Email Reader
Read, search, and manage emails from your inbox, including downloading attachments and listing folders.
mcp_email_reader
Model Context Protocol (MCP) server exposes several mcp tools called search_emails, download_attachment and list_folders. This has been tested on Claude Desktop and LibreChat with Ollama.
Installation
Prerequisites
Windows
-
Install Claude Desktop (or another MCP-enabled AI tool)
- Download Claude for Desktop
- Follow the current installation instructions: Installing Claude Desktop
-
Install Python 3.10 or higher:
- Download the latest Python installer from python.org
- Run the installer, checking "Add Python to PATH"
- Open Command Prompt and verify installation with
python --version
-
Install uv:
- Open Command Prompt as Administrator
- Run
pip install --user uv - Verify installation with
uv --version
macOS
-
Install Claude Desktop (or another MCP-enabled AI tool)
- Download Claude for Desktop
- Follow the current installation instructions: Installing Claude Desktop
-
Install Python 3.10 or higher:
- Using Homebrew:
brew install python - Verify installation with
python3 --version
- Using Homebrew:
-
Install uv:
- Using Homebrew:
brew install uv - Alternatively:
pip3 install --user uv - Verify installation with
uv --version
- Using Homebrew:
Configuration
Add the following to your claude_desktop_config.json:
{
"mcpServers": {
"mcp_email_reader": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/karateboss/mcp_email_reader@main",
"mcp_email_reader"
],
"env": {
"IMAP_SERVER": "<email server>",
"EMAIL_ACCOUNT": "<user email account>",
"EMAIL_PASSWORD_ENC": "<encrypted password>"
"EMAIL_SECRET_KEY": "<secret key used to encypt password>"
}
}
}
Note: Clearly, the secret key can be used to decrypt the encrypted password and is therefore a potential security risk - although claude_desktop_config.json is stored locally on your laptop/PC. It has been added to the json file above since it is not possible to add a .env file when using uvx to clone the repo dynamically.
Attribution
This software package implements the ability to read emails into a MCP enabled framework and is developed by karateboss.
Contributing
We welcome contributions to improve these tools. Please submit issues and pull requests through our repository.
Support
For questions and support:
- Check our documentation
- Submit an issue in our repository
Máy chủ liên quan
TradingView Backtest Assistant”
exposes a remote MCP endpoint so agents can: run strategy backtests by symbol/timeframe/date range, pass strategy inputs programmatically,receive structured backtest results (trades, win rate, profit, drawdown).
Lobster Roll
Agent-native messaging — where AI agents and humans are equal participants. Open source, self-hostable, MCP-ready.
API Docs MCP
MCP server for API documentation, supporting GraphQL, OpenAPI/Swagger, and gRPC from local files or remote URLs
MCP Chat Desktop App
A cross-platform desktop app for interacting with various Large Language Models (LLMs) through the Model Context Protocol (MCP).
MCP Server Whisper
Advanced audio transcription and processing using OpenAI's Whisper and GPT-4o models.
Ayni Protocol
Visual coordination protocol for AI agents — 22 MCP tools for glyph-based communication with 50-70% token savings, shared memory, governance, and on-chain attestation.
WhatsApp
Search, read, and send WhatsApp messages and contacts. Requires a local Go WhatsApp bridge.
Desktop Notification
Send cross-platform desktop notifications from AI assistants.
DingDing Bot
Send various types of messages, including text, markdown, images, and files, to a DingDing group robot.
LnExchange MCP Node Service
A Node.js service for interacting with the LnExchange API for spot trading.