ariffazil/MCP Server Smoke Test
skills/mcp-smoke-test/SKILL.md
Validate that MCP servers respond correctly to health probes and basic tool calls. Detect down servers, mismatched schemas, and transport errors.
tools
Updated May 27, 2026
$ install --global
skillsauthnpx skillsauth add ariffazil/openclaw-workspace MCP Server Smoke TestInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 27, 2026, 3:12 AM171.5s1 file scanned
SKILL.md
- id:
- mcp-smoke-test
- name:
- MCP Server Smoke Test
- version:
- 1.0.0
- description:
- Validate that MCP servers respond correctly to health probes and basic tool calls. Detect down servers, mismatched schemas, and transport errors.
- owner:
- AAA
- risk_tier:
- low
- physics:
- false
- math:
- false
- language:
- true
- skills:
- []
- servers:
- []
- schema_version:
- 1
- artifact_hash:
- pending
MCP Server Smoke Test
Overview
Federation organs expose MCP surfaces on different ports. This skill validates that each server is reachable, returns the expected tool count, and responds to a basic tool call without errors.
When to Use
- Daily federation health sweep
- After restarting any MCP server
- Before declaring a deployment successful
- When an agent reports "server unreachable"
When NOT to Use
- Do not use to probe external/third-party MCP servers without permission
- Do not use as a load test — this is a smoke test, not a stress test
- Do not use to extract secrets from MCP servers
Inputs
| Input | Required | Description |
|-------|----------|-------------|
| server_list | yes | Array of {name, url, expected_tools} |
| timeout_ms | no | Default 5000ms |
Procedure
Step 1: Health Probe
For each server in server_list:
- Send HTTP GET to
/healthor root endpoint - Record: status code, response time, error (if any)
- If status != 200 → flag as DOWN
Step 2: Tool Surface Probe
For each healthy server:
- List available tools (MCP
tools/listor REST equivalent) - Count tools and compare to
expected_tools - If count mismatch → flag as DRIFT
Step 3: Basic Tool Call
For each healthy server:
- Call a safe, read-only tool (e.g.,
arif_floor_status,health) - Verify response parses correctly
- If parse error or exception → flag as BROKEN
Step 4: Compile Report
Allowed Tools
| Tool | Purpose |
|------|---------|
| curl / fetch | HTTP health probe |
| mcp-call | MCP tool invocation |
Forbidden Actions
- NEVER call destructive tools during smoke test
- NEVER send malformed input designed to crash servers
- NEVER probe ports not in the canonical federation list
Output Format
## Skill Result: mcp-smoke-test
### Summary
[X/Y] servers healthy, [Z] drift, [W] broken
### Per-Server Results
| Server | Status | Tools | RTT | Error |
|--------|--------|-------|-----|-------|
| arifOS | UP | 13/13 | 45ms | — |
| GEOX | UP | 28/28 | 120ms | — |
| WEALTH | DOWN | — | — | connection refused |
### Drift Detected
- None / [list]
### Recommendations
1. [Action] — [Server] — [Priority]
Escalation Path
| Condition | Escalate To | Method | |-----------|-------------|--------| | arifOS down | ops.agent + Arif | Immediate alert | | Tool count drift >5 | AAA agent | Registry update needed | | Repeated failures | A-FORGE agent | Deployment rollback check |
Skill version 1.0.0 — AAA Skill Library
Related Skills
ariffazil/skill-trigger-linter
development
VerifiedTrustedCommunity
Check every skill’s “use when” and “do not use when” clauses for collisions, missing negatives, and vague verbs like “help,” “assist,” or “improve.” Load when linting, reviewing, or validating trigger boundaries.
SKILL.mdUpdated May 27, 2026
ariffazil/skill-creator
development
VerifiedTrustedCommunity
Bootstrap, design, and package new skills. Load when capturing user intent for a new skill or drafting its initial instruction framework.
SKILL.mdUpdated May 27, 2026
ariffazil/Federation Service Health Triage
content-media
VerifiedTrustedCommunity
Diagnose which federation services are up, down, or drifting. Produce a prioritized remediation plan.
SKILL.mdUpdated May 27, 2026
ariffazil/Secret Safety Scan
business
VerifiedTrustedCommunity
Scan a repo or workspace for exposed secrets, tokens, keys, and credentials. Produce a findings report with remediation steps.
SKILL.mdUpdated May 27, 2026