pn-create-mcp-architecture

pn-create-mcp-architecture is a skill for Cursor from perniemann/pnCore. It costs 34 tokens per session (506 once invoked), scanned A, original, MIT.

A guide for documenting the MCP servers a project uses, what each one does, and how it connects to the project. MCP is a standard way for AI assistants to access tools and data sources.

In plain words
What is it for?
Use it to create an MCP architecture document that records servers, purposes, integration points, and the agent-to-tool relationships in a project.
Why use it?
It gives developers and maintainers a shared map of the project's external tools, making setup, onboarding, and future changes easier to understand.

Skill for Cursor

Written for Cursor: shipped in a Cursor plugin.

Part of the pn-core plugin — 133 skills, 19 commands, 9 agents, 1 MCP server shipped together

Good fit Use it to create an MCP architecture document that records servers, purposes, integration points, and the agent-to-tool relationships in a project.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/perniemann/pncore/pn-create-mcp-architecture
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 perniemann/pnCore --skill pn-create-mcp-architecture
Clone the repo
git clone --depth 1 https://github.com/perniemann/pnCore

Made for: Cursor.

Or install pn-core, the plugin that ships this one along with the rest of its 133 skills, 19 commands, 9 agents, 1 MCP server.

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 pn-create-mcp-architecture

README.md
[![agentmods](https://agentmods.dev/badge/skills/perniemann/pncore/pn-create-mcp-architecture/github.svg)](https://agentmods.dev/skills/perniemann/pncore/pn-create-mcp-architecture)
Your own site
<a href="https://agentmods.dev/skills/perniemann/pncore/pn-create-mcp-architecture"><img src="https://agentmods.dev/badge/skills/perniemann/pncore/pn-create-mcp-architecture/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for pn-create-mcp-architecture

Your own site · 80×15
<a href="https://agentmods.dev/skills/perniemann/pncore/pn-create-mcp-architecture"><img src="https://agentmods.dev/badge/skills/perniemann/pncore/pn-create-mcp-architecture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 506 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00034 $0.00506
Opus 5 $0.00017 $0.00253
Sonnet 5 $0.00007 $0.00101
Haiku 4.5 $0.00003 $0.00051

Measured 7d ago against content hash 19fcd35f81f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

pn-create-mcp-architecture 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 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.

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.

packages/pn-core-mcp/content/skills/integrations/pn-create-mcp-architecture/SKILL.md · 65 lines

What it actually says

Create MCP Architecture Document

Purpose

Create docs/MCP.md that documents which MCP servers the project uses, their purpose, and how they integrate. Enables onboarding and tooling maintenance.

When to use

  • During project kickoff when discovery or workspace indicates multiple MCPs in use
  • When project relies on MCPs (e.g. pn-core, Octocode, Stripe, n8n, shadcn) for development
  • When adding or documenting MCP setup for a project

Input

  • Discovery spec (stack, integrations mentioned)
  • Workspace .cursor/mcp.json or equivalent if inspectable
  • Known MCPs: pn-core, Octocode, Stripe, n8n, shadcn, Playwright, etc.

Instructions

  1. Identify MCPs in use: From discovery (payments → Stripe MCP; workflows → n8n MCP; UI → shadcn MCP; code research → Octocode), workspace config if available, or user confirmation.

  2. Apply template:

# [Project] MCP Architecture

## Overview
Which MCPs this project uses and why.

## MCP Servers

| MCP | Purpose | Integration |
|-----|---------|-------------|
| pn-core | Skills, agents, workflows, orchestration | Primary orchestration |
| [name] | [purpose] | [how it's used] |
| ... | ... | ... |

## Agent → MCP → Tool
Example flows: e.g. Frontend work → pn-core → pn-frontend-developer; Code trace → Octocode → lspGotoDefinition.

## Configuration
- Config path: `.cursor/mcp.json` (or equivalent)
- Env vars or secrets required (do not include values)
  1. Load pn-documentation: Apply format conventions.

  2. Save to: docs/MCP.md. Create docs/ if missing.

Output

  • MCP doc at docs/MCP.md
  • Gate: "MCP architecture doc complete. Proceed?" when in workflow.

Integration

  • pn-new (Involved mode): Optional step when MCPs in use; runs before refs index.
  • pn-tooling-mcp-maintenance: For config review and version compatibility; this skill produces the doc.
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 · 65 lines · 34 tokens per session scan A 19fcd35f81f6

Subscribe to this mod's changes

pn-create-mcp-architecture is a skill published in the GitHub repository perniemann/pnCore (0 stars, last pushed 4d ago), licensed MIT. It adds 34 tokens to every session and 506 once invoked, about $0.0002 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 2026-09-03.