MCP-серверы

The official MCP reference and test server demonstrates tools, resources, prompts, sampling, and protocol capabilities for MCP client development.

MCP server that provides access to Wikipedia content. Lets AI agents search articles, fetch full or summarized page content, and resolve references, giving models reliable, citable background knowledge for research and question answering.

Reference MCP server for Git repository operations. Provides tools to read, search, and manipulate Git repositories including viewing commit history, diffs, branches, file contents at specific revisions, and repository status. Enables AI agents to understand code changes and navigate version history without direct filesystem access.

Provides persistent memory capabilities through a knowledge graph stored in a local JSON file. Enables AI agents to create, read, update, and delete entities and their relationships. Useful for maintaining context across conversations, storing user preferences, and building structured knowledge bases that persist between sessions.

Reference MCP server providing time and timezone conversion capabilities. Enables AI agents to get the current time in any timezone, convert between timezones, calculate time differences, and format dates. Useful for scheduling, international coordination, and any task requiring accurate time awareness.

Provides access to AWS documentation and service information through the Model Context Protocol. Enables AI agents to search AWS documentation, retrieve service descriptions, look up API references, and find best practices for AWS services. Part of the official AWS Labs MCP servers collection with multiple AWS-focused servers available.

Предоставляет доступ только для чтения к базам PostgreSQL через Model Context Protocol. Позволяет AI-агентам изучать схемы баз данных, выполнять SELECT-запросы и исследовать структуру таблиц. Для защиты от случайного изменения данных использует изоляцию транзакций только для чтения. Ранее входил в набор эталонных серверов, теперь архивирован и доступен в servers-archived.

Provides browser automation capabilities through the Model Context Protocol using Puppeteer. Enables AI agents to navigate web pages, take screenshots, click elements, fill forms, and execute JavaScript in a browser context. Useful for web scraping, testing, and interacting with web applications programmatically. Originally part of the reference servers, now archived and available in servers-archived.

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.