Discover Awesome MCP Servers

MCP Finder

A smart router that helps users discover the most relevant tools from an MCP catalog using natural language queries and AI-driven reranking. It utilizes hybrid search and intent analysis to select the best tool for a given task and explains the reasoning behind each choice.

turing-test-game

Enables interaction with the AnyAnyGame Turing test service via HTTP and WebSocket, exposing tools for auth, matching, messaging, and meme search.

molmcp

A graph-based codebase capability discovery engine for LLM agents, exposing indexed code symbols, signatures, and relationships over MCP to enable agents to find and use tools without guessing names.

local-llm-mcp

An MCP server that provides local, private, synchronous access to Ollama models for prompt answering, text classification, and model listing, without any file access or command execution.

xmit-mcp

Remote MCP server for the Transmit email platform, enabling email sending, contact management, template and campaign operations via natural language.

Oxenstierna

Provides access to the Swedish National Archives (Riksarkivet) through multiple APIs, enabling users to search, explore, and download digitized historical records and images.

TeamDesk MCP Server

MCP server for TeamDesk databases, enabling CRUD operations, search, and document generation via natural language.

Claude Code Toolkit

Maintenance, recovery, and observability for Claude Code. CLI + MCP server + dashboard.

Translations MCP Server

Enables automatic discovery and fast searching of translation files in projects, supporting partial/exact key-value matching with file watching and multiple translation file formats.

Structurizr DSL Debugger for Cursor

Here's a translation of the English text into Portuguese, along with some considerations for clarity and context: **Option 1 (More Literal):** "Servidor MCP para conectar ao DSL do Structurizer renderizado no navegador e retornar mensagens de erro referentes à análise sintática para o Cursor IDE." **Option 2 (Slightly More Natural):** "Servidor MCP para se conectar ao DSL do Structurizer, renderizado no navegador, e retornar mensagens de erro de análise sintática para o IDE Cursor." **Option 3 (Emphasizing the Purpose):** "Servidor MCP para permitir a conexão com o DSL do Structurizer, que é renderizado no navegador, e enviar mensagens de erro de análise para o IDE Cursor." **Explanation of Choices and Considerations:** * **MCP Server:** "Servidor MCP" is generally fine as it's likely an acronym or specific term. * **Connect to:** "Conectar a" or "Conectar-se a" are both valid. "Conectar-se a" is slightly more formal. * **Structurizer DSL:** "DSL do Structurizer" is a direct translation and works well. * **Rendered in the browser:** "Renderizado no navegador" is the standard translation. * **Return error messages regarding parsing:** This is where the phrasing can be improved. * "Mensagens de erro referentes à análise sintática" (Option 1) is very literal and a bit clunky. * "Mensagens de erro de análise sintática" (Option 2) is more concise and common. * "Enviar mensagens de erro de análise" (Option 3) focuses on the action of sending the messages. * **Cursor IDE:** "IDE Cursor" is fine, assuming "Cursor" is the name of the IDE. **Recommendation:** I would recommend **Option 2** or **Option 3** as they are more natural-sounding in Portuguese. The best choice depends on the specific context and the desired level of formality. If you want to emphasize the *purpose* of the server, Option 3 is a good choice. If you want a more direct and concise translation, Option 2 is better.

insight-mcp

Enables hybrid document search (BM25 and dense) over a configurable corpus via MCP tools, returning passages and sources for AI agents to cite in answers.

linkedin-engine

Enables running the entire LinkedIn sales motion inside Claude Code, including content creation, audience warming, outreach, and booking calls.

Google Drive MCP Server

An actively maintained fork of the official Google Drive MCP server that enables users to search, download, and read files via the Google Drive API. It features improved OAuth token management and automatically converts Google Workspace documents into formats like Markdown and CSV for easier LLM consumption.

mcp-context-guard

Compresses tool outputs, manages token budgets, deduplicates content, and filters by relevance to optimize context window usage for AI agents.

AutoDL MCP Server

Manages AutoDL GPU cloud instances, including lifecycle management, SSH operations, file transfer, and GPU monitoring.

autoMate

A personal AI assistant server that provides MCP tools for notes, files, reminders, memory, shell, browser, and 30+ SaaS integrations, enabling AI clients to access and manage your data across sessions.

lunar

Browser-based geometry processing server that enables AI agents to create geometry, run analysis and operators, inspect results, and take screenshots via MCP.

zxkol

ZXKOL transforms tasks like "finding Douyin beauty influencers with 100k–500k followers" into simple tool calls—eliminating the need to write web scrapers or integrate platform-specific SDKs.

OpenWeatherMap MCP Server

Provides weather data, forecasts, air quality, and location services via OpenWeatherMap API integration.

Databricks MCP Server by CData

Databricks MCP Server by CData

arc-devtools-mcp

MCP server enabling AI agents to control and inspect Chrome/Arc browsers via DevTools, with Arc-specific tab reuse.

Tencent Cloud COS MCP Server

Enables interaction with Tencent Cloud Object Storage (COS) through MCP protocol. Supports file upload, download, deletion, listing objects, and generating temporary signed URLs for cloud storage management.

mcp-vision-bridge

Gives text-only LLM coding agents vision by routing images to a multimodal model and returning detailed textual descriptions. Supports local files, URLs, clipboard, base64, raw bytes, and multiple providers like OpenAI, Anthropic, and Gemini.

mcp-api-server

FastAPI-based MCP server integrating YOLOv8 object detection and embedding services, enabling AI agents to analyze images via the Model Context Protocol.

Brazilian Dev MCP

MCP server with tools for Brazilian data like CPF, CNPJ, CEP validation and generation, and currency quotes.

ncloud-mcp-server

Enables natural language management of Naver Cloud Platform infrastructure, covering over 60 services and 1,000+ API tools.

Trek Agent Control

Enables AI agents to securely read, plan, and sync real trips from the Trek WeChat mini-program via authenticated remote MCP, supporting tools for itinerary management, reservations, and file attachments.

tokrepo-mcp-server

Search and install 200+ curated AI assets (skills, prompts, MCP configs, scripts, workflows) from TokRepo's open registry. Works with Claude Code, Cursor, Codex, and any MCP-compatible client.

baserCMS MCP Server

Model Context Protocol server implementation for operating baserCMS that enables GitHub Copilot and other agent modes to interact with baserCMS through its API.

catalogue-api

Provides a read-only API over a book catalogue, offering tools to search books, retrieve book details and series, and inspect provenance and source agreement data.