Skip to main content
hc
Submit
commandsSource-backedReview first Safety ✓ Privacy ✓

/mcp-smoke-test - MCP Server Verification Runbook

Community slash command runbook for post-install MCP verification using only documented Claude Code MCP commands: claude mcp list, claude mcp get, and the /mcp panel for authentication status before exercising a read-only tool.

by kiannidev·added 2026-06-16·
Claude Code
HarnessClaude Code
Invocation:/mcp-smoke-test [server-name]
Review first — review before installing

Open the source and read safety notes before installing.

Safety notes

  • Prefer read-only tools during verification; avoid destructive MCP tools on production data.
  • Remove failing servers from MCP config before sharing logs externally.

Privacy notes

  • MCP tool outputs may include repository paths; redact before posting publicly.

Prerequisites

  • Server already added with claude mcp add or present in project .mcp.json.
  • Non-production credentials when testing OAuth or remote MCP servers.

Schema details

Install type
cli
Troubleshooting
No
Source repository stats
Scope
Source repo
Runtime and command metadata
Command syntax
/mcp-smoke-test [server-name]
Full copyable content
/mcp-smoke-test [server-name]

About this resource

Scope

This is a community custom entry you add under .claude/commands/ or .claude/hooks/. It is not a built-in Claude Code feature named on code.claude.com.

The /mcp-smoke-test runbook walks through documented MCP management commands after you add a server. It does not assume a built-in /mcp-smoke-test page on code.claude.com.

Usage

/mcp-smoke-test [server-name]

What it does

When you invoke this command, follow these steps:

  1. List configured servers. Run claude mcp list and confirm the target server appears with the expected scope (project, user, or local).
  2. Inspect one server. Run claude mcp get <server-name> to review transport, command or URL, and pending approval status documented in the MCP guide.
  3. Check live status in Claude Code. Ask the operator to open /mcp and confirm authentication status, tool count, and any servers flagged as needing auth.
  4. Handle pending approval. If the guide shows Pending approval for a project .mcp.json server, complete the interactive approval flow before testing tools.
  5. Exercise one read-only tool. With explicit user approval, invoke a documented read-only MCP tool with minimal arguments and record errors or OAuth prompts.
  6. Summarize rollback. If verification fails, document removal steps using claude mcp remove <server-name> and reverting .mcp.json edits.

Output format

  • Server name, transport, and scope
  • claude mcp get configuration summary
  • /mcp authentication and tool availability notes
  • Sample read-only tool result
  • Pass/fail verdict and rollback steps

Source Verification Notes

Verified against Claude Code MCP documentation on 2026-06-16:

  • claude mcp list lists configured MCP servers and shows pending approval states for project-scoped .mcp.json entries.
  • claude mcp get <name> prints configuration details for a single server.
  • The /mcp panel shows authentication status, tool counts, and servers that advertise tools but expose none.
  • Remote servers may require OAuth completed through the /mcp menu.
  • claude mcp remove <name> removes a configured server when rollback is needed.

Duplicate Check

No command in content/commands/ documents this MCP post-install verification runbook using claude mcp list, claude mcp get, and /mcp together.

#mcp#slash-command#verification#setup

Source citations

Add this badge to your README

Show that /mcp-smoke-test - MCP Server Verification Runbook is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.

Listed on HeyClaude
[![Listed on HeyClaude](https://heyclau.de/badge/commands/mcp-smoke-test.svg)](https://heyclau.de/entry/commands/mcp-smoke-test)

How it compares

/mcp-smoke-test - MCP Server Verification Runbook side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.

Field/mcp-smoke-test - MCP Server Verification Runbook

Community slash command runbook for post-install MCP verification using only documented Claude Code MCP commands: claude mcp list, claude mcp get, and the /mcp panel for authentication status before exercising a read-only tool.

Open dossier 		Claude Agent SDK MCP Integration Capability Pack Skill

Expert Claude Agent SDK MCP integration capability pack for designing, reviewing, and rolling out Agent SDK MCP integration with source-backed checklists, production rules, and privacy-safe output contracts.

Open dossier 		Claude Code managed MCP governance Capability Pack Skill

Expert Claude Code managed MCP governance capability pack for designing, reviewing, and rolling out managed MCP governance with source-backed checklists, production rules, and privacy-safe output contracts.

Open dossier 		Claude Code Troubleshooting Triage Capability Pack Skill

Expert Claude Code troubleshooting triage capability pack for diagnosing install failures, auth errors, MCP issues, sandbox blocks, and update regressions with source-backed triage matrices and privacy-safe support output.

Open dossier
Trust
Install riskReview firstReview firstReview firstReview first
Notes Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓
Categorycommandsskillsskillsskills
Sourcesource-backedsource-backedsource-backedsource-backed
Authorkiannidevkiannidevkiannidevkiannidev
Added2026-06-162026-06-142026-06-142026-06-15
Platforms
Claude Code
Claude CodeCodexWindsurfGeminiCursorCLI
Claude CodeCodexWindsurfGeminiCursorCLI
Claude CodeCodexWindsurfGeminiCursorCLI
Source repo————
Safety notes✓Prefer read-only tools during verification; avoid destructive MCP tools on production data. Remove failing servers from MCP config before sharing logs externally.✓This skill plans Agent SDK MCP integration; it must not execute destructive changes without explicit approval. Browser, computer-use, and remote surfaces can access sensitive UI state; scope tests carefully. MCP and SDK integrations may exfiltrate data if tool scopes are too broad. The public `anthropics/claude-code` repository ships documentation links to code.claude.com for settings, security, and integration surfaces. Scheduled or autonomous workflows compound risk; cap blast radius in staging first.✓This skill plans managed MCP governance; it must not execute destructive changes without explicit approval. Browser, computer-use, and remote surfaces can access sensitive UI state; scope tests carefully. MCP and SDK integrations may exfiltrate data if tool scopes are too broad. The public `anthropics/claude-code` repository ships documentation links to code.claude.com for settings, security, and integration surfaces. Scheduled or autonomous workflows compound risk; cap blast radius in staging first.✓This skill triages failures; it must not disable sandbox, security, or managed policy without explicit admin approval. Do not paste secrets, OAuth tokens, or session cookies into public troubleshooting threads. Avoid running destructive fix steps (global uninstall, credential deletion) without user confirmation. MCP and plugin removals can break team workflows; document rollback before changes.
Privacy notes✓MCP tool outputs may include repository paths; redact before posting publicly.✓Reviews may expose integration tokens, customer metadata, and internal URLs related to Agent SDK MCP integration. Telemetry and analytics configs can include account emails; redact before sharing externally. Keep troubleshooting logs in internal channels unless explicitly sanitized. Third-party vendors remain outside Anthropic retention policies; document separately.✓Reviews may expose integration tokens, customer metadata, and internal URLs related to managed MCP governance. Telemetry and analytics configs can include account emails; redact before sharing externally. Keep troubleshooting logs in internal channels unless explicitly sanitized. Third-party vendors remain outside Anthropic retention policies; document separately.✓Troubleshooting logs can expose repo paths, auth emails, internal URLs, and MCP tool arguments. Support handoffs may include session transcripts; redact customer or employee identifiers first. Network proxy and ZDR settings can reveal enterprise security posture; keep details in private channels. Diagnostic exports may contain API usage metadata governed by org retention policies.
Prerequisites
  • Server already added with claude mcp add or present in project .mcp.json.
  • Non-production credentials when testing OAuth or remote MCP servers.
  • Access to Claude Code or Agent SDK environment where Agent SDK MCP integration will run.
  • Ability to read project, user, and managed settings relevant to the workflow.
  • Staging repository or sandbox account for safe validation.
  • Platform or security stakeholder available for policy-bound rollouts.
  • Access to Claude Code or Agent SDK environment where managed MCP governance will run.
  • Ability to read project, user, and managed settings relevant to the workflow.
  • Staging repository or sandbox account for safe validation.
  • Platform or security stakeholder available for policy-bound rollouts.
  • Claude Code version, OS, install method, and recent config or update changes.
  • Access to local logs, settings files, and MCP configuration relevant to the failure.
  • Ability to reproduce the failure in a controlled session when safe.
  • Admin contact path for managed policy, network proxy, or enterprise auth issues.
Install
/mcp-smoke-test [server-name]
———
Config————
Citations
ClaimUnclaimedUnclaimedUnclaimedUnclaimed

Signals

Loading live community signals…

More like this, weekly

A short, calm digest of reviewed Claude resources. Unsubscribe any time.