use-mcp

use-mcp is a command for coding agents from aitytech/agentkits-marketing. It costs 12 tokens per session (1,251 once invoked), scanned A, original, MIT.

A command for using MCP servers, which let an AI agent call connected tools and services for tasks such as analytics or SEO. It defines response rules, data checks, and questions for choosing the task scope and integration type.

In plain words
What is it for?
Use it to request a quick query, an analysed result, or a multi-source report across analytics, SEO, and other MCP integrations.
Why use it?
It helps select the right kind of connected-tool task while keeping results tied to verified data. It prevents guessed metrics when a tool fails or data is missing.

Command

Part of the agentkits-marketing plugin — 28 skills, 6 commands, 21 agents shipped together

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/aitytech/agentkits-marketing/use-mcp
Clone the repo
git clone --depth 1 https://github.com/aitytech/agentkits-marketing

Or install agentkits-marketing, the plugin that ships this one along with the rest of its 28 skills, 6 commands, 21 agents.

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 use-mcp

README.md
[![agentmods](https://agentmods.dev/badge/commands/aitytech/agentkits-marketing/use-mcp.svg)](https://agentmods.dev/commands/aitytech/agentkits-marketing/use-mcp)
Your own site
<a href="https://agentmods.dev/commands/aitytech/agentkits-marketing/use-mcp"><img src="https://agentmods.dev/badge/commands/aitytech/agentkits-marketing/use-mcp.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,251 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00012 $0.01251
Opus 5 $0.00006 $0.00626
Sonnet 5 $0.00002 $0.00250
Haiku 4.5 $0.00001 $0.00125

Measured 5d ago against content hash 50ae6348dbf5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

use-mcp scanned grade A with 0 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 5d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

commands/use-mcp.md · 211 lines

How it starts

The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Language & Quality Standards

CRITICAL: Respond in the same language the user is using. If Vietnamese, respond in Vietnamese. If Spanish, respond in Spanish.

Standards: Token efficiency, sacrifice grammar for concision, list unresolved questions at end.

Skills: Activate analytics-attribution skill.

Components: Reference ./.claude/components/interactive-questions.md


Data Reliability

CRITICAL: MCP tools provide verified real-time data. Never fabricate results.

  • MCP data is trusted - use it directly in reports
  • ⚠️ If tool fails - show error, don't substitute fake data
  • Never guess metrics that MCP should provide

Interactive Parameter Collection

Step 1: Ask Output Scope

Question: "What level of MCP task do you need?" Header: "Scope" MultiSelect: false

Options:

  • Quick Query - Single data pull
  • Standard - Query with analysis
  • Comprehensive - Multi-source with report
  • Custom - I'll specify what I need

Step 2: Ask Integration Type

Question: "Which integration category?" Header: "Category" MultiSelect: false

Options:

  • Analytics - GA, Search Console, attribution
  • SEO - Semrush, DataForSEO, keywords
  • App Intel - SensorTower, app analytics
  • CRM/Ads - HubSpot, Meta, social

Step 3: Ask Data Need

Question: "What data do you need?" Header: "Data" MultiSelect: true

Options:

  • Metrics - Numbers, KPIs, performance
  • Rankings - Position, keyword, competitive
  • Contacts - Leads, customers, segments
  • Content - Posts, campaigns, creatives

Step 4: Ask Time Frame

Question: "What time period?" Header: "Period" MultiSelect: false

Options:

  • Real-time - Current/latest data
  • Last Week - Past 7 days
  • Last Month - Past 30 days
  • Custom - I'll specify dates

Step 5: Confirmation

Display summary:

## MCP Task Configuration

| Parameter | Value |
|-----------|-------|
| Task | [description] |
| Category | [selected category] |
| Data Types | [selected data] |
| Period | [selected period] |
| Scope | [Quick/Standard/Comprehensive] |

Read the full file on GitHub · 211 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. 5d ago First seen · 211 lines · 12 tokens per session scan A 50ae6348dbf5

Subscribe to this mod's changes

use-mcp is a command published in the GitHub repository aitytech/agentkits-marketing (595 stars, last pushed 6d ago), licensed MIT. It adds 12 tokens to every session and 1,251 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.