mcp-setup

mcp-setup is a skill for Claude Code, Codex from LeadMagic/gtm-skills. It costs 55 tokens per session (1,645 once invoked), scanned A, original, MIT.

A guide for connecting AI agents to business tools through the Model Context Protocol, a standard way for agents to discover and use tools. It focuses on choosing tools, limiting permissions, and tracking tool use.

In plain words
What is it for?
Use it to connect agents to CRM, account-enrichment, sales-sequencing, analytics, or support tools, and to design safer permissions and multi-tool workflows.
Why use it?
It helps prevent agents from having unnecessary access or making uncontrolled changes in systems such as CRMs and enrichment tools. It also makes connected tools and their actions easier to review.

Skill for Claude CodeCodex

Part of the gtm-skills plugin — 196 skills 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 skills/leadmagic/gtm-skills/mcp-setup
Any agent
npx skills add LeadMagic/gtm-skills --skill mcp-setup
Clone the repo
git clone --depth 1 https://github.com/LeadMagic/gtm-skills

Made for: Claude Code, Codex.

Or install gtm-skills, the plugin that ships this one along with the rest of its 196 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 mcp-setup

README.md
[![agentmods](https://agentmods.dev/badge/skills/leadmagic/gtm-skills/mcp-setup.svg)](https://agentmods.dev/skills/leadmagic/gtm-skills/mcp-setup)
Your own site
<a href="https://agentmods.dev/skills/leadmagic/gtm-skills/mcp-setup"><img src="https://agentmods.dev/badge/skills/leadmagic/gtm-skills/mcp-setup.svg" alt="Measured on agentmods" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,645 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 $0.00055 $0.01645
Opus 5 $0.00028 $0.00822
Sonnet 5 $0.00011 $0.00329
Haiku 4.5 $0.00006 $0.00164

Measured today against content hash e1b52ef6f331, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-setup 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 today.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/check-output.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/automation/mcp-setup/SKILL.md · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Setup

Overview

MCP turns AI agents into tool-using operators. The risk is that teams connect every tool, expose write access, and then wonder why the agent behaves unpredictably. Good MCP setup is not "give the agent more tools." It is tool curation, permission design, and auditability.

This skill configures MCP for GTM workflows where agents research accounts, enrich records, inspect CRM, draft messaging, and route tasks without uncontrolled external side effects.

When to Use

Use this skill when the user asks to "set up MCP for sales tools", "connect our CRM to Claude/Jesse", "give my agent enrichment capabilities", "build an MCP server for GTM tools", "configure MCP permissions", "connect LeadMagic MCP", "orchestrate multiple MCP servers", or "make agent tool use safer".

Authoritative Foundations

Model Context Protocol Specification

MCP standardizes how agents discover tools, resources, and prompts. The key design principle is clear tool descriptions and predictable tool inputs/outputs.

Anthropic — Tool Use Design Patterns

Tools should be narrowly described, unambiguous, and paired with verification steps. Agents need clear rules for when to call a tool and when to ask for confirmation.

Least Privilege Access Control

Agents should receive the minimum access needed for the current task. Read-only first, write access only where the business process explicitly requires it.

Audit Logging

Log every tool call: tool name, who triggered it, timestamp, and a short summary of inputs/outputs. Without this, you cannot debug mistaken CRM writes or sequence enrollments.

Prerequisites

  • Agent platform that supports MCP
  • List of tools to expose
  • API credentials stored securely
  • Permission model: read, draft, write, send
  • Audit log destination
  • Human approval policy for write actions

Step-by-Step Process

Phase 1: Inventory Tool Categories

Category Example Tools Default Permission
Enrichment email finder, company enrichment Read / lookup
CRM accounts, contacts, deals Read-only first
Sequencing campaign creation, enrollment Draft-only
Analytics dashboards, event data Read-only
Support Plain MCP (threads, customers, tenants, help center) Read + draft replies; confirm before send

Read the full file on GitHub · 175 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. today Changed e1b52ef6f331
  2. 5d ago First seen · 175 lines · 55 tokens per session scan A f723a384a286

Subscribe to this mod's changes

mcp-setup is a skill published in the GitHub repository LeadMagic/gtm-skills (46 stars, last pushed 2d ago), licensed MIT. It adds 55 tokens to every session and 1,645 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

outreachmagic

Your agent goes blind after send. Sync sequencer webhooks, research leads via Serper, and find/verify emails — all in one local SQLite DB your agent queries directly.

outreachmagic/outreachmagic · 40 tokens

cold-email

Expert cold email strategist for B2B outbound campaigns. Use when the user asks about cold email writing, email sequences, email deliverability, domain warmup, SPF/DKIM/DMARC setup, email personalization, cold email templates, email copywriting frameworks, email compliance (CAN-SPAM, GDPR), bounce management, inbox…

Frontal-so/outbound-skills · 177 tokens

list-building

Expert B2B list building orchestrator for outbound sales campaigns. Use when the user asks about building lead lists, Sales Navigator search, boolean filters, ICP definition, ICP scoring, lead sources, data validation, email verification, list segmentation, Apollo prospecting, Clay Find People, list hygiene…

Frontal-so/outbound-skills · 190 tokens

claygent

Use Clay's AI research agent (Claygent) for web research, custom data extraction, and information that does not exist in standard databases. Use when the user asks about Claygent, AI research in Clay, web browsing for data, custom data points, real-time company research, or scraping with AI. Triggers on "Claygent"…

Frontal-so/outbound-skills · 131 tokens

conditional-logic

Write Clayscript formulas, conditional runs, and credit-saving logic in Clay. Use when the user asks about Clayscript, Clay formulas, conditional runs, saving credits with logic, data manipulation, if/then logic, JavaScript formulas in Clay, or the AI formula generator. Triggers on "Clayscript", "formula"…

Frontal-so/outbound-skills · 128 tokens

people-enrichment

Find and enrich contacts at target companies in Clay. Use when the user asks about finding decision makers, people enrichment, LinkedIn enrichment, title or seniority filtering, buying committee mapping, contact discovery at companies, or Sales Navigator imports. Triggers on "find contacts", "find people", "people…

Frontal-so/outbound-skills · 110 tokens