pnCore
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@pnCorestart a new gated delivery workflow to add user authentication"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
pnCore — v0.18.7
pnCore is an MCP server and Cursor plugin. It runs software delivery as a sequence of named, gated steps instead of one long chat.
It ships discovery, planning, skeptic challenge, design, audits, assets, and delivery through a deterministic workflow_step engine — backed by skills, agents, rules, and pn-core:// resources, not a folder of prompts.
Catalog: 170 skills, 9 public agents + 6 internal orchestration agents, 31 visible slash palette files (30 under pn submenu + /pn stub) + 18 palette-hidden surgical commands (49 command files total), 26 MCP tools, 16 workflow types, plus pn-core:// resources and prompts.
Why this exists
A single chat can plan a feature, write the code, and tell you it's done — but there's no checkpoint in between. If it goes sideways on step three, you're rereading the whole transcript to find out where. Asking it to redo one part usually means starting the conversation over, and whatever context got it that far is gone.
pnCore moves that step list out of the chat. workflow_step(type, index, state) runs one step at a time — discovery, plan, build, review — and hands back the next instruction. A skeptic pass, a human gate, or workflow_verify decides whether a step actually passed, not the model's own say-so. If you get disconnected, workflow_state_save and workflow_state_load pick the run back up where it left off.
Related MCP server: odin
What it is
Deterministic. workflow_step(type, index, state) decides the next instruction. Steps aren't skipped by assumption — skipping one is a gate decision, logged in state.
Gated. Skeptic, human, and workflow_verify gates are built into the engine. Intent is full auto, design focused, or involved — involved means you approve discovery, plan, specialists, and review before they run.
Multi-surface. One canonical tree in packages/pn-core-mcp/content/. The MCP runs the engine in any client. The Cursor plugin adds the / palette, file-glob rules, agent selector, and stop hook. Pi registers the same 26 tools natively.
Resumable. Every run has a run_id. Handoff lines and usage land in JSONL. After a disconnect, load state and continue the same step list.
Install
Prerequisite: Node.js 22+.
Call health first — it should return version, calendarDateUtc, and capabilities. If it doesn't, nothing downstream (skills, agents, workflow_step) will load either.
Cursor — MCP (one-click)
Or add manually to ~/.cursor/mcp.json:
{
"mcpServers": {
"pn-core": {
"command": "npx",
"args": ["-y", "--package=git+https://github.com/perniemann/pnCore.git#main", "--", "pn-core"],
"env": { "GIT_TERMINAL_PROMPT": "0", "GIT_ASKPASS": "echo" }
}
}
}GIT_TERMINAL_PROMPT=0 and GIT_ASKPASS=echo fail fast when git cannot authenticate (missing credentials, rate limit, or a bad URL). Without them, a credential prompt on piped stdin leaves Cursor in a forever loading state.
Cursor — Plugin
From your target project directory:
npx github:perniemann/pnCore plugin-installCopies commands, rules, skills, agents, config, and hooks into .cursor/ and .cursor-plugin/. Reload Cursor, then run /pn-new.
MCP or plugin? MCP is the engine. The plugin is the Cursor surface (slash palette, rules, agents, stop hook). The intended Cursor setup is both. Details: Plugin vs MCP.
pi.dev (Pi coding agent)
pi install git:github.com/perniemann/pnCore@mainPi surfaces a single /pn entry. Direct invoke: /pn pn-build. Native tools ship with pi install git:…/pnCore or pi install . from this repo root after npm run build:mcp. Cursor and Claude Code still use the stdio MCP server. See ADR-0008 and ADR-0009.
Claude Code
Use the same MCP JSON. Settings → MCP Servers, paste the block, enable it. See Anthropic's MCP documentation.
Windows, Cloud Agents, this-checkout node paths, and first-npx timeouts: packages/pn-core-mcp/README.md. Clone-and-develop: CONTRIBUTING.md.
Quick start
Install MCP and/or plugin (above).
Call
health— version, UTC date, capabilities.New repo or greenfield:
/pn-neworworkflow_step("project_kickoff", 0, {})— discovery, refs, PRD, and design docs underdocs/refs/.Build or extend:
/pn-buildorworkflow_step("full_dev", 0, {})— skips kickoff when the project already has context.Before ship:
/pn-deliveror/pn-frontend-audit.
Copy-paste first message:
pn-new ▲
Build [your-project-name] — [one-line description].
References: [path or "in .ref/"] (pitch, requirements, design assets).
Analyze both: prior art and design.
Intent: Involved — full gates at discovery, plan, specialists, and review.
Delivery tier: full. Design ambition: distinctive.Answer Step 0: Yes, Both. Step 1: (3) Involved.
More prompts: docs/how-to-use-guide.md.
Workflows
Call list_workflow_types for live step counts.
Use it for | Workflow | Cursor | MCP entry |
New project: refs, discovery, PRD, design |
|
|
|
Build a feature or product end-to-end |
|
|
|
Design-first UI |
|
|
|
Scored frontend diagnosis + fix roadmap |
|
|
|
API, security, data, errors, performance |
|
|
|
SVG, raster, or placeholders |
|
|
|
Evidence-led strategy brief |
|
|
|
Competing implementations (2–3 worktrees) |
|
|
|
Multi-slice hierarchical build |
|
|
|
Also on the engine: visual_tweak, prompt_optimize, game_feature, engine_feature (Unreal / Godot), fsi_analyst_draft, media_director. Full table and aliases: list_workflow_types.
Example: full_dev
# | Who | Action |
1 | You |
|
2 | Agent |
|
3 | Agent | Prior-art and research pass for your stack. |
4 | Agent |
|
5 | You | Review plan. Involved intent runs skeptic challenge; approve before build. |
6 | Agent |
|
7 | Agent |
|
8 | Agent | Optional merge phase ( |
9 | Agent |
|
10 | You |
|
Tool steps are 0-based. Resume after disconnect: workflow_state_save then workflow_state_load. Schema: pn-core://reference/workflow-state-schema.md.
Design-first: workflow_step("design", 0) instead of full_dev. Load .pncore-design.md via /pn-setup.
Game / 3D: workflow_step("game_feature", 0) for feature loops. For full builds, use full_dev and name the stack in discovery.
What changes
Without pnCore | With pnCore |
One long transcript | Named steps, each with a |
"Done" means the model stopped talking | Skeptic, |
A retry starts a new chat |
|
Skills live in a folder you have to remember to load | The engine loads gates and skills automatically |
Works in Cursor chat, nowhere else | MCP runs in any client; Pi has native tools |
Three tier concepts (do not conflate them): delivery tier (MVP/Full), context tier (1–4 reading depth), model tier (fast / standard / premium / premium_thinking / long_horizon). Loop orchestration: suggest_model_tier with role: orchestrator → long_horizon. See pn-core://reference/delivery-tier-criteria.md and MCP tools.
Load before a build session: pn-core://reference/best-practices.md, pn-core://reference/loop-orchestration-guide.md, pn-core://reference/aesthetics-baseline.md, and health for the current UTC date.
Honest edges
Situation | What happens | What to do |
A one-line typo fix | The workflow overhead isn't worth it | Ask directly, skip |
Plugin without MCP | Slash templates only — no | Install MCP for Cursor, or both |
First npx on a git+https package URL | Cursor MCP can time out on a cold clone | Pre-warm once, then reload. Matrix: MCP README |
| Preview flags; off by default | Set |
Vue, Svelte, Angular, Unity | Limited support | Prefer React, Astro, Next, vanilla web, Node, Three.js / Babylon, n8n, web3 |
Best fit: teams building with Cursor on React, Astro, Next.js, vanilla web, Node backends, Three.js / Babylon / gamedev, n8n, and web3. Inventory: docs/plugin-reference.md.
Documentation
Guide | What's in it |
Copy-paste prompts, example flows, MCP-only bootstrap | |
MCP tools, resources, workflow patterns, state/handoff | |
Rules, skills, agents, commands, hooks | |
MCP config, 26 tools, env vars, error codes, resources | |
Companion MCPs (Octocode, Stripe, n8n, …) | |
End-to-end pitch-to-app walkthrough | |
Kickoff and | |
Workspace map, scripts, PR workflow, ADR policy | |
Release history |
Scripts
Contributor scripts, local MCP config, and how to develop pnCore live in CONTRIBUTING.md. Repo layout: docs/folder-structure.md.
License
MIT — see LICENSE.
This server cannot be installed
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceAutomates DevOps workflows like vulnerability resolution, code review, test generation, and DORA metrics through Claude Code slash commands, using a state machine for reliable execution.32MIT
- AlicenseNot gradedqualityBmaintenanceProvides a specification-driven workflow layer for AI-assisted coding, enabling agents to follow an explicit 11-phase feature workflow with checkpoints, artifacts, and quality gates.MIT
- FlicenseNot gradedqualityBmaintenanceOrchestrates multi-stakeholder feature refinement and development execution workflows for AI-assisted software teams.
- AlicenseNot gradedqualityDmaintenanceEnforces client-mandated development workflows with audit trails, state persistence, and compliance reporting. Provides tools for issue tracking, testing, deployment, and verification to ensure non-negotiable compliance.MIT
Related MCP Connectors
Autonomous dev team steered from chat: plain-English requests in, tested merged PRs out.
Software component catalog: search your org's services, docs, APIs, dependencies, and ownership.
Durable agent-to-agent handoffs and shared scratchpad for multi-agent workflows.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/perniemann/pnCore'
If you have feedback or need assistance with the MCP directory API, please join our Discord server