mcp-server-expert

mcp-server-expert is a cursor rule for Cursor from onmax/nimiq-mcp. It costs 1,020 tokens per session, scanned A, original, MIT.

A set of guidance for building MCP servers, which are small programs that let AI applications access tools and data through a common protocol.

In plain words
What is it for?
Designing MCP server architecture, implementing resources and reusable prompts, negotiating protocol versions, and supporting transports such as standard input/output or HTTP.
Why use it?
It helps developers follow the protocol, handle connections and capabilities correctly, and structure resources and prompts consistently.

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/onmax/nimiq-mcp/mcp-server-expert
Clone the repo
git clone --depth 1 https://github.com/onmax/nimiq-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-server-expert

README.md
[![agentmods](https://agentmods.dev/badge/rules/onmax/nimiq-mcp/mcp-server-expert.svg)](https://agentmods.dev/rules/onmax/nimiq-mcp/mcp-server-expert)
Your own site
<a href="https://agentmods.dev/rules/onmax/nimiq-mcp/mcp-server-expert"><img src="https://agentmods.dev/badge/rules/onmax/nimiq-mcp/mcp-server-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,020 This file is loaded in full into every session.
When invoked 1,020 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 $0.01020 $0.01020
Opus 5 $0.00510 $0.00510
Sonnet 5 $0.00204 $0.00204
Haiku 4.5 $0.00102 $0.00102

Measured 5d ago against content hash 1332295403b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-server-expert 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 5d 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-server-expert.mdc · 166 lines

How it starts

The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Server Development Expert

You are an expert in developing Model Context Protocol (MCP) servers with deep knowledge of the latest protocol specifications, best practices, and implementation patterns.

Protocol Understanding

Core Architecture

  • MCP Servers: Lightweight programs that expose specific capabilities through the standardized Model Context Protocol
  • Client-Server Architecture: MCP follows a 1:1 connection pattern where MCP clients maintain connections with MCP servers
  • MCP Hosts: Applications like Claude Desktop, IDEs, or AI tools that access data through MCP
  • Transport Layer: Communication mechanism between clients and servers (stdio, HTTP, WebSocket)

Latest Protocol Version

  • Follow the latest MCP specification (Version 2025-06-18)
  • Stay updated with protocol changes and deprecations
  • Implement proper version negotiation and capability detection

Core MCP Concepts

Resources

  • Expose data and content from servers to LLMs
  • Implement proper resource discovery and retrieval
  • Use appropriate MIME types and metadata
  • Support efficient caching and updates

Prompts

  • Create reusable prompt templates and workflows
  • Implement dynamic prompt generation based on context
  • Support parameterized prompts with proper validation
  • Enable prompt discovery and documentation

Tools

  • Enable LLMs to perform actions through your server
  • Implement proper input validation and error handling
  • Design idempotent operations where possible
  • Provide clear tool descriptions and parameter schemas

Sampling

  • Allow servers to request completions from LLMs
  • Implement proper context management for sampling requests
  • Handle sampling responses and error cases gracefully

Development Best Practices

Server Implementation

// Use official MCP SDKs when available
import { Server } from '@modelcontextprotocol/sdk/server/index.js';
import { StdioServerTransport } from '@modelcontextprotocol/sdk/server/stdio.js';

// Implement proper initialization and cleanup
const server = new Server(
  {
    name: 'my-mcp-server',
    version: '1.0.0',
  },
  {
    capabilities: {
      resources: {},
      tools: {},
      prompts: {},
    },
  }
);

Read the full file on GitHub · 166 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. 5d ago First seen · 166 lines · 1,020 tokens per session scan A 1332295403b6

Subscribe to this mod's changes

mcp-server-expert is a cursor rule published in the GitHub repository onmax/nimiq-mcp (4 stars, last pushed 10mo ago), licensed MIT. It adds 1,020 tokens to every session, about $0.0051 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.