1,095 boosters for "mcp" — open source, verified from GitHub, ready to install
A comprehensive Figma MCP system prompt that enables AI development tools (Claude, Cursor, Windsurf) to automatically extract design systems, components, and pixel-perfect code directly from Figma designs. Developers using design-to-code workflows benefit from automated analysis without manual extraction.
Starwind UI MCP Server integrates the Starwind UI component library with AI coding assistants (Cursor, Windsurf, Claude) via the Model Context Protocol, enabling developers to leverage pre-built UI components in their projects seamlessly.
An MCP server that automates HWPX (Korean word processor) document operations including loading, editing, validation, and batch text processing for users working with Korean office documents.
Enables efficient searching of Zotero libraries through Python code execution, avoiding context crashes while providing multi-strategy search with automatic deduplication. Ideal for researchers and developers who need comprehensive, safe access to large reference collections.
FlyonUI MCP is a Model Context Protocol server that integrates FlyonUI components with Claude, enabling AI-assisted UI development and design workflows.
A ToDo List MCP server built with Fireproof that integrates persistent task management into Claude Desktop and Claude Code. Useful for developers who want to manage tasks within their AI assistant workflow.
"description": "Lightweight knowledge graph for AI-assisted development. Impact analysis, code search, dependency tracking, and context generation.", "email": "freepeak@example.com" "homepage": "https://github.com/FreePeak/LeanKG",
Blockscout MCP Server enables AI agents and automation tools to query blockchain data directly, including account balances, transaction history, and smart contract interactions. Developers building AI-powered blockchain applications, trading bots, and automation tools benefit from seamless blockchain data access.
Heuristic scoring (no AI key configured).
A demo MCP server implementation showing best practices for building Claude integrations, designed as a learning resource rather than a production tool. Useful for developers learning MCP server architecture and TypeScript integration patterns.
A TUI-style MCP server that enables Claude and other AI models to ask users questions interactively through a web interface, useful for developers building interactive AI applications that need user input during execution.
"description": "Give Claude eyes and hands — screen capture and interaction for full-auto workflows", "name": "Kyle Zobell", "url": "https://gitlab.com/3spky5u"
"name": "autotask-mcp", "version": "2.18.0", "description": "MCP (Model Context Protocol) server for Kaseya Autotask PSA integration",
The Decodo MCP Server enables Claude to interface with proxy management and web scraping services, offering IP rotation, rate limiting, and residential proxy capabilities for developers building scraping infrastructure.
"name": "semantic-search", "description": "Search your local documents with natural language. Index folders of PDFs, Word docs, markdown, and more — then ask questions in English or German and get answers with source citations.", "name": "Omar Drljevic"
A testing framework for Model Context Protocol (MCP) servers with CLI tools and dual transport support (SSE/stdio). Developers building or integrating MCP servers can use this to validate their implementations against protocol standards.
"name": "context-provider", "description": "MCP context & instinct engine — learned rules from sessions with confidence scoring. Provides tool-aware context injection and 6 MCP tools.", "version": "2.0.0-alpha.4",
"name": "claude-code-toolkit", "name": "Scott Spence" "description": "Productivity and ecosystem tools for Claude Code",
An AI-powered MCP server that enables Claude to automate browser interactions using Playwright, allowing developers to build intelligent automation workflows directly within Claude and Cursor. Ideal for developers needing web automation, testing, and AI-driven browser tasks.
<!-- AIOS-GENERATED: orchestrator-agents v1 --> You are the Planner. Clarify scope, risks, dependencies, and execution order before code changes. Produce a concrete plan that an implementer can follow. Output a single JSON object (no surrounding text) that conforms to .
<!-- AIOS-GENERATED: orchestrator-agents v1 --> You are the Implementer. Own code changes inside the agreed file scope and report concrete results. Prefer minimal diffs and include verification evidence. Output a single JSON object (no surrounding text) that conforms to .
<!-- AIOS-GENERATED: orchestrator-agents v1 --> You are the Reviewer. Review correctness, regressions, maintainability, and test coverage. Do not modify code; report findings and recommendations. Output a single JSON object (no surrounding text) that conforms to .
