EmailAssistant MCP Server

EmailAssistant MCP Server

AI-powered email assistant that enables sending, parsing, and managing emails using natural language. Provides 4 tools (smart_email, parse_email_intent, send_email, email_chat) with SSE/stdio transport support.

Category
Visit Server

README

EmailAssistant MCP Server

AI-powered email assistant. Send, parse, and manage emails using natural language. MCP server with 4 tools (smart_email, parse_email_intent, send_email, email_chat). Supports SSE/stdio transport and Bearer Token authentication.


EmailAssistant - AI 邮件助手

用自然语言发邮件的智能助手。支持 GUI、API、MCP Server 三种使用方式。

功能

  • 自然语言发邮件 — "帮我给 test@qq.com 发个会议通知" 一句话搞定
  • 多模型意图解析 — 智谱 GLM / DeepSeek / 通义千问 / Claude / 本地规则
  • 附件支持 — 自动识别文件路径并附加
  • MCP Server — 可被 Claude Code / Claude Desktop 等 AI 工具直接调用

快速开始

方式一:Windows 本机安装

# 1. 一键安装
双击 install.bat

# 2. 编辑配置(填入 LLM API Key)
编辑 config.json

# 3. 一键启动(API + GUI)
双击 start_all.bat

方式二:Docker

# 1. 准备配置
cp config.example.json config.json
# 编辑 config.json 填入 API Key

# 2. 启动
docker-compose up -d

# 3. 如需 MCP SSE 模式
docker-compose --profile mcp-sse up -d

前置依赖

  • Python 3.10+(Windows 安装)
  • EmailMarketer 服务运行在 localhost:8100(用于实际发送邮件)

配置说明

编辑 config.json:

字段 说明
model 当前使用的模型:zhipu / deepseek / qwen / claude / local
models.*.api_key 对应模型的 API Key
emailmarketer.api_url EmailMarketer API 地址(默认 http://localhost:8100)
emailmarketer.api_key EmailMarketer API Key

不想配 API Key?选择 local 模式,使用本地规则解析(无需联网)。

API 接口

启动:python run_api.py(端口 8200)

方法 路径 说明
GET /api/v1/health 健康检查
POST /api/v1/parse 意图解析({"message": "..."} → 结构化 JSON)
POST /api/v1/send 直接发邮件(to_email, subject, body, attachment_path)
POST /api/v1/chat 一步到位:解析 → 发邮件或聊天回复

MCP Server 集成

Claude Code

在项目根目录 .mcp.json 中添加:

{
  "mcpServers": {
    "email-assistant": {
      "command": "python",
      "args": ["<路径>/EmailAssistant/run_mcp.py"],
      "cwd": "<路径>/EmailAssistant",
      "env": {
        "EA_API_URL": "http://localhost:8200"
      }
    }
  }
}

Claude Desktop

在 claude_desktop_config.json 中添加相同配置。

MCP Tools

Tool 说明
smart_email(message) 自然语言发邮件
parse_email_intent(message) 仅解析意图,不发送
send_email(to_email, subject, body, attachment_path) 直接发邮件
email_chat(message) 智能聊天

SSE 模式

python run_mcp.py --transport sse --port 8201

端口分配

服务 端口
API 8200
MCP SSE 8201

项目结构

EmailAssistant/
├── main.py              # GUI 主程序
├── intent_parser.py     # 意图解析引擎
├── email_client.py      # EmailMarketer API 客户端
├── config_manager.py    # 配置管理
├── config.json          # 运行配置
├── config.example.json  # 配置模板
├── run_api.py           # FastAPI 服务
├── run_mcp.py           # MCP Server
├── requirements.txt     # Python 依赖
├── install.bat          # Windows 一键安装
├── start_all.bat        # Windows 一键启动
├── Dockerfile           # Docker 镜像
└── docker-compose.yml   # Docker 编排

Recommended Servers

playwright-mcp

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.

Official
Featured
TypeScript
Magic Component Platform (MCP)

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.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

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.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

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.

Official
Featured
TypeScript
Kagi MCP Server

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.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

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.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured