verify-mcp-cli

verify-mcp-cli is a command for Claude Code from AtlasDevHQ/atlas. It costs 43 tokens per session (11,287 once invoked), scanned D, original, AGPL-3.0.

A staging check for the two non-web ways into a service: MCP, a tool connection protocol, and a command-line interface. It tests trial provisioning, account claiming, device-flow login, and one REST API command.

In plain words
What is it for?
Run it after a release that changes MCP onboarding, the CLI, or API-key creation to verify the staging user journey.
Why use it?
It catches onboarding, login, and API-key problems after changes to the MCP setup, CLI, or API.

Command 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 commands/atlasdevhq/atlas/verify-mcp-cli
Clone the repo
git clone --depth 1 https://github.com/AtlasDevHQ/atlas

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 verify-mcp-cli

README.md
[![agentmods](https://agentmods.dev/badge/commands/atlasdevhq/atlas/verify-mcp-cli.svg)](https://agentmods.dev/commands/atlasdevhq/atlas/verify-mcp-cli)
Your own site
<a href="https://agentmods.dev/commands/atlasdevhq/atlas/verify-mcp-cli"><img src="https://agentmods.dev/badge/commands/atlasdevhq/atlas/verify-mcp-cli.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 11,287 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 3 findings. Scan, not verified.
Origin unknown 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 $0.00043 $0.11287
Opus 5 $0.00022 $0.05643
Sonnet 5 $0.00009 $0.02257
Haiku 4.5 $0.00004 $0.01129

Measured 3d ago against content hash ef8e5dc8e123, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade D, and why

verify-mcp-cli scanned grade D with 3 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 3d 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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

curl -sS "$API/api/v1/auth/region-probe" -H 'content-type: application/json' -d "{\"emailHash\":\"$EH\"}"

Reaches for credential fileshighPrivilege escalation

SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.

KEY=~/.ssh/id_ed25519_personal # MUST match the .pub `keys add` registered (it auto-picks an arbitrary ~/.ssh/*.pub — use the one whose comment is your Railway account email; an `-i` mismatch → status:signup_required)

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -sS -D "$H" -o /dev/null "$API/mcp/onboarding" \
.claude/commands/verify-mcp-cli.md · 303 lines

The source is not reproduced here

Licensed AGPL-3.0

The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

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. 3d ago First seen · 303 lines · 43 tokens per session scan D ef8e5dc8e123

Subscribe to this mod's changes

verify-mcp-cli is a command published in the GitHub repository AtlasDevHQ/atlas (1 stars, last pushed 3d ago), licensed AGPL-3.0. It adds 43 tokens to every session and 11,287 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it D with 3 findings (sends data to an external url, reaches for credential files, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.