gmail-sorter
Enables sorting and managing Gmail messages using multi-agent Claude Code. Provides MCP tools for Gmail operations like listing unread emails and creating labels.
README
gmail-sorter
Система сортировки личного Gmail на мультиагентах Claude Code. Полная архитектура — в
architecture.md. Этот репозиторий реализует её по фазам.
Статус: Фазы 0–4. Продакшн-запуск на VPS по расписанию — см. docs/runbook.md.
Требования
- Python 3.11+
- (для живых Gmail-вызовов) OAuth-клиент из Google Cloud Console с включённым Gmail API
Установка
python -m venv .venv
# Windows PowerShell:
.venv\Scripts\Activate.ps1
# Linux/macOS:
# source .venv/bin/activate
pip install -e ".[dev]"
Тесты (работают офлайн, без Gmail-кредов)
python -m pytest
Инициализация state.db
БД создаётся автоматически при старте MCP-сервера. Вручную:
python -c "import sys; sys.path.insert(0,'mcp'); import db; db.init_db('data/state.db'); print('ok')"
OAuth (разово, требует client_secret из Google Cloud)
# Положи скачанный client_secret в .gmail-credentials.json (см. .env.example)
python mcp/google_auth.py # откроет браузер, сохранит .gmail-token.json
Создание меток Gmail (разово, после OAuth)
python scripts/setup_labels.py
Запуск MCP-сервера через Claude Code
Скопируй .claude/settings.local.json.example → .claude/settings.local.json. ВАЖНО: значение command должно указывать на python из venv (Claude Code запускает MCP-сервер отдельным процессом и НЕ наследует активированный venv): на Windows — .venv\Scripts\python.exe, на Linux VPS — .venv/bin/python. Затем в Claude Code вызови инструменты mcp__gmail__list_unread_batch и т.д.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.