cursorrules

cursorrules is a cursor rule for Cursor from elephant-xyz/elephant-mcp. It costs 1,096 tokens per session, scanned A, original, MIT.

A set of instructions for Cursor AI when it works in a TypeScript project that builds Model Context Protocol servers. It documents commands for development, testing, linting, formatting, and the project structure.

In plain words
What is it for?
Use it to run the project, start development mode, execute Vitest tests, check code quality, format files, and understand the main source components.
Why use it?
It gives the coding agent consistent project-specific guidance instead of relying on guesses about how to build or check the repository.

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/elephant-xyz/elephant-mcp/cursorrules
Clone the repo
git clone --depth 1 https://github.com/elephant-xyz/elephant-mcp

Made for: Cursor.

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 cursorrules

README.md
[![agentmods](https://agentmods.dev/badge/rules/elephant-xyz/elephant-mcp/cursorrules.svg)](https://agentmods.dev/rules/elephant-xyz/elephant-mcp/cursorrules)
Your own site
<a href="https://agentmods.dev/rules/elephant-xyz/elephant-mcp/cursorrules"><img src="https://agentmods.dev/badge/rules/elephant-xyz/elephant-mcp/cursorrules.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,096 This file is loaded in full into every session.
When invoked 1,096 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 $0.01096 $0.01096
Opus 5 $0.00548 $0.00548
Sonnet 5 $0.00219 $0.00219
Haiku 4.5 $0.00110 $0.00110

Measured 4d ago against content hash ef543a2d1c63, 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 4d 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.

.cursorrules · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cursor AI Rules

This file provides guidance to Cursor AI when working with code in this repository.

Development Commands

# Build the project
npm run build

# Development with hot reloading (builds and starts server with watch mode)
npm run dev

# Start the production server
npm start

# Testing
npm test               # Run tests with vitest in watch mode
npm run test:ci        # Run tests once with JSON output for CI

# Code quality
npm run lint           # Check for linting issues
npm run lint:fix       # Fix auto-fixable linting issues
npm run format         # Format code with Prettier
npm run format:check   # Check code formatting

Architecture Overview

This is a TypeScript template for building Model Context Protocol (MCP) servers. The architecture follows a simple two-layer pattern:

Core Components

  • src/index.ts - Main MCP server entry point that:
    • Sets up the stdio server transport for inter-process communication
    • Defines all available MCP tools with their JSON schemas
    • Connects to the transport via stdin/stdout
    • Handles error responses in MCP format
  • src/config.ts - Environment configuration with validation using Zod
  • src/logger.ts - Structured logging with Pino (OpenTelemetry compatible)
  • src/lib/utils.ts - Utility functions for MCP response formatting

Template MCP Tools Available

The template includes one example tool to demonstrate MCP tool implementation:

  • listClassesByDataGroup - List classes for an Elephant data group with names and descriptions

Build System

  • Uses Vite for building with ES modules output format
  • TypeScript compilation targeting Node.js 22.18+ (native type stripping enabled by default)
  • External dependency: @modelcontextprotocol/sdk (not bundled)
  • Source alias @ points to src/ directory
  • Output goes to dist/ directory

Testing

  • Uses Vitest as the test runner and framework
  • Test files should be placed alongside source files with .test.ts extension
  • Vitest provides built-in TypeScript support and ES modules compatibility
  • Run npm test for watch mode development testing
  • Run npm run test:ci for CI/automated testing with JSON output

Read the full file on GitHub · 121 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. 4d ago First seen · 121 lines · 1,096 tokens per session scan A ef543a2d1c63

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository elephant-xyz/elephant-mcp (2 stars, last pushed 5d ago), licensed MIT. It adds 1,096 tokens to every session, about $0.0055 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.