Zimbra MCP Server

Zimbra MCP Server

Enables to manage Zimbra emails, tags, calendar, and contacts through natural language. Supports searching, sending, drafting emails, managing contacts, tags, and calendar events.

Category
Visit Server

README

Zimbra MCP Server

MCP (Model Context Protocol) server for Zimbra to manage emails, tags, calendar, and contacts.

Installation

cd ~/Projets/MCP/zimbra-mcp

# With uv
uv sync

# Or with pip
pip install -e .

Configuration

Create a .env file from the example:

cp .env.example .env

Configure your Zimbra credentials:

ZIMBRA_URL=https://zimbra.example.com/service/soap
ZIMBRA_USER=me@example.com
ZIMBRA_PASSWORD=your_password
ZIMBRA_TIMEOUT=30
ZIMBRA_ENABLE_SEND=false
Variable Description Default
ZIMBRA_URL Zimbra SOAP endpoint URL (required)
ZIMBRA_USER Zimbra account email (required)
ZIMBRA_PASSWORD Zimbra account password (required)
ZIMBRA_TIMEOUT Request timeout in seconds 30
ZIMBRA_ENABLE_SEND Enable send_email tool (true/1/yes) false

Usage

Start the server

uv run zimbra-mcp

Test with MCP Inspector

mcp dev src/zimbra_mcp/server.py

Available Tools

Emails

Tool Description
search_emails Search with Zimbra syntax (in:inbox, from:, tag:, etc.)
get_email Retrieve an email by ID with full body
download_attachment Download an attachment to a local file
list_folders List all mail folders
search_folder Search for a folder by name or path (case-insensitive partial match)
move_emails Move emails to a folder
mark_as_read Mark emails as read or unread
delete_emails Delete emails (soft delete to Trash, or hard delete)
create_draft Create a draft with optional reply/forward support
send_email Send an email directly (opt-in, requires ZIMBRA_ENABLE_SEND=true)

Reply & Forward Drafts

create_draft and send_email support linking to an original message for replies and forwards:

Parameter Description
orig_msg_id ID of the original message
reply_type "r" for reply, "w" for forward
include_original "inline" to quote in body, "attachment" to attach as .eml

Examples:

  • Simple draft: create_draft(to=[...], subject="...", body="...")
  • Reply with quote: create_draft(to=[...], subject="Re: ...", body="...", orig_msg_id="123", reply_type="r", include_original="inline")
  • Forward as attachment: create_draft(to=[...], subject="Fwd: ...", body="...", orig_msg_id="123", reply_type="w", include_original="attachment")

Zimbra Search Syntax

Basic operators:

  • in:inbox - Emails in inbox
  • from:john@example.com - Emails from John
  • to:me - Emails sent to me
  • tag:important - Emails with "important" tag
  • subject:meeting - Subject containing "meeting"
  • has:attachment - Emails with attachments
  • after:2024-01-01 before:2024-12-31 - Date range (ISO or MM/DD/YYYY)
  • is:unread - Unread emails
  • is:flagged - Flagged emails

Boolean operators:

  • from:john OR from:mary - Emails from John OR Mary
  • NOT is:read or -is:read - Unread emails (exclusion)
  • (from:john OR from:mary) subject:urgent - Parentheses for grouping

Combinations: in:inbox from:boss tag:urgent is:unread

Contacts

Tool Description
search_contacts Search contacts (all fields). Use "*" or empty for all
get_contact Retrieve a contact by ID
create_contact Create a contact (name, email, phone, company, etc.)
update_contact Update specific fields of an existing contact
delete_contact Delete one or more contacts

Tags

Tool Description
list_tags List all tags with colors
create_tag Create a tag (name, color)
delete_tag Delete a tag
add_tag_to_emails Add a tag to emails
remove_tag_from_emails Remove a tag

Available colors: blue, cyan, green, purple, red, yellow, pink, gray, orange

Calendar

Tool Description
get_calendar_events Events over a period
get_event_details Full details of an event
create_event Create an event
get_free_busy User availability

Development

Running tests

# Install test dependencies
uv sync --extra test

# Run tests
uv run pytest

# Verbose output
uv run pytest -v

Test structure

Tests use unittest.mock to mock the Zimbra SOAP client, so no Zimbra server is needed. The capture_tools fixture in conftest.py intercepts @mcp.tool() decorators to access tool functions directly.

Claude Code Integration

Add to your MCP configuration (~/.claude/settings.json):

{
  "mcpServers": {
    "zimbra": {
      "command": "uv",
      "args": ["run", "--directory", "/home/me/Projets/MCP/zimbra-mcp", "zimbra-mcp"],
      "env": {
        "ZIMBRA_URL": "https://zimbra.example.com/service/soap",
        "ZIMBRA_USER": "me@example.com",
        "ZIMBRA_PASSWORD": "your_password"
      }
    }
  }
}

Project Structure

zimbra-mcp/
├── pyproject.toml
├── README.md
├── CLAUDE.md
├── .env.example
├── src/
│   └── zimbra_mcp/
│       ├── __init__.py
│       ├── server.py          # FastMCP entry point
│       ├── config.py          # Configuration
│       ├── client.py          # Zimbra SOAP client
│       ├── errors.py          # Exceptions
│       └── tools/
│           ├── __init__.py
│           ├── emails.py      # Email tools
│           ├── tags.py        # Tag tools
│           ├── contacts.py    # Contact tools
│           └── calendar.py    # Calendar tools
└── tests/
    ├── conftest.py            # Shared fixtures
    ├── test_config.py
    ├── test_errors.py
    ├── test_client.py
    └── tools/
        ├── test_emails.py
        ├── test_tags.py
        ├── test_contacts.py
        └── test_calendar.py

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