karimo-overview: Command for Claude Code

.claude/commands/test-mcp.md

test-mcp is a command for Claude Code from opensesh/karimo-overview. It costs 7 tokens per session (2,336 once invoked), scanned A, original, Apache-2.0.

An automated check for a BOS MCP server, a service that lets AI tools access other software. It tests the server connection, login, available tools, resources, asset handling, and error messages.

In plain words
What is it for?
Use it to verify environment variables, connect to the server, test its tools and resource endpoint, and report passed, failed, or skipped checks.
Why use it?
It finds setup, authentication, and integration problems in one run instead of requiring separate manual checks.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is opensesh/karimo-overview's own configuration. It tells Claude Code how to work on karimo-overview itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything karimo-overview configures →

Reuse

Borrowing it

Nothing to install: this file belongs to opensesh/karimo-overview. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/opensesh/karimo-overview/main/.claude/commands/test-mcp.md
Clone the repo
git clone --depth 1 https://github.com/opensesh/karimo-overview

Made for: Claude Code.

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.

agentmods badge for test-mcp

README.md
[![agentmods](https://agentmods.dev/badge/commands/opensesh/karimo-overview/test-mcp.svg)](https://agentmods.dev/commands/opensesh/karimo-overview/test-mcp)
Your own site
<a href="https://agentmods.dev/commands/opensesh/karimo-overview/test-mcp"><img src="https://agentmods.dev/badge/commands/opensesh/karimo-overview/test-mcp.svg" alt="Measured on agentmods" height="20"></a>
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,336 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00007 $0.02336
Opus 5 $0.00003 $0.01168
Sonnet 5 $0.00001 $0.00467
Haiku 4.5 $0.00001 $0.00234

Measured 7d ago against content hash e3eb7a528492, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

test-mcp 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 7d 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.

- Verify the base URL is reachable with a quick `curl -s -o /dev/null -w "%{http_code}" {BASE_URL}`
.claude/commands/test-mcp.md · 204 lines

How it starts

The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run an automated test suite against the BOS MCP server. This validates environment, authentication, all 10 tools, the resource endpoint, asset proxy, and error sanitization.

Setup

  1. Determine the base URL:

    • If the dev server is running: http://localhost:3000
    • Otherwise use NEXT_PUBLIC_APP_URL or https://bos-3-0.vercel.app
    • Verify the base URL is reachable with a quick curl -s -o /dev/null -w "%{http_code}" {BASE_URL}
  2. Get the MCP API key:

    • Check if MCP_TEST_API_KEY env var is set
    • If not, ask the user for their MCP API key (generated in BOS settings)
  3. Initialize results tracking:

    • Track pass/fail/skip counts
    • Store failure details for summary

Test Execution

Run tests sequentially. For each test, report the result inline: PASS, FAIL (with reason), or SKIP (with reason).

Phase 1: Environment Check

Check that required env vars are set (read their existence, not their values):

# Check each var exists (non-empty)
[ -n "$NEXT_PUBLIC_SUPABASE_URL" ] && echo "PASS: NEXT_PUBLIC_SUPABASE_URL" || echo "FAIL: NEXT_PUBLIC_SUPABASE_URL not set"
[ -n "$SUPABASE_SERVICE_ROLE_KEY" ] && echo "PASS: SUPABASE_SERVICE_ROLE_KEY" || echo "FAIL: SUPABASE_SERVICE_ROLE_KEY not set"
[ -n "$OPENAI_API_KEY" ] && echo "PASS: OPENAI_API_KEY" || echo "FAIL: OPENAI_API_KEY not set"

Phase 2: Auth Flow

Test authentication against the MCP endpoint:

# A1: No token - expect 401
curl -s -o /dev/null -w "%{http_code}" -X POST {BASE_URL}/api/mcp \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-03-26","capabilities":{},"clientInfo":{"name":"test","version":"1.0"}}}'

# A2: Invalid token - expect 401
curl -s -o /dev/null -w "%{http_code}" -X POST {BASE_URL}/api/mcp \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer fake_invalid_token_xyz" \
  -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-03-26","capabilities":{},"clientInfo":{"name":"test","version":"1.0"}}}'

# A3: Valid token - expect 200
curl -s -o /dev/null -w "%{http_code}" -X POST {BASE_URL}/api/mcp \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer {API_KEY}" \
  -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-03-26","capabilities":{},"clientInfo":{"name":"test","version":"1.0"}}}'

# A5: OAuth metadata
curl -s -o /dev/null -w "%{http_code}" {BASE_URL}/.well-known/oauth-authorization-server

Read the full file on GitHub · 204 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.

  1. 7d ago First seen · 204 lines · 7 tokens per session scan A e3eb7a528492

Subscribe to this mod's changes

test-mcp is a command published in the GitHub repository opensesh/karimo-overview (11 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 7 tokens to every session and 2,336 once invoked, about $0.0000 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.