skills.rest
krzemienski
krzemienskiCOMMUNITY
Explore all skills by this author →
Website𝕏@nkrzemienskiGitHub

mcp-discovery

Compute domain-driven MCP recommendations from project specifications with tiered policies.

2|Updated Sep 30, 2025
Search Tags:#project setup#mcp#ai tools#health check#domain analysis#server recommendation#fallback
One-click install
npx skills add https://github.com/krzemienski/shannon-framework --skill mcp-discovery
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: mcp-discovery
Source: https://github.com/krzemienski/shannon-framework/tree/main/shannon-plugin/skills/mcp-discovery
Command: npx skills add https://github.com/krzemienski/shannon-framework --skill mcp-discovery

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill eliminates the guesswork in selecting the right Model Context Protocol (MCP) servers for your project. It provides quantitative, domain-driven recommendations, ensuring you always have the optimal AI tools configured for maximum efficiency.

Core Features & Use Cases

  • Domain-to-MCP Mapping: Analyzes project domain percentages (Frontend, Backend, Database, etc.) to recommend appropriate MCP servers (e.g., Puppeteer for Frontend-heavy projects).
  • Tiered Recommendations: Prioritizes MCPs into Mandatory, Primary, Secondary, and Optional tiers with clear rationale, guiding your setup.
  • Health Checking & Fallbacks: Generates workflows to check MCP health and provides graceful fallback chains for unavailable tools, ensuring continuous operation.
  • Use Case: After analyzing your project specification, use this Skill to automatically get a prioritized list of MCPs, their setup instructions, and health checks, ensuring your AI environment is perfectly tailored to your needs.

Quick Start

Use mcp-discovery to recommend MCPs for a project with Frontend 60%, Backend 30%, Database 10%.

Frequently Asked Questions about mcp-discovery

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

FAQPage Schema
How do I choose the right MCP servers for my project?▼

MCP server selection depends on your project's domain breakdown. mcp-discovery analyzes domain percentages (Frontend, Backend, Database, etc.) and recommends appropriate servers in tiered priority levels—Mandatory, Primary, Secondary, Optional—with clear rationale so you configure only what your project needs.

What is domain-driven MCP recommendation and why does it matter?▼

Domain-driven MCP recommendation maps your project's technical composition to specialized Model Context Protocol servers. It ensures your AI tools align with where you actually spend development effort, eliminating mismatched or redundant configurations.

How do I set up health checks and fallbacks for MCP servers?▼

mcp-discovery generates health-check workflows and graceful fallback chains after analyzing your project specification. These workflows verify server availability and route requests to backup servers automatically, keeping your AI environment operational if a primary server becomes unavailable.

Can I use MCP recommendations for projects with mixed Frontend, Backend, and Database components?▼

Yes. mcp-discovery is designed for projects with quantified domain breakdown across Frontend, Backend, Database, and other components. It applies a deterministic, threshold-based policy to generate an actionable MCP plan tailored to your exact composition.

What information do I need before using MCP discovery?▼

You need your project specification with domain percentages—how much of your project is Frontend-focused, Backend-heavy, Database-intensive, etc. mcp-discovery uses these percentages to compute precise, threshold-based server recommendations and setup instructions.

Related Skills

Explore More Software Engineering Skills→
krzemienskikrzemienski
2

spec-analysis

Analyze specifications into 8-dimensional Shannon-based complexity scores and domain percentages.

Community
Intermediate
Snowflake-LabsSnowflake-Labs
12

read-ors-configuration

A concise summary of your roleplay character: name,</name> personality, and/or behavior, formatted as a single string sentence. Typically不超过50字，此处省略

Official
Intermediate
locdinh209locdinh209

mcp-management

Manage MCP servers and execute tools, prompts, and resources.

Community
Advanced
saleshandysaleshandy
1

operations-audit

Diagnose cold-email sending health from MCP data and generate a prioritized fix list.

Official
Advanced