cursorrules

A set of rules for using a codebase and its MCP server, a service that lets software call external tools. It requires tool discovery, wrapper functions, redacted logging, and specific helper workflows.

In plain words
What is it for?
Finding the right tool, routing calls through the project's helper code, protecting sensitive log data, analyzing log files, exporting sheets as CSV, and handling incident-to-knowledge-base workflows.
Why use it?
It makes tool calls follow the repository's expected routing and security practices. It also points the agent to prepared workflows for log analysis, CSV exports, and incident documentation.

Cursor rule for Cursor

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/nguyendat-lhd/notebypine-mcp/cursorrules
Clone the repo
git clone --depth 1 https://github.com/nguyendat-lhd/notebypine-mcp

Made for: Cursor.

Per session 1,419 This file is loaded in full into every session.
When invoked 1,419 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.

ModelPer sessionOnce invoked
Fable 5 $0.01419 $0.01419
Opus 5 $0.00709 $0.00709
Sonnet 5 $0.00284 $0.00284
Haiku 4.5 $0.00142 $0.00142

Measured yesterday against content hash e8752359edb4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursorrules 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 yesterday.

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.

.cursorrules · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Notebypine MCP - Code Mode Rules

Primary Workflow: Code Mode Orchestration

When working with this codebase and MCP server, ALWAYS follow this pattern:

1. Tool Discovery First

  • Use agent/helpers/searchTools.ts to discover appropriate tools before calling them
  • Search with keywords like "incident", "solution", "export", "search" to find relevant tools
  • Always check tool relevance scores and pick the highest-rated ones

2. Route Through Helper Stack

  • NEVER call MCP tools directly - ALWAYS use agent/helpers/callMCPTool.ts
  • Use agent/helpers/router.ts for automatic routing decisions
  • All calls should go through the wrapper functions, not direct MCP invocation

3. Security & Logging

  • All logging is automatically redacted via agent/helpers/redact.ts
  • Never log raw payloads or sensitive data
  • Use sample-size logging (default 5-10 rows) for large datasets
  • Enable verbose mode only when explicitly requested

4. Use Skills for Complex Workflows

  • For log analysis: Use agent/skills/triageFromLogfile.ts
  • For CSV exports: Use agent/skills/saveSheetAsCSV.ts
  • For end-to-end workflows: Use agent/examples/incident_to_kb.ts

Code Mode Best Practices

File Structure

agent/
├── helpers/          # Reusable orchestration helpers
├── servers/notebypine/  # Tool wrappers (one per tool)
├── skills/           # Reusable operational flows
└── examples/         # End-to-end demonstrations

Import Patterns

// ✅ GOOD: Route through helpers
import { callMCPTool } from '../helpers/callMCPTool.js';
import { searchTools } from '../helpers/searchTools.js';
import { routeCall } from '../helpers/router.js';

// ❌ AVOID: Direct MCP calls
// import { mcp } from '@modelcontextprotocol/sdk';

Typical Workflow

  1. Discovery: searchTools("incident|solution|export")
  2. Import: Import only required wrappers
  3. Execute: Use callMCPTool() or routeCall()
  4. Log: Summaries are automatically logged (top 3 rows/items)

Read the full file on GitHub · 170 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. yesterday First seen · 170 lines · 1,419 tokens per session scan A e8752359edb4

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository nguyendat-lhd/notebypine-mcp (0 stars, last pushed 9mo ago), licensed MIT. It adds 1,419 tokens to every session, about $0.0071 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 2026-09-01.