engineering-mcp

Design, implement, and audit MCP servers with Rust and JSON Schema.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/Git-Fg/taches-principled-light --skill engineering-mcp
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: engineering-mcp
Source: https://github.com/Git-Fg/taches-principled-light/tree/main/skills/engineering-mcp
Command: npx skills add https://github.com/Git-Fg/taches-principled-light --skill engineering-mcp

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill assists in the design, implementation, and auditing of Model Context Protocol (MCP) servers, providing comprehensive support for tool decomposition, JSON Schema creation, Rust implementation, client development, and quality assessment.

Core Features & Use Cases

  • Design: Decompose MCP tools, define output contracts, create error codes, and handle security and capability negotiation.
  • Schema: Write LLM-friendly JSON Schemas for MCP tools, adhering to constraint discipline and best practices.
  • Implementation: Implement MCP servers in Rust using rmcp and schemars, managing server lifecycles and error handling.
  • Client Development: Develop MCP clients for agents, ensuring proper tool consumption and error handling.
  • Quality Assessment: Evaluate existing MCP servers against a Claude-Optimal rubric, identifying areas for improvement.

Quick Start

Use the engineering-mcp skill to design a new MCP server for managing user sessions.

Frequently Asked Questions about engineering-mcp

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I design an MCP server with proper tool decomposition and JSON Schema?

Designing an MCP server requires decomposing tools into manageable units, defining output contracts, and writing LLM-friendly JSON Schemas that adhere to constraint discipline for robust server infrastructure.

What is the best way to implement a scalable MCP server in Rust?

Implementing a scalable MCP server in Rust involves using the rmcp and schemars libraries to manage server lifecycles, handle errors efficiently, and ensure secure capability negotiation.

How do I audit an existing MCP server for quality and LLM compatibility?

Auditing an MCP server involves evaluating it against a Claude-Optimal rubric to assess tool decomposition, JSON Schema compliance, and error handling, identifying areas for improvement.

Do I need deep Rust knowledge to develop MCP clients for agents?

Yes, developing MCP clients for agents requires deep knowledge of the MCP protocol and Rust programming to ensure proper tool consumption, manage server lifecycles, and handle errors correctly.

How does capability negotiation work when building MCP servers?

Capability negotiation in MCP servers involves defining security parameters and output contracts during the design phase to ensure robust, scalable, and secure communication between clients and tools.

What should I include in JSON Schemas to make MCP tools LLM-friendly?

Creating LLM-friendly JSON Schemas for MCP tools requires adhering to constraint discipline, defining clear output contracts, and following best practices to ensure accurate tool decomposition and consumption.