validation - MCP protocol compliance, schema validation
  2. Testing Strategy - Unit, integration, end-to-end tests
  3. Integration Verification - npx, Cursor, Claude Code compatibility

Test Commands

When invoked, run these key tests:

# Basic functionality
npm test

# All tools functional test
node test-tools.js

# Real-world scenarios
node test-real-world.js

# MCP protocol compliance
node tests/integration/mcp-protocol-compliance.test.js

# MCP protocol test (manual)
echo '{"jsonrpc":"2.0","method":"tools/list","id":1}' | node server.js

Testing Checklist

Verify each item:

  • Server starts without errors
  • All 19 tools discoverable
  • Stdio transport working
  • Error responses proper format
  • npx execution works

Tool Testing Matrix

Tool Category Test Approach
Basic (fetch_url, etc.) Direct invocation, error scenarios
Search (search_web) Query validation, result format
Crawl (crawl_deep, map_site) Depth limits, link extraction
Premium (batch_scrape) Concurrent handling, error isolation

Performance Metrics

  • Server startup: < 2s
  • Tool response: < 5s (most operations)
  • Memory: Stable, no leaks
  • Error rate: < 1%

Reporting

Provide actionable feedback:

  • Specific error messages with file:line
  • Steps to reproduce
  • Suggested fixes
  • Performance bottlenecks
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. 2d ago First seen · 71 lines · 36 tokens per session scan A e61b4d8a8cff

Subscribe to this mod's changes

testing-validation is an agent published in the GitHub repository mysleekdesigns/crawlforge-mcp (2 stars, last pushed 2d ago), licensed MIT. It adds 36 tokens to every session and 421 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.