imap-mcp
An IMAP client MCP server for reading mail from Dovecot or Synology MailPlus mailboxes, with optional webhook triggers for new messages. It provides tools for managing emails and automates workflows by firing webhooks when matching messages arrive.
README
imap-mcp
IMAP client MCP. Read mail from a Dovecot / Synology MailPlus mailbox, and optionally fire webhooks when new matching messages arrive — replaces fragile Gmail OAuth for automation triggers.
Tools
| Tool | Description |
|---|---|
list_unread(mailbox, limit) |
Unread message summaries |
search(criteria, mailbox, limit) |
Raw IMAP SEARCH |
fetch(uid, mailbox) |
Full message (headers + text + html) |
mark_read(uid, mailbox) |
Set \Seen flag |
move(uid, source, dest) |
Move to another folder |
list_folders() |
All folders |
get_status() |
IMAP ping + watcher rules + fire count |
Environment
| Variable | Required | Description |
|---|---|---|
IMAP_HOST |
✓ | Server (e.g. 192.168.68.61) |
IMAP_PORT |
Default 993 |
|
IMAP_SSL |
true (default) or false |
|
IMAP_USERNAME |
✓ | Synology account name, not email |
IMAP_PASSWORD |
✓ | |
IMAP_DEFAULT_MAILBOX |
Default INBOX |
|
WATCHES_JSON |
Inline JSON array of watch rules | |
WATCHES_FILE |
Path to JSON file (default /data/watches.json) |
|
POLL_INTERVAL_SECS |
Default 30 |
|
PORT |
MCP server port (default 38105) |
Watch rules
[
{
"name": "garmin-livetrack",
"mailbox": "INBOX",
"criteria": "FROM \"noreply@garmin.com\" SUBJECT \"LiveTrack\" UNSEEN",
"webhook_url": "http://host.docker.internal:5678/webhook/livetrack-mail",
"mark_read": true,
"move_to": null
}
]
On startup the watcher "primes" each rule with existing matching UIDs, so
only new mail after boot fires. Every POLL_INTERVAL_SECS it re-runs
each rule's criteria and POSTs matching messages (full body) to webhook_url
as { "rule": "...", "mailbox": "...", "message": {...} }. After a
successful POST it either moves the message to move_to, or marks it read
if mark_read.
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.