What is testing-and-quality?

A testing guide for an MCP server with 31 tools. MCP is a standard way for AI assistants to connect to external tools and data.

Use it to run the comprehensive test suite, follow a manual checklist, verify development and production settings, and review test results.

It provides a repeatable way to check normal operations, authentication-related failures, input handling, configuration, errors, performance, and security.

testing-and-quality — Cursor rule for Cursor by skywinder: A testing guide for an MCP server with 31…

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 rules/skywinder/osm-edit-mcp/testing-and-quality

Clone the repo

git clone --depth 1 https://github.com/skywinder/osm-edit-mcp

Made for: Cursor.

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.

README.md

[![agentmods](https://agentmods.dev/badge/rules/skywinder/osm-edit-mcp/testing-and-quality.svg)](https://agentmods.dev/rules/skywinder/osm-edit-mcp/testing-and-quality)

Your own site

<a href="https://agentmods.dev/rules/skywinder/osm-edit-mcp/testing-and-quality"><img src="https://agentmods.dev/badge/rules/skywinder/osm-edit-mcp/testing-and-quality.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Nothing until a file matches its globs; then the whole rule loads.

When invoked 1,707 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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.01707
Opus 5	$0.00000	$0.00853
Sonnet 5	$0.00000	$0.00341
Haiku 4.5	$0.00000	$0.00171

Measured 4d ago against content hash 9a10cd69c43e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

testing-and-quality 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 4d 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.

.cursor/rules/testing-and-quality.mdc · 226 lines

How it starts

The opening of the file, as written. The whole thing — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Testing and Quality Assurance Guide

Comprehensive Testing Framework

Automated Testing with test_comprehensive.py

The test_comprehensive.py provides systematic testing of all 31 MCP tools:

# Run full test suite
python test_comprehensive.py

# Expected output: JSON report, logs, and console summary

Test Categories

Read Operations (Tests 1-15): Safe operations that should mostly pass
Write Operations (Tests 16-27): OAuth-protected, expected to fail without auth
Natural Language (Tests 28-31): Input validation and processing

Manual Testing with TESTING_CHECKLIST.md

Follow TESTING_CHECKLIST.md for systematic manual validation:

Testing Phases

Pre-test Setup: Configuration verification
Automated Testing: Run comprehensive test suite
Manual Testing: Phase-by-phase validation
Configuration Testing: Dev/prod switching
Error Handling: Edge cases and failures
Performance Testing: Response times and memory
Security Testing: Credential handling and validation

Test Results Analysis

Review TEST_RESULTS_SUMMARY.md for:

✅ Working tools (ready for use)
❌ Expected failures (OAuth-dependent, normal)
🔧 Issues to debug (actual problems requiring fixes)

Quality Standards

Test Success Criteria

Read operations: ≥80% success rate
Write operations: Expected 401/auth failures
Validation tools: 100% success rate
Error handling: Graceful failures with informative messages

Configuration Testing

Test dev/prod switching in .env:

# Test development mode
OSM_USE_DEV_API=true
python -c "from src.osm_edit_mcp.server import config; print(config.current_api_base_url)"

# Test production mode (careful!)
OSM_USE_DEV_API=false
python -c "from src.osm_edit_mcp.server import config; print(config.current_api_base_url)"

Logging Level Testing

Verify log levels in .env:

LOG_LEVEL=DEBUG   # Should show detailed debug info
LOG_LEVEL=INFO    # Should show operation info
LOG_LEVEL=WARNING # Should show only warnings/errors
LOG_LEVEL=ERROR   # Should show only errors

Read the full file on GitHub · 226 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.

4d ago First seen · 226 lines · 0 tokens per session scan A 9a10cd69c43e

Subscribe to this mod's changes

testing-and-quality is a cursor rule published in the GitHub repository skywinder/osm-edit-mcp (4 stars, last pushed 21d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,707 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 2026-08-31.

Testing

testing-and-quality