Discover Awesome MCP Servers

SkillsGuard

Static security scanner for AI agent skill packages that detects malicious SKILL.md files and bundled scripts before they run.

sql-sop-mcp

MCP server that integrates sql-sop SQL linter into LLM clients, enabling linting SQL queries and listing lint rules via chat tools.

depsonar

Comprehensive dependency audit MCP server supporting 9 languages and 23 tools for scanning, updating, security auditing, and migration detection.

MCP TypeScript SDK

A toolkit for building Model Context Protocol servers and clients that provide standardized context for LLMs, allowing applications to expose resources, tools, and prompts through stdio or Streamable HTTP transports.

Task MCP Server

A simple task management server that enables users to add, list, complete, and delete tasks through natural language interactions in Claude Desktop.

Slack MCP Server

An MCP server that enables searching for messages and listing channels within a Slack workspace. It provides tools to retrieve channel history and filter messages based on text matching and date ranges.

artifactory-mcp

Enables AI assistants to query Maven artifacts in JFrog Artifactory by reusing credentials from ~/.m2/settings.xml and providing tools like getting latest stable versions, listing artifacts, and checking dependency updates.

Zefix MCP

Enables AI assistants to search the Swiss Central Business Name Index (Zefix) for companies by name or UID, with optional filters, and retrieve full company details including address, legal form, history, and representatives.

obsidian-mcp-server

Connects Claude.ai to your local Obsidian vault for full CRUD access, search, and daily note creation via the Model Context Protocol.

ToolRoute

Intelligent routing layer for AI agents — recommends the best MCP server and LLM for any task, scored on 132+ real benchmark executions.

国金QMT-MCP

A modular quantitative trading assistant that integrates with XTQuant/QMT trading platform, enabling AI-assisted trading strategy generation, real-time trade execution, and performance backtesting.

Axion Planetary MCP

Enables MCP clients to access Google Earth Engine's satellite imagery and geospatial analysis capabilities. Provides tools for vegetation analysis, crop classification, disaster monitoring, and interactive map creation using petabytes of satellite data.

Supply Chain Disruption Monitor

MCP server that exposes tools for monitoring supply chain disruptions, including vessel positions, port weather, congestion, and news. Includes an AI agent that synthesizes these sources to assess route risks.

ActTrace

MCP server for EU AI Act compliance, providing risk classification of AI features and Article 50 transparency notices.

wiz-light-mcp

MCP server for controlling WiZ smart lights locally via UDP: discover bulbs, power control, color, temperature, and scenes.

Design-Pattern-MCP

Provides design pattern templates and anti-pattern guidance to AI coding agents for correct pattern implementation.

whitelabel-fleet-mcp

Exposes file, shell, git, and memory tools from a host Mac to remote Claude clients (e.g., iPhone) via HTTPS and Tailscale, enabling full coding capabilities on the go.

Multi Agent Orchestrator MCP

Coordinates specialized agents (Architecture, Quality, Cloud, Prompt) to plan, build, test, and deploy applications with self-healing capabilities, authentication, and analytics for autonomous software engineering workflows.

mcp-youtube

High-efficiency YouTube MCP server: Get token-optimized, structured data for your LLMs using the YouTube Data API v3.

DevEyes

DevEyes is a Model Context Protocol (MCP) server that captures screenshots from your local development environment and automatically optimizes them for LLM consumption.

OMNI-Sales

Servidor MCP de Vendas

@looppause/mcp

Pauses AI agent execution and routes approval requests to humans via Slack or email, with cryptographically signed proof of the human's decision.

linkedin-mcp

Enables AI agents to publish posts, images, comments, and reactions to LinkedIn as the authenticated user, with built-in safety features like daily budgets and deduplication.

open-museum-mcp

Federated, license-verified search across open-access museum collections — currently The Met, Cleveland, AIC, Wikimedia Commons, and Europeana, with more being added. Strict-default-deny rights gate accepts only CC0 / Public Domain Mark, returning reuse-safe artwork with citations in three styles.

battery-mcp

Enables LLMs to verify the novelty and validity of invented battery materials, with support for searching and validating against a materials database.

Real Browser MCP

Provides a real browser that bypasses bot detection (Cloudflare, Turnstile) for AI agents, enabling navigation, clicking, typing, screenshots, and data collection through MCP tools.

mcp-playwright-scraper

An MCP server that scrapes content from web pages, including JavaScript-heavy sites, and converts it into high-quality Markdown. It leverages Playwright for headless browser automation and Pypandoc for clean content conversion.

mcp-api-tester Tools & Interfaces

Here are a few possible translations, depending on the specific nuance you want to convey: * **Opção 1 (Mais direta):** Servidor MCP para LLM para testar API * **Opção 2 (Um pouco mais descritiva):** Servidor MCP para LLM para teste de API * **Opção 3 (Com foco no propósito):** Servidor MCP para LLM usado para testar APIs **Explanation of Choices:** * **MCP:** It's likely best to leave "MCP" as is, assuming it's an acronym or specific term. If you know what it stands for, you could replace it with the full term in Portuguese if appropriate. * **LLM:** Similarly, "LLM" (Large Language Model) is often used as is, even in Portuguese contexts. You *could* translate it to "Modelo de Linguagem Grande" but it's less common. * **API:** "API" is also commonly used in Portuguese without translation. * **"para" vs. "usado para":** "Para" is a direct translation of "for." "Usado para" (used for) adds a bit more emphasis on the purpose of the server. * **"teste de API" vs. "testar API":** Both are correct. "Teste de API" is a noun phrase ("API test"), while "testar API" is a verb phrase ("to test API"). Therefore, the best option depends on the context. If you want a simple and direct translation, **Option 1** is fine. If you want to emphasize the purpose, **Option 3** might be better.

Rovodev MCP Tool

Integrates the Atlassian Rovo Dev CLI with the Model Context Protocol, allowing AI assistants to perform deep code analysis using Rovo Dev's large context capabilities. It enables features like repository-wide queries, file-specific analysis, and specialized coding modes through a standard MCP interface.

md-redline

Inline review comments for markdown specs and design docs. Agents request human review mid-task via MCP and pause until you send feedback.