MCP-серверы
Открытый реестр серверов Model Context Protocol. Находите инструменты, ресурсы и промпты для ИИ-агентов по категории, типу подключения и сценарию использования.
Некоторые описания переведены автоматически в рамках пилота и пока не проверены редактором.
Серверы
177
Инструменты
471
Категории
11
Участники
155
Auth0's official MCP server that connects AI agents to the Auth0 Management API. Lets developers create and configure applications, deploy Actions, manage APIs and connections, and query tenant logs using natural language. Runs locally with interactive tenant authentication and stores access tokens in the system keychain so the model never sees them directly, supporting secure Auth0 administration.
A Model Context Protocol server for Google Drive that lets AI assistants list, search, and read files stored in Drive, with automatic export of Google Docs, Sheets, Slides, and Drawings to readable formats. Authenticates via OAuth 2.0 and exposes Drive files as MCP resources so agents can ground their answers in your documents without copying data into chat first.
Официальный MCP-сервер GitHub, напрямую подключающий AI-инструменты к платформе GitHub. Позволяет AI-агентам управлять репозиториями, issues, pull requests, ветками, файлами, workflow GitHub Actions и безопасностью кода. Поддерживает удалённый режим через OAuth и локальный запуск через Docker или бинарный файл с точной настройкой набора инструментов.
Official Figma MCP server that brings design context directly into AI coding workflows. Provides tools for extracting design information, generating code from Figma selections, taking screenshots, creating and editing Figma files, generating diagrams from Mermaid syntax, searching design systems, managing Code Connect mappings, and uploading assets. Supports both remote (OAuth) and local (desktop app) server modes.
MCP server for Gmail that lets AI agents read, search, draft, and send email, manage labels, and organize the inbox via the Gmail API with OAuth. Handy for triaging mail, drafting replies, and automating routine inbox workflows from an AI client.
MCP server for Google Calendar that lets AI agents view, create, update, and delete events, check availability across calendars, and schedule meetings via the Calendar API with OAuth. Useful for natural-language scheduling and calendar management.
Official Hugging Face MCP Server that connects AI assistants directly to the Hugging Face Hub ecosystem. Provides tools for searching and retrieving models, datasets, and research papers, running inference on thousands of Gradio-powered AI applications (Spaces), and accessing the full Hub API. Supports remote HTTP-streaming via https://huggingface.co/mcp with OAuth or Bearer token auth, as well as local stdio deployment. Works with Claude, Gemini CLI, VS Code, Cursor, and any MCP-compatible client.
Official Atlassian Rovo MCP Server — a cloud-based bridge between Atlassian Cloud and any MCP-compatible AI tool. Enables AI agents to search, summarize, create, and update Jira issues, Confluence pages, and Compass components in real-time. Uses OAuth 2.1 or API token authentication, respects existing user permissions, and supports remote HTTP-streaming as well as local stdio via the mcp-remote proxy. Works with Claude, GitHub Copilot, Gemini CLI, VS Code, Cursor, and ChatGPT.
Official HubSpot MCP server connecting AI tools to the HubSpot CRM. Enables agents to read and manage contacts, companies, deals, and tickets, search the CRM, and create engagements such as notes and tasks. Honors HubSpot scopes and rate limits via OAuth.
MCP server for Google Sheets. Lets AI agents read and write cell ranges, create and update spreadsheets and tabs, append rows, and apply formatting via the Sheets API with OAuth. Useful for lightweight data entry, reporting, dashboards, and automating spreadsheet-driven workflows.
MCP server for Salesforce that lets AI agents query and modify CRM data using SOQL, manage standard and custom objects (Accounts, Contacts, Opportunities, Cases), describe object metadata, and execute Apex anonymous blocks. Supports both production and sandbox orgs via OAuth or username-password flows.
MCP server for Dropbox cloud storage. Lets AI agents list folders, upload and download files, search content, move and delete items, and create shared links via the Dropbox API with OAuth. Useful for document workflows, backups, and giving agents access to files stored in Dropbox.
Cloudinary's official MCP servers for managing media through conversational AI. Cover the full media workflow: uploading and transforming images and videos, organizing assets with structured metadata, configuring processing pipelines, and running AI-powered content analysis. Available as remote OAuth endpoints or local npx processes across several focused servers (asset management, environment config, structured metadata, and analysis).
Honeycomb's MCP server that lets AI assistants query and analyze observability data, including events, traces, alerts (triggers), and boards. Agents can run queries against datasets, inspect columns and schemas, and cross-reference production behavior with the codebase to investigate incidents. Connects to Honeycomb via API key or OAuth.
Automattic's MCP server that connects AI assistants such as Claude Desktop to WordPress sites. Supports multiple authentication methods (OAuth 2.0, JWT, and application passwords) and exposes the WordPress REST and WP-CLI capabilities so agents can read and manage posts, pages, media, and site settings through natural language.
Skills и MCP-серверы
в чём разница?Skillsописывают, что делать
Skill объединяет инструкции, пример промпта и рекомендуемые модели, чтобы агент стабильно выполнял задачу. Skills добавляют знания, а не новые подключения.
MCP-серверыописывают, как подключиться
MCP-сервер расширяет возможности агента, подключая его к реальным системам: базам данных, API и файлам. MCP добавляет подключения и действия, а не инструкции к задаче.
Простое правило: выбирайте Skill, когда модели нужно хорошо выполнить задачу, и MCP-сервер, когда ей нужен доступ к инструменту или системе. Их можно сочетать: Skill может использовать инструменты MCP-сервера.
Создали MCP-сервер?
Добавьте его в открытый реестр, который поддерживает сообщество.