How to Use the Gmail MCP in CrewAI

Q: How do I search Gmail with my CrewAI agents?

Include listgmailmessages in your agent's tool list. Your agents will query the inbox based on the tasks you define in their role description.

Q: Can CrewAI agents read my Gmail content?

Yes, when you give them access to getmessagecontent. They parse the text to decide whether to label or archive the email.

Q: Will CrewAI automatically label my Gmail emails?

You can configure an agent to call modifymessagelabels whenever it identifies a relevant email. It acts autonomously based on your instructions.

Deploy a specialized crew of agents to manage your inbox with the Gmail MCP Server and CrewAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Gmail MCP to CrewAI

Create your Vinkius account to connect Gmail to CrewAI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Gmail with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Collaborative inbox monitoring

Assign a monitoring agent to poll your inbox using `list_unread_emails`. Once it finds a message, it hands off the data to an analytical agent for processing. This teamwork keeps your inbox organized without you touching a thing. Agents share the context of the threads they analyze via `get_thread_details`.

Specialized email response teams

Set up an agent to handle categorization using `list_mailbox_labels` while another agent performs the actual move or label update. This separation of concerns prevents errors. You get an autonomous system that acts like a real team. One agent researches, the other acts, and they both verify the state through the server tools.

Autonomous inbox cleanup

Task a moderator agent with identifying junk mail and executing `trash_gmail_message`. It reviews incoming threads against your criteria and clears the clutter. This keeps your focus on high-value threads. The agents handle the repetitive work of identifying and trashing messages based on the rules you provide.

Setup guide

Set up Gmail MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Gmail tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Gmail Analyst",
    goal="Access and analyze Gmail data via MCP.",
    backstory="Expert analyst with direct Gmail access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Gmail transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Gmail Analyst",
        goal="Access and analyze Gmail data via MCP.",
        backstory="Expert analyst with direct Gmail access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Gmail transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Gmail. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Gmail now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Gmail MCP in CrewAI

Include `list_gmail_messages` in your agent's tool list. Your agents will query the inbox based on the tasks you define in their role description.

Yes, when you give them access to `get_message_content`. They parse the text to decide whether to label or archive the email.

You can configure an agent to call `modify_message_labels` whenever it identifies a relevant email. It acts autonomously based on your instructions.

Each agent operates within the session you provide. Vinkius ensures that your endpoint token limits access only to the necessary tools.

We use a zero-trust model. The server only processes the raw email content you authorize, with no logs kept of your private messages after the agent completes its task.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript