mcp-integration

mcp-integration is a cursor rule for Cursor from r-huijts/ethics-check-mcp. It costs 0 tokens per session (641 once invoked), scanned A, original, MIT.

Implementation rules for building an MCP server with the official MCP software kit. MCP is a standard way for an AI assistant to discover and call tools provided by another program.

In plain words
What is it for?
Use them when implementing or extending an MCP server, especially one that communicates with Claude Desktop through standard input and output.
Why use it?
They provide a consistent structure for registering tools, validating inputs, running the requested operation, and formatting responses.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit Use them when implementing or extending an MCP server, especially one that communicates with Claude Desktop through standard input and output.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/r-huijts/ethics-check-mcp/mcp-integration
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/r-huijts/ethics-check-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 mcp-integration

README.md
[![agentmods](https://agentmods.dev/badge/rules/r-huijts/ethics-check-mcp/mcp-integration/github.svg)](https://agentmods.dev/rules/r-huijts/ethics-check-mcp/mcp-integration)
Your own site
<a href="https://agentmods.dev/rules/r-huijts/ethics-check-mcp/mcp-integration"><img src="https://agentmods.dev/badge/rules/r-huijts/ethics-check-mcp/mcp-integration/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for mcp-integration

Your own site · 80×15
<a href="https://agentmods.dev/rules/r-huijts/ethics-check-mcp/mcp-integration"><img src="https://agentmods.dev/badge/rules/r-huijts/ethics-check-mcp/mcp-integration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 641 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.00641
Opus 5 $0.00000 $0.00320
Sonnet 5 $0.00000 $0.00128
Haiku 4.5 $0.00000 $0.00064

Measured 9d ago against content hash 166b62962d40, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

mcp-integration 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 9d 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/mcp-integration.mdc · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Integration Patterns

MCP Server Architecture

This project implements a Model Context Protocol (MCP) Server using the official MCP SDK. The server follows standard MCP patterns for tool registration and execution.

Core MCP Components

Server Initialization

  • Server Instance: Created in src/index.ts with name "ethics-check" and version "0.1.0"
  • Transport: Uses StdioServerTransport for communication with Claude Desktop
  • Capabilities: Declares tools capability to expose ethical oversight functions

Tool Registration Pattern

Tools are registered via ListToolsRequestSchema handler in src/index.ts:

{
  name: "tool_name",
  description: "Tool description for Claude",
  inputSchema: {
    type: "object",
    properties: { /* JSON Schema */ },
    required: ["required_fields"]
  }
}

Tool Execution Pattern

Tool calls are handled via CallToolRequestSchema handler:

  1. Parameter Validation: Check required fields and types
  2. Input Transformation: Convert MCP args to typed interfaces
  3. Tool Execution: Call implementation function
  4. Response Formatting: Return structured markdown content

MCP-Specific Implementation Details

Input/Output Interfaces

Each tool defines TypeScript interfaces in src/tools/:

  • ToolNameInput: Parameters expected from MCP client
  • ToolNameOutput: Structured response from tool logic
  • Conversion between MCP args and typed inputs happens in src/index.ts

Error Handling

  • McpError: Use official MCP error types (ErrorCode.InvalidParams, ErrorCode.MethodNotFound)
  • Validation: Check required parameters before tool execution
  • Graceful Degradation: Fallback responses when AI parsing fails

Response Formatting

  • Content Type: Always return text content type
  • Markdown Format: Use structured markdown for readable responses
  • Consistent Structure: Headers, sections, and formatting patterns across tools

Read the full file on GitHub · 68 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. 9d ago First seen · 68 lines · 0 tokens per session scan A 166b62962d40

Subscribe to this mod's changes

mcp-integration is a cursor rule published in the GitHub repository r-huijts/ethics-check-mcp (5 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 641 tokens. 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.