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.
npx agentmods add rules/elephant-xyz/elephant-mcp/cursorrulesgit clone --depth 1 https://github.com/elephant-xyz/elephant-mcpWrote 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.
[](https://agentmods.dev/rules/elephant-xyz/elephant-mcp/cursorrules)<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>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 | $0.01096 | $0.01096 |
| Opus 5 | $0.00548 | $0.00548 |
| Sonnet 5 | $0.00219 | $0.00219 |
| Haiku 4.5 | $0.00110 | $0.00110 |
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.
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 Zodsrc/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 tosrc/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.tsextension - Vitest provides built-in TypeScript support and ES modules compatibility
- Run
npm testfor watch mode development testing - Run
npm run test:cifor CI/automated testing with JSON output
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.
- 4d ago First seen · 121 lines · 1,096 tokens per session scan A ef543a2d1c63
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.
Other cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.