global-standards

global-standards is a cursor rule for Cursor from Kenlan2022/mcp_servers_showcase. It costs 1,898 tokens per session, scanned A, original, MIT.

A rule set for developing MCP servers, which are programs that give AI assistants access to tools and data.

In plain words
What is it for?
It helps structure a project, initialise it with uv, add development dependencies, and build and test one component at a time.
Why use it?
It reduces mistakes from making many untested changes and keeps development organised with tasks, tests, and progress notes.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit It helps structure a project, initialise it with uv, add development dependencies, and build and test one component at a time.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/kenlan2022/mcp_servers_showcase/global-standards
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.

Clone the repo
git clone --depth 1 https://github.com/Kenlan2022/mcp_servers_showcase

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 global-standards

README.md
[![agentmods](https://agentmods.dev/badge/rules/kenlan2022/mcp_servers_showcase/global-standards.svg)](https://agentmods.dev/rules/kenlan2022/mcp_servers_showcase/global-standards)
Your own site
<a href="https://agentmods.dev/rules/kenlan2022/mcp_servers_showcase/global-standards"><img src="https://agentmods.dev/badge/rules/kenlan2022/mcp_servers_showcase/global-standards.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,898 This file is loaded in full into every session.
When invoked 1,898 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.01898 $0.01898
Opus 5 $0.00949 $0.00949
Sonnet 5 $0.00380 $0.00380
Haiku 4.5 $0.00190 $0.00190

Measured 7d ago against content hash 5c2fadefd436, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

global-standards 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 7d 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.

.cursor/rules/global-standards.mdc · 321 lines

How it starts

The opening of the file, as written. The whole thing — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.


type: always name: "Global MCP Standards" description: "Common standards for all MCP servers with incremental development approach"

Global MCP Server Development Standards

Core Philosophy: Incremental Development

CRITICAL: Never create multiple untested files at once. Follow the incremental approach:

  1. Plan First: Always create or update TODO/TASKS lists before coding
  2. One Step at a Time: Implement one feature/component at a time
  3. Test Immediately: Write and run tests for each component before moving to next
  4. Document Progress: Update TODO lists and add completion notes
  5. Review Before Proceed: Ensure current step works before starting next

Project Structure Requirements

Use UV for Development

# Project initialization
uv init mcp-servers-project
cd mcp-servers-project
uv add mcp fastapi uvicorn pytest pytest-asyncio

# Development dependencies
uv add --dev black isort mypy flake8 pre-commit

Task Management (MANDATORY)

Before any coding, create/update:

TODO.md Example:

# TODO List

## Current Sprint
- [ ] Setup basic MCP server structure
- [ ] Implement ping/pong handler
- [ ] Add basic tool registration
- [ ] Write unit tests for handlers

## Completed
- [x] Project initialization with UV
- [x] Basic project structure setup

## Blocked/Questions
- [ ] Need to research MCP protocol version compatibility

TASKS.md Example:

# Detailed Task Breakdown

## Task: Setup Basic MCP Server Structure
**Status**: In Progress
**Priority**: High

### Subtasks:
1. [x] Create main.py with MCP server initialization
2. [ ] Add configuration management
3. [ ] Implement basic logging
4. [ ] Add error handling middleware

### Acceptance Criteria:
- Server can start without errors
- Basic logging is working
- Configuration can be loaded from environment

### Notes:
- Using uvicorn for ASGI server
- MCP protocol requires specific message format

Development Workflow

Incremental Implementation Steps

Step 1: Always Plan

# Before implementing, add TODO comments
# TODO: Implement MCP server initialization
# TODO: Add message handler registration
# TODO: Implement basic error handling

Read the full file on GitHub · 321 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. 7d ago First seen · 321 lines · 1,898 tokens per session scan A 5c2fadefd436

Subscribe to this mod's changes

global-standards is a cursor rule published in the GitHub repository Kenlan2022/mcp_servers_showcase (0 stars, last pushed 1y ago), licensed MIT. It adds 1,898 tokens to every session, about $0.0095 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.