What is mcp-only-bootstrap?

A workspace rule file that connects Cursor to pn-core through MCP, a standard way for tools to share context with an AI agent. It loads pn-core's build and design rules without installing the full plugin.

Use it in Cursor projects for pn-core build, design, and fix tasks. It helps configure the MCP connection and load the required rules automatically.

It lets pn-core workflows work in a project even when the plugin's file-based rules are not installed. It also tells the agent which rules and skills to load at the start of a task.

mcp-only-bootstrap — Cursor rule for coding agents by perniemann: A workspace rule file that connects Cursor to pn-core…

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 rules/perniemann/pncore/mcp-only-bootstrap

Clone the repo

git clone --depth 1 https://github.com/perniemann/pnCore

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.

README.md

[![agentmods](https://agentmods.dev/badge/rules/perniemann/pncore/mcp-only-bootstrap.svg)](https://agentmods.dev/rules/perniemann/pncore/mcp-only-bootstrap)

Your own site

<a href="https://agentmods.dev/rules/perniemann/pncore/mcp-only-bootstrap"><img src="https://agentmods.dev/badge/rules/perniemann/pncore/mcp-only-bootstrap.svg" alt="Measured on agentmods" height="20"></a>

Per session 436 This file is loaded in full into every session.

When invoked 436 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5	$0.00436	$0.00436
Opus 5	$0.00218	$0.00218
Sonnet 5	$0.00087	$0.00087
Haiku 4.5	$0.00044	$0.00044

Measured 3d ago against content hash 2d04cdfe9f6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-only-bootstrap 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 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.

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.

docs/mcp-only-bootstrap.mdc · 22 lines

What it actually says

pn-core MCP-only bootstrap

Start every new chat with: [pn-default] ▲ (context tag + Unicode U+25B2). Do this before any other output or tool call.

Requires pn-core MCP. If build/design flows do not trigger, pn-core may not be configured. Add to ~/.cursor/mcp.json (user) or .cursor/mcp.json (project). From pnCore repo: npm run mcp-config. See docs/mcp-usage-guide.md.

When pn-core MCP is available, load and follow the canonical pn rules so build/design and skill use behave like the full plugin.

First action in the session (or when the user gives a build/design/fix request):

Call get_rule("pn-build-gate") and follow it (use workflow_step or get_command for build/design; use skills directly for fix/tweak).
Call get_rule("pn-mcp-proactive") and follow it (use list_skills / get_skill, list_agents / get_agent, list_commands / get_command when the task matches a pn id).

You do not have the plugin's file-based rules in this workspace, so you must load these two rules via MCP and apply them. After that, proceed as the rules specify.

Continual learning: The skill pn-continual-learning is available via get_skill("pn-continual-learning"). When the user asks to "update AGENTS.md from transcripts" or "run continual learning", load that skill and follow its workflow (read transcripts, extract preferences/facts, merge into AGENTS.md). Automatic run-on-stop requires the plugin's hook and script; MCP-only, run the skill when the user asks.

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.

3d ago First seen · 22 lines · 436 tokens per session scan A 2d04cdfe9f6e

Subscribe to this mod's changes

mcp-only-bootstrap is a cursor rule published in the GitHub repository perniemann/pnCore (0 stars, last pushed yesterday), licensed MIT. It adds 436 tokens to every session, about $0.0022 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 2026-08-31.

LLM TypeScript Writing and docs agents cursor mcp plugin

mcp-only-bootstrap

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

pn-core MCP-only bootstrap

What this file has done since we first saw it

Other cursor rules, from other repositories

1001-typescript

nauro-ship-task

aim

frontend

000-writing-style

702-aws-well-architected-framework