mcp▌

Persistent, searchable memory system for agents to store and retrieve architectural decisions, patterns, and project knowledge. \n \n Provides four core MCP tools: memory_search for querying by text/type/tags, memory_write to record decisions and patterns, memory_read to retrieve specific entries, and memory_stats for usage analytics \n Runs as an MCP server that syncs with project documentation, enabling long-term knowledge retention across agent sessions \n Includes a standalone dashboard (por

Interactive UIs for MCP tools that run inside Claude Desktop and other MCP-enabled hosts. \n \n Combines an MCP tool (called by the LLM) with an HTML resource (renders the UI) linked via _meta.ui.resourceUri \n Supports React with useApp hook, vanilla JS, Vue, Svelte, Preact, and Solid; clone the SDK repo to access working templates and API reference for each framework \n Requires CSP configuration in resource contents for all network requests, including localhost; handlers must be registered be

Search and stream TV shows, anime, and variety content across multiple sources with optional casting to Xiaomi or Android TVs. \n \n Searches multiple source sites for shows, anime, short dramas, and variety programs with pagination support \n Supports casting to Xiaomi TVs and Android TVs (via TvBox) when configured with device IP environment variables \n Some sources return webpage URLs instead of direct playable links; use curl to extract actual .m3u8 or .mp4 addresses \n Search operations ma

Control and query Home Assistant smart home devices via MCP protocol. \n \n Supports device control commands including turn on/off, light brightness adjustment, and fan speed control with area and domain filtering \n Query live device states and context across your entire Home Assistant instance \n Requires MCP server integration enabled in Home Assistant with HASS_BASE_URL and HASS_ACCESS_TOKEN environment variables configured \n Commands target devices by name, area, or domain for flexible mul

This skill provides access to 1200+ MCP (Model Context Protocol) servers - standardized tools that extend AI capabilities. Connect Claude to filesystems, databases, APIs, and document processing tools.

Build and debug MCP servers and clients connecting AI systems with external tools and data sources. \n \n Supports TypeScript (Node.js SDK) and Python (FastMCP) for implementing tool handlers, resource providers, and prompt templates with Zod or Pydantic schema validation \n Covers three transport layers: stdio (local), HTTP, and SSE (streaming), with JSON-RPC 2.0 protocol compliance and interactive debugging via the MCP inspector \n Includes scaffolding workflows, schema design patterns, and er

Jira and Confluence automation via MCP protocol with JQL/CQL queries, ticket management, and sprint workflows. \n \n Supports querying Jira issues with JQL filters, creating and updating tickets with custom fields, and managing sprints and backlogs \n Enables searching, creating, and editing Confluence pages using CQL syntax with space and content management \n Includes authentication patterns for OAuth 2.0, API tokens, and PAT credentials with permission scope validation \n Provides reference g

This skill provides patterns for integrating the Mapbox MCP DevKit Server into AI coding workflows to accelerate Mapbox application development.

Comprehensive guide for building high-quality MCP servers that enable LLMs to interact with external services. \n \n Four-phase workflow covering research, implementation, review, and evaluation with detailed checklists and best practices for each stage \n Agent-centric design principles including workflow optimization, context efficiency, actionable error messages, and evaluation-driven development \n Language-specific implementation guides for Python (FastMCP) and Node/TypeScript with SDK docu

Generate production-ready MCP servers in Ruby using the official SDK with complete project scaffolding. \n \n Generates a full project structure with tools, prompts, resources, tests, and configuration files following Ruby conventions \n Includes input/output schemas, tool annotations, and structured content support for type-safe MCP implementations \n Provides example tools (greet, calculate), prompts (code review), and resources with comprehensive test coverage using Minitest \n Supports stdio