mcpField
G
Gmail

Gmail

Remote
pipeworx.ioCommunication0Updated 2d ago

About Gmail

Gmail MCP Pack exposes Gmail operations to agents and other MCP clients, including searching, reading, and sending email. It also lists labels and can run as a local stdio MCP server.

Key features

  1. 01List messages by label or read status
  2. 02Fetch message bodies and attachment details
  3. 03Search with Gmail query syntax
  4. 04Send email with CC, BCC, or attachments
  5. 05List system and custom labels

Use cases

  1. 01Find unread or attachment-bearing messages
  2. 02Review email content and recipient details
  3. 03Send messages with copied recipients or files

MCP support

It provides Gmail message and label tools to MCP clients. It can connect through the Pipeworx gateway or run locally over stdio; the gateway route requires a connected Gmail account.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://gateway.pipeworx.io/gmail/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

mcp-gmail

Gmail MCP Pack

Part of Pipeworx — an MCP gateway connecting AI agents to 1879+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Tools

ToolDescription
gmail_list_messagesList messages in your inbox with optional filtering by label or read status. Returns message IDs, thread IDs, and preview text. Use gmail_search for complex queries like date ranges or attachments.
gmail_get_messageFetch full email details by message ID. Returns headers, subject, body text, sender, recipients, attachments, and applied labels.
gmail_searchSearch emails using Gmail query syntax (e.g., 'from:[email protected]', 'subject:invoice', 'has:attachment', 'after:2024/01/01', 'is:unread'). Returns matching message IDs.
gmail_sendSend an email with recipient, subject, and body text. Optionally add CC, BCC, reply-to address, and file attachments.
gmail_list_labelsGet all your labels including system folders (INBOX, SENT, TRASH, DRAFTS) and custom labels. Returns label names and IDs for filtering or organizing.

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "gmail": {
      "url": "https://gateway.pipeworx.io/gmail/mcp"
    }
  }
}
What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/gmail/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — ask_pipeworx, discover_tools, search_within, remember/recall and the rest of the gateway-wide set. So the tool count you see is larger than this table: a single-pack endpoint currently lists roughly 30 shared tools alongside the pack's own. The connection's initialize response states its exact scope, and is the authoritative answer for a given day.

This is deliberate, not multiplexing by accident. The meta-tools are what let a scoped connection answer a question this pack does not cover — via ask_pipeworx, which routes across the whole catalog — without you adding a second MCP server. There is currently no way to mount a pack endpoint without them; if the extra schemas cost you more context than the routing is worth, connect to the full gateway once rather than to several pack endpoints.

Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:

{
  "mcpServers": {
    "pipeworx": {
      "url": "https://gateway.pipeworx.io/mcp"
    }
  }
}

Both URLs reach the same gateway and the same 1879+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.

No MCP client? Call it over HTTP

This pack runs against a connected gmail account, so it needs a Pipeworx key: sign in at https://pipeworx.io/account, connect gmail, then call POST https://gateway.pipeworx.io/v1/tools/gmail_list_messages with Authorization: Bearer <your Pipeworx key>. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/gmail_list_messages. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.

Standalone (no gateway account)

This package also runs as a local stdio MCP server — no Pipeworx account, no gateway round-trip:

{
  "mcpServers": {
    "gmail": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-gmail"]
    }
  }
}

Or run it directly to confirm it starts:

npx -y @pipeworx/mcp-gmail

It speaks MCP over stdin/stdout and answers initialize/tools/list/tools/call for only this pack's tools — none of the shared meta-tools the gateway connection above adds. Same source, same tools, no ask_pipeworx routing.

Using with ask_pipeworx

Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:

ask_pipeworx({ question: "your question about Gmail data" })

The gateway picks the right tool and fills the arguments automatically.

More

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.