About
Gmail API Integration Server provides comprehensive access to Gmail's email management capabilities through the Model Context Protocol. It enables AI assistants to interact with Gmail accounts for sending, organizing, and managing emails programmatically. Key features: - Send emails and create drafts directly from Gmail accounts - Retrieve, search, and manage messages and conversation threads - Organize emails with label management including custom colors and visibility settings - Configure mailbox settings including vacation responders, IMAP/POP access, and language preferences - Track mailbox history and monitor changes - Secure OAuth2 authentication through Google Cloud credentials
Tools 64
create_draftCreate a draft email in Gmail. Note the mechanics of the raw parameter.
delete_draftDelete a draft
get_draftGet a specific draft by ID
list_draftsList drafts in the user's mailbox
send_draftSend an existing draft
create_labelCreate a new label
delete_labelDelete a label
get_labelGet a specific label by ID
list_labelsList all labels in the user's mailbox
patch_labelPatch an existing label (partial update)
update_labelUpdate an existing label
batch_delete_messagesDelete multiple messages
batch_modify_messagesModify the labels on multiple messages
delete_messageImmediately and permanently delete a message
get_messageGet a specific message by ID with format options
list_messagesList messages in the user's mailbox with optional filtering
modify_messageModify the labels on a message
send_messageSend an email message to specified recipients. Note the mechanics of the raw parameter.
trash_messageMove a message to the trash
untrash_messageRemove a message from the trash
get_attachmentGet a message attachment
delete_threadDelete a thread
get_threadGet a specific thread by ID
list_threadsList threads in the user's mailbox
modify_threadModify the labels applied to a thread
trash_threadMove a thread to the trash
untrash_threadRemove a thread from the trash
get_auto_forwardingGets auto-forwarding settings
get_imapGets IMAP settings
get_languageGets language settings
get_popGets POP settings
get_vacationGet vacation responder settings
update_auto_forwardingUpdates automatic forwarding settings
update_imapUpdates IMAP settings
update_languageUpdates language settings
update_popUpdates POP settings
update_vacationUpdate vacation responder settings
add_delegateAdds a delegate to the specified account
remove_delegateRemoves the specified delegate
get_delegateGets the specified delegate
list_delegatesLists the delegates for the specified account
create_filterCreates a filter
delete_filterDeletes a filter
get_filterGets a filter
list_filtersLists the message filters of a Gmail user
create_forwarding_addressCreates a forwarding address
delete_forwarding_addressDeletes the specified forwarding address
get_forwarding_addressGets the specified forwarding address
list_forwarding_addressesLists the forwarding addresses for the specified account
create_send_asCreates a custom send-as alias
delete_send_asDeletes the specified send-as alias
get_send_asGets the specified send-as alias
list_send_asLists the send-as aliases for the specified account
patch_send_asPatches the specified send-as alias
update_send_asUpdates a send-as alias
verify_send_asSends a verification email to the specified send-as alias
delete_smime_infoDeletes the specified S/MIME config for the specified send-as alias
get_smime_infoGets the specified S/MIME config for the specified send-as alias
insert_smime_infoInsert (upload) the given S/MIME config for the specified send-as alias
list_smime_infoLists S/MIME configs for the specified send-as alias
set_default_smime_infoSets the default S/MIME config for the specified send-as alias
get_profileGet the current user's Gmail profile
watch_mailboxWatch for changes to the user's mailbox
stop_mail_watchStop receiving push notifications for the given user mailbox
README
Gmail MCP
[](https://badge.fury.io/js/@shinzolabs%2Fgmail-mcp) [](https://smithery.ai/server/@shinzo-labs/gmail-mcp)
A Model Context Protocol (MCP) implementation for the Gmail API, providing a standardized interface for email management, sending, and retrieval.
Features
Prerequisites
To run this MCP server, you first need to set up a Google API Client for your organization, with each user running a script to retrieve their own OAuth refresh token.
Google API Client Setup (once per organization)
1. Go to the Google Cloud Console.
2. Create a new project or select an existing one.
3. Enable the Gmail API for your project.
4. Go to Credentials and create an OAuth 2.0 Client ID. Choose "Desktop app" for the client type.
5. Download and save the OAuth keys JSON as ~/.gmail-mcp/gcp-oauth.keys.json. ⚠️ NOTE: to create ~/.gmail-mcp/ through MacOS's Finder app you need to enable hidden files first.
6. (Optional) For remote server installation (ex. using Smithery CLI), note the CLIENT_ID and CLIENT_SECRET from this file.
Client OAuth (once per user)
1. Have the user copy ~/.gmail-mcp/gcp-oauth.keys.json to their computer at the same path.
2. Run npx @shinzolabs/gmail-mcp auth.
3. A browser window will open where the user may select a profile, review the requested scopes, and approve.
4. (Optional) For remote server installation, note the file path mentioned in the success message (~/.gmail-mcp/credentials.json by default). The user's REFRESH_TOKEN will be found here.
Client Configuration
There are several options to configure your MCP client with the server. For hosted/remote server setup, use Smithery's CLI with a Smithery API Key. For local installation, use npx or build from source. Each of these options is explained below.
Smithery Remote Server (Recommended)
To add a remote server to your MCP client config.json, run the following command from Smithery CLI:
npx -y @smithery/cli install @shinzo-labs/gmail-mcp
Enter your CLIENT_ID, CLIENT_SECRET, and REFRESH_TOKEN when prompted.
Smithery SDK
If you are developing your own agent application, you can use the boilerplate code here.
NPX Local Install
To install the server locally with npx, add the following to your MCP client config.json:
{
"mcpServers": {
"gmail": {
"command": "npx",
"args": [
"@shinzolabs/gmail-mcp"
]
}
}
}
Build from Source
1. Download the repo:
git clone https://github.com/shinzo-labs/gmail-mcp.git
2. Install packages and build with pnpm (inside cloned repo):
pnpm i && pnpm build
3. Add the following to your MCP client config.json:
{
"mcpServers": {
"gmail": {
"command": "node",
"args": [
"/path/to/gmail-mcp/dist/index.js"
]
}
}
}
Config Variables
| Variable | Description | Required? | Default |
|--------------------------|---------------------------------------------------------|---------------------------------|--------------------------------------|
| AUTH_SERVER_PORT | Port for the temporary OAuth authentication server | No | 3000 |
| CLIENT_ID | Google API client ID (found in GMAIL_OAUTH_PATH) | Yes if remote server connection | '' |
| CLIENT_SECRET | Google API client secret (found in GMAIL_OAUTH_PATH) | Yes if remote server connection | '' |
| GMAIL_CREDENTIALS_PATH | Path to the user credentials file | No | MCP_CONFIG_DIR/credentials.json |
| `GM
Related MCP Servers
AI Research Assistant
hamid-vakilzadeh
AI Research Assistant provides comprehensive access to millions of academic papers through the Semantic Scholar and arXiv databases. This MCP server enables AI coding assistants to perform intelligent literature searches, citation network analysis, and paper content extraction without requiring an API key. Key features include: - Advanced paper search with multi-filter support by year ranges, citation thresholds, field of study, and publication type - Title matching with confidence scoring for finding specific papers - Batch operations supporting up to 500 papers per request - Citation analysis and network exploration for understanding research relationships - Full-text PDF extraction from arXiv and Wiley open-access content (Wiley TDM token required for institutional access) - Rate limits of 100 requests per 5 minutes with options to request higher limits through Semantic Scholar
Linkup
LinkupPlatform
Linkup is a real-time web search and content extraction service that enables AI assistants to search the web and retrieve information from trusted sources. It provides source-backed answers with citations, making it ideal for fact-checking, news gathering, and research tasks. Key features of Linkup: - Real-time web search using natural language queries to find current information, news, and data - Page fetching to extract and read content from any webpage URL - Search depth modes: Standard for direct-answer queries and Deep for complex research across multiple sources - Source-backed results with citations and context from relevant, trustworthy websites - JavaScript rendering support for accessing dynamic content on JavaScript-heavy pages
Math-MCP
EthanHenrickson
Math-MCP is a computation server that enables Large Language Models (LLMs) to perform accurate numerical calculations through the Model Context Protocol. It provides precise mathematical operations via a simple API to overcome LLM limitations in arithmetic and statistical reasoning. Key features of Math-MCP: - Basic arithmetic operations: addition, subtraction, multiplication, division, modulo, and bulk summation - Statistical analysis functions: mean, median, mode, minimum, and maximum calculations - Rounding utilities: floor, ceiling, and nearest integer rounding - Trigonometric functions: sine, cosine, tangent, and their inverses with degrees and radians conversion support