agentmods.dev

antimetal-mcp-setup

antimetal-mcp-setup is a skill for Claude Code from antimetal/cursor-plugin. It costs 48 tokens per session (516 once invoked), scanned B, original, MIT.

A setup check for the Antimetal MCP server, which lets an agent connect to Antimetal tools. It verifies the required API key and explains how to add one if it is missing.

In plain words
What is it for?
It is for checking the MCP configuration and preparing the Antimetal connection before other Antimetal tasks run.
Why use it?
It prevents Antimetal tool calls from failing because the server is not authenticated.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the antimetal plugin — 3 skills shipped together

not rated 1repo 3mo ago B scan 48 tokens original MIT

Good fit It is for checking the MCP configuration and preparing the Antimetal connection before other Antimetal tasks run.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/antimetal/cursor-plugin/antimetal-mcp-setup
View source ↗ antimetal/cursor-plugin
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.

Any agent
npx skills add antimetal/cursor-plugin --skill antimetal-mcp-setup
Clone the repo
git clone --depth 1 https://github.com/antimetal/cursor-plugin

Made for: Claude Code.

Or install antimetal, the plugin that ships this one along with the rest of its 3 skills.

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 antimetal-mcp-setup

README.md
[![agentmods](https://agentmods.dev/badge/skills/antimetal/cursor-plugin/antimetal-mcp-setup.svg)](https://agentmods.dev/skills/antimetal/cursor-plugin/antimetal-mcp-setup)
Your own site
<a href="https://agentmods.dev/skills/antimetal/cursor-plugin/antimetal-mcp-setup"><img src="https://agentmods.dev/badge/skills/antimetal/cursor-plugin/antimetal-mcp-setup.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 516 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 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 $0.00048 $0.00516
Opus 5 $0.00024 $0.00258
Sonnet 5 $0.00010 $0.00103
Haiku 4.5 $0.00005 $0.00052

Measured 8d ago against content hash 137e3aa6c771, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

antimetal-mcp-setup scanned grade B 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 8d 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.

Reads MCP configurationmediumAgent snooping

mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.

The Antimetal MCP server authenticates via an API key sent in the `Authorization` header. The plugin's MCP configuration (`../../mcp.json` relative to this file) references the `ANTIMETAL_API_KEY` environment variable. I
skills/antimetal-mcp-setup/SKILL.md · 43 lines

What it actually says

Antimetal MCP Setup

You are the gatekeeper. Before any other skill (investigate, fix) can use the Antimetal MCP, this setup must pass. Do not attempt to list or call MCP tools until it does.

How It Works

The Antimetal MCP server authenticates via an API key sent in the Authorization header. The plugin's MCP configuration (../../mcp.json relative to this file) references the ANTIMETAL_API_KEY environment variable. If this variable is missing or empty, every MCP request will fail silently.

Setup Checklist

  1. Read the MCP config. Open ../../mcp.json (the grandparent directory of this skill) and confirm it references ANTIMETAL_API_KEY in the authorization header.

  2. Verify the API key is set. Check whether ANTIMETAL_API_KEY exists in the environment.

    • If it's set: skip ahead -- you're good to go.
    • If it's not set: stop here. Walk the user through getting one:
      1. Sign up or log in at antimetal.com
      2. Generate an API key from account settings
      3. Add it to their shell profile: 
        export ANTIMETAL_API_KEY="am_..."
      4. Source the profile or restart the terminal, then reload the Cursor window via the Command Palette (⌘⇧P on Mac, Ctrl+Shift+P on Windows/Linux) → Reload Window

    Do not proceed past this step without a valid key. Do not check tool schemas, do not attempt MCP calls. The user must provide the key first.

  3. Hand off. Once the key is confirmed, continue to whichever skill the user needs -- investigate or fix.

What This Skill Is NOT

This skill configures the connection. It does not:

  • Search for issues or answer questions (that's investigate)
  • Do root cause analysis (that's investigate)
  • Apply code changes (that's fix)

If setup passes, get out of the way and let the right skill take over.

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. 8d ago First seen · 43 lines · 48 tokens per session scan B 137e3aa6c771

Subscribe to this mod's changes

antimetal-mcp-setup is a skill published in the GitHub repository antimetal/cursor-plugin (1 stars, last pushed 3mo ago), licensed MIT. It adds 48 tokens to every session and 516 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

incidentincident-managementincident-responseinfrastructure
Related

Other skills, from other repositories

Incident Response Planner

Analyze an infrastructure incident alert and produce a structured response plan plus an executable on-call runbook. Use for incident, alert, on-call, and runbook requests.

AgentEra/Agently · 37 tokens

setup-environment-profile

Point the ilert CLI at a staging, preview or self-hosted ilert environment by giving it its own profile.

iLert/ilert-cli · 28 tokens

ilert-essentials

Core ilert concepts and CLI behaviour: the object model and the rules behind the field names.

iLert/ilert-cli · 0 tokens

migrate-from-opsgenie

Map Opsgenie resources onto ilert equivalents.

iLert/ilert-cli · 17 tokens

migrate-from-pagerduty

Map PagerDuty resources onto ilert equivalents.

iLert/ilert-cli · 16 tokens

migrate-from-statuspageio

Map Statuspageio (Atlassian Statuspage) resources onto ilert status page equivalents.

iLert/ilert-cli · 25 tokens