Email Agent Mcp

Name: Email Agent Mcp
Author: UseJunior

@UseJunior

代码仓库

关于 Email Agent Mcp

Email connectivity for AI agents — MCP server for Claude Code, Gemini CLI, Cursor, and more

#mail #mcp #ai-agent #microsoft-365 #outlook #model-context-protocol #openclaw

基本信息

分类

AI 与智能体

许可证

Apache-2.0

运行时

node

传输方式

stdio

发布者

UseJunior

提交者

Steven Obiajulu

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "email-agent-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "email-agent-mcp"
      ]
    }
  }
}

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Email Agent Mcp?

Email Agent Mcp is an open-source TypeScript MCP server that lets AI agents (Claude Code, Cursor, Gemini CLI, OpenClaw, and others) read, search, draft, reply, label, mark read, move, and send email through your own mailbox. It supports Microsoft 365/Outlook and Gmail with security-first defaults that prevent agents from sending email until you explicitly configure an allowlist.

How to use Email Agent Mcp?

Run npx -y email-agent-mcp to start the interactive setup wizard, which walks you through OAuth configuration and mailbox selection. Then add the server to your MCP client’s settings (e.g., Claude Code settings.json, Cursor .cursor/mcp.json, or Gemini CLI). For OpenClaw, configure an mcp block in ~/.openclaw/openclaw.json. An optional email watcher polls your mailbox and sends wake signals to OpenClaw when new email arrives.

Key features of Email Agent Mcp

15 MCP tools for reading, writing, and managing email
Send allowlist empty by default; agents cannot send until configured
Delete disabled by default; requires explicit operator opt-in
Error sanitization that strips API keys, file paths, and stack traces
Body file sandboxing with path traversal protection
Outbound attachments via file path or inline base64 (25 MB cap)

Use cases of Email Agent Mcp

AI agents reading and summarizing recent email from your mailbox
Drafting and sending email replies under allowlist control
Full-text search across mailboxes for relevant threads
Labeling, flagging, moving, and deleting emails (with security gates)
Monitoring a mailbox for new messages and triggering agent workflows

FAQ from Email Agent Mcp

Does this work with Claude Code?

Yes. Run npx email-agent-mcp to start the MCP server, then configure it in your Claude Code settings.

Can agents send email without my permission?

No. The send allowlist is empty by default. Agents cannot send any email until you explicitly configure allowed recipients.

Does this store my email credentials?

OAuth tokens are managed by MSAL (Microsoft) and stored in your OS keychain or local config files under ~/.email-agent-mcp/. Agent Email never stores raw passwords.

Can I connect multiple mailboxes?

Yes. You can configure Microsoft 365 and Gmail simultaneously. Read actions default to your primary mailbox; write actions require specifying a mailbox when multiple are configured.

The OpenClaw CLI rejects my config with "Unrecognized key: mcp"

The OpenClaw CLI and macOS app can be different versions. The app may support config keys the CLI doesn't recognize yet. Update the CLI with npm install openclaw@latest in your NemoClaw directory, or restart the gateway directly.

AI 与智能体分类下的更多 MCP 服务器

欢迎来到智言平台

Shy2593666979

AgentChat 是一个基于 LLM 的智能体交流平台，内置默认 Agent 并支持用户自定义 Agent。通过多轮对话和任务协作，Agent 可以理解并协助完成复杂任务。项目集成 LangChain、Function Call、MCP 协议、RAG、Memory、HITL、Skill、Milvus 和 ElasticSearch 等技术，实现高效的知识检索与工具调用，使用 FastAPI 构建高性能后端服务。

797

🛡️ A.I.G（AI-Infra-Guard）

Tencent

A full-stack AI Red Teaming platform securing AI ecosystems via OpenClaw Security Scan, Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.

4.1K