Use this skill to discover tools, prompts, and resources exposed by configured Model Context Protocol (MCP) servers, select capabilities for a task, and run tools through a command-line interface or Gemini CLI. It also describes multi-server client patterns and configuration.
Manage Model Context Protocol (MCP) servers - discover, analyze, and execute tools/prompts/resources from configured MCP servers. Use when working with MCP integrations, need to discover available MCP capabilities, filter MCP tools for specific tasks, execute MCP tools programmatically, access MCP prompts/resources, or implement MCP client functionality. Supports intelligent tool selection, multi-server management, and context-efficient capability discovery.
Run score Not tested
See how to installReview the instructions the agent will receive before you install.
Skill for managing and interacting with Model Context Protocol (MCP) servers.
MCP is an open protocol enabling AI agents to connect to external tools and data sources. This skill provides scripts and utilities to discover, analyze, and execute MCP capabilities from configured servers without polluting the main context window.
Key Benefits:
Use this skill when:
MCP servers configured in .claude/.mcp.json.
Gemini CLI Integration (recommended): Create symlink to .gemini/settings.json:
mkdir -p .gemini && ln -sf .claude/.mcp.json .gemini/settings.json
See references/configuration.md and references/gemini-cli-integration.md.
npx tsx scripts/cli.ts list-tools # Saves to assets/tools.json
npx tsx scripts/cli.ts list-prompts
npx tsx scripts/cli.ts list-resources
Aggregates capabilities from multiple servers with server identification.
LLM analyzes assets/tools.json directly - better than keyword matching algorithms.
Primary: Gemini CLI (if available)
gemini -y -m gemini-2.5-flash -p "Take a screenshot of https://example.com"
Secondary: Direct Scripts
npx tsx scripts/cli.ts call-tool memory create_entities '{"entities":[...]}'
Fallback: mcp-manager Subagent
See references/gemini-cli-integration.md for complete examples.
Use Gemini CLI for automatic tool discovery and execution. See references/gemini-cli-integration.md for complete guide.
Quick Example:
gemini -y -m gemini-2.5-flash -p "Take a screenshot of https://example.com"
Benefits: Automatic tool discovery, natural language execution, faster than subagent orchestration.
Use mcp-manager agent when Gemini CLI unavailable. Subagent discovers tools, selects relevant ones, executes tasks, reports back.
Benefit: Main context stays clean, only relevant tool definitions loaded when needed.
LLM reads assets/tools.json, intelligently selects relevant tools using context understanding, synonyms, and intent recognition.
Coordinate tools across multiple servers. Each tool knows its source server for proper routing.
Core MCP client manager class. Handles:
.claude/.mcp.jsonCommand-line interface for MCP operations. Commands:
list-tools - Display all tools and save to assets/tools.jsonlist-prompts - Display all promptslist-resources - Display all resourcescall-tool <server> <tool> <json> - Execute a toolNote: list-tools persists complete tool catalog to assets/tools.json with full schemas for fast reference, offline browsing, and version control.
Method 1: Gemini CLI (recommended)
npm install -g gemini-cli
mkdir -p .gemini && ln -sf .claude/.mcp.json .gemini/settings.json
gemini -y -m gemini-2.5-flash -p "Take a screenshot of https://example.com"
Method 2: Scripts
cd .claude/skills/mcp-management/scripts && npm install
npx tsx cli.ts list-tools # Saves to assets/tools.json
npx tsx cli.ts call-tool memory create_entities '{"entities":[...]}'
Method 3: mcp-manager Subagent
See references/gemini-cli-integration.md for complete guide.
See references/mcp-protocol.md for:
Gemini CLI (Primary): Fast, automatic, intelligent tool selection
command -v geminigemini -y -m gemini-2.5-flash -p "<task>"Direct CLI Scripts (Secondary): Manual tool specification
npx tsx scripts/cli.ts call-tool <server> <tool> <args>mcp-manager Subagent (Fallback): Context-efficient delegation
The mcp-manager agent uses this skill to:
gemini command if availableThis keeps main agent context clean and enables efficient MCP integration.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Design interfaces by studying reference examples, setting visual rules, and balancing appearance with usability and accessibility. The skill also guides screenshot analysis, iterative design image generation, micro interactions, and documenting design decisions in project guidelines.
Use Google Gemini to analyze audio, images, videos, and PDFs, or generate and edit images. Get results such as timestamped transcripts, summaries, extracted tables, answers about media, and images made from prompts.
Use this skill to plan and build backend systems, from API design and authentication to database tuning, security, testing, deployment, and monitoring. It offers technology choices and practical checklists for turning requirements into production-ready services.
Use this skill to add authentication and authorization to TypeScript applications with Better Auth. It covers email and social sign-in, sessions, database setup, two-factor authentication, passkeys, and access rules, with guidance for several web frameworks.
Integrate Bunny.net services through their APIs to configure CDN pull zones, manage stored files and video, edit DNS records, and deploy edge scripts or containers. The skill also covers Shield protection, image optimization, and the credentials each service requires.
Use Puppeteer CLI scripts to automate browser tasks and inspect web pages. The skill can navigate, click, fill forms, capture screenshots, collect page data, monitor console and network activity, and measure performance including Core Web Vitals. Results are provided as JSON.